Ronghang Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ronghang Zhu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Sheng Li
University of Virginia, Charlottesville, Virginia, USA
10 shared publications - Pengsheng Ji
Department of Statistics, University of Georgia
3 shared publications - Weili Shi
School of Data Science, University of Virginia, Charlottesville, VA, USA
3 shared publications - Dongliang Guo
University of Virginia University of Virginia University of Virginia The University of Texas at Dallas University of Virginia University of Virginia
2 shared publications - Ernest Mwebaze
College of Computing & IS, Makerere University, P.O. Box 7062, Kampala, Uganda
2 shared publications - Juliet Nabbuye Sekandi
University of Georgia
2 shared publications
Latest Publications
- Open Access
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs.
Open AccessNo Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilities of large language models (LLMs). However, is this effectiveness and cost-efficiency truly a free lunch? In this study, we comprehensively investigate the fairness costs associated with RAG by proposing a practical three-level threat model from the perspective of user awareness of fairness. Specifically, varying levels of user fairness awareness result in different degrees of fairness censorship on the external dataset. We examine the fairness implications of RAG using uncensored, partially censored, and fully censored datasets. Our experiments demonstrate that fairness alignment can be easily undermined through RAG without the need for fine-tuning or retraining. Even with fully censored and supposedly unbiased external datasets, RAG can lead to biased outputs. Our findings underscore the limitations of current alignment methods in the context of RAG-based LLMs and highlight the urgent need for new strategies to ensure fairness. We propose potential mitigations and call for further research to develop robust fairness safeguards in RAG-based LLMs.
- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34  (12) , 12411-12424
Unsupervised Class-Imbalanced Domain Adaptation With Pairwise Adversarial Training and Semantic Alignment
Unsupervised domain adaptation (UDA) has become an appealing approach for knowledge transfer from a labeled source domain to an unlabeled target domain. However, when the classes in source and target domains are imbalanced, most existing UDA methods experience significant performance drop, as the decision boundary usually favors the majority classes. Some recent class-imbalanced domain adaptation (CDA) methods aim to tackle the challenge of biased label distribution by exploiting pseudo-labeled target samples during the training process. However, these methods suffer from the issues with unreliable pseudo labels and error accumulation during training. In this paper, we propose a pairwise adversarial training approach for class-imbalanced domain adaptation. Unlike conventional adversarial training in which the adversarial samples are obtained from the â„“ p ball of the original samples, we generate adversarial samples from the interpolated line of the aligned pairwise samples from source and target domains. The pairwise adversarial training (PAT) is a novel data-augmentation method which can be integrated into existing unsupervised domain adaptation (UDA) models to tackle the CDA problem. Inspired by the noise injection, we also extend the pairwise adversarial training to noisy pairwise adversarial training (nPAT), in which the random noise is injected into the generation of the adversarial samples. In our study, we evaluate our proposed methods as well as the baselines on three major benchmark datasets, namely Office-Home, DomainNet and Office-31. For Office-Home and Office-31, we sample the data according to the Reversely-unbalanced Source and Unbalanced Target (RS-UT) protocol so that the class distribution can be imbalanced. The extensive experimental results show that UDA models integrated with our proposed nPAT can achieve prominent improvements on most tasks compared to the baseline methods as well as the state-of-the-art CDA methods. The average accuracy of our nPAT can achieve 66.56% and 80.22% on Office-Home and DomainNet, respectively, which are higher than that of the second-best methods. Besides, Experiments also show that our method is robust to the unreliability of the pseudo labels.
- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34  (12) , 12411-12424
Unsupervised Class-Imbalanced Domain Adaptation With Pairwise Adversarial Training and Semantic Alignment
Unsupervised domain adaptation (UDA) has become an appealing approach for knowledge transfer from a labeled source domain to an unlabeled target domain. However, when the classes in source and target domains are imbalanced, most existing UDA methods experience significant performance drop, as the decision boundary usually favors the majority classes. Some recent class-imbalanced domain adaptation (CDA) methods aim to tackle the challenge of biased label distribution by exploiting pseudo-labeled target samples during the training process. However, these methods suffer from the issues with unreliable pseudo labels and error accumulation during training. In this paper, we propose a pairwise adversarial training approach for class-imbalanced domain adaptation. Unlike conventional adversarial training in which the adversarial samples are obtained from the â„“ p ball of the original samples, we generate adversarial samples from the interpolated line of the aligned pairwise samples from source and target domains. The pairwise adversarial training (PAT) is a novel data-augmentation method which can be integrated into existing unsupervised domain adaptation (UDA) models to tackle the CDA problem. Inspired by the noise injection, we also extend the pairwise adversarial training to noisy pairwise adversarial training (nPAT), in which the random noise is injected into the generation of the adversarial samples. In our study, we evaluate our proposed methods as well as the baselines on three major benchmark datasets, namely Office-Home, DomainNet and Office-31. For Office-Home and Office-31, we sample the data according to the Reversely-unbalanced Source and Unbalanced Target (RS-UT) protocol so that the class distribution can be imbalanced. The extensive experimental results show that UDA models integrated with our proposed nPAT can achieve prominent improvements on most tasks compared to the baseline methods as well as the state-of-the-art CDA methods. The average accuracy of our nPAT can achieve 66.56% and 80.22% on Office-Home and DomainNet, respectively, which are higher than that of the second-best methods. Besides, Experiments also show that our method is robust to the unreliability of the pseudo labels.
- Open Access
- 19 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18  (7) , 1-53
A Survey of Trustworthy Representation Learning Across Domains
As AI systems have obtained significant performance to be deployed widely in our daily lives and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts of AI systems, and representation learning is the fundamental technology in machine learning. How to make representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework, which includes four concepts, i.e., robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions.
- 19 June 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18  (7) , 1-53
Open AccessA Survey of Trustworthy Representation Learning Across Domains
As AI systems have obtained significant performance to be deployed widely in our daily lives and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts of AI systems, and representation learning is the fundamental technology in machine learning. How to make representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework, which includes four concepts, i.e., robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38  (8) , 9142-9150
Open-Set Graph Domain Adaptation via Separate Domain Alignment
Domain adaptation has become an attractive learning paradigm, as it can leverage source domains with rich labels to deal with classification tasks in an unlabeled target domain. A few recent studies develop domain adaptation approaches for graph-structured data. In the case of node classification task, current domain adaptation methods only focus on the closed-set setting, where source and target domains share the same label space. A more practical assumption is that the target domain may contain new classes that are not included in the source domain. Therefore, in this paper, we introduce a novel and challenging problem for graphs, i.e., open-set domain adaptive node classification, and propose a new approach to solve it. Specifically, we develop an algorithm for efficient knowledge transfer from a labeled source graph to an unlabeled target graph under a separate domain alignment (SDA) strategy, in order to learn discriminative feature representations for the target graph. Our goal is to not only correctly classify target nodes into the known classes, but also classify unseen types of nodes into an unknown class. Experimental results on real-world datasets show that our method outperforms existing methods on graph domain adaptation.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38  (8) , 9142-9150
Open AccessOpen-Set Graph Domain Adaptation via Separate Domain Alignment
Domain adaptation has become an attractive learning paradigm, as it can leverage source domains with rich labels to deal with classification tasks in an unlabeled target domain. A few recent studies develop domain adaptation approaches for graph-structured data. In the case of node classification task, current domain adaptation methods only focus on the closed-set setting, where source and target domains share the same label space. A more practical assumption is that the target domain may contain new classes that are not included in the source domain. Therefore, in this paper, we introduce a novel and challenging problem for graphs, i.e., open-set domain adaptive node classification, and propose a new approach to solve it. Specifically, we develop an algorithm for efficient knowledge transfer from a labeled source graph to an unlabeled target graph under a separate domain alignment (SDA) strategy, in order to learn discriminative feature representations for the target graph. Our goal is to not only correctly classify target nodes into the known classes, but also classify unseen types of nodes into an unknown class. Experimental results on real-world datasets show that our method outperforms existing methods on graph domain adaptation.
- Open Access
Trustworthy Representation Learning Across Domains
As AI systems have obtained significant performance to be deployed widely in our daily live and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts for AI systems and representation learning is the fundamental technology in machine learning. How to make the representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework which includes four concepts, i.e, robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions.
Open AccessTrustworthy Representation Learning Across Domains
As AI systems have obtained significant performance to be deployed widely in our daily live and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts for AI systems and representation learning is the fundamental technology in machine learning. How to make the representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework which includes four concepts, i.e, robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions.
- Open Access
- 23 February 2023
- Published by JMIR Publications Inc. in JMIR AI
- Vol. 2  (1) , e40167
Application of Artificial Intelligence to the Monitoring of Medication Adherence for Tuberculosis Treatment in Africa: Algorithm Development and Validation
Background: Artificial intelligence (AI) applications based on advanced deep learning methods in image recognition tasks can increase efficiency in the monitoring of medication adherence through automation. AI has sparsely been evaluated for the monitoring of medication adherence in clinical settings. However, AI has the potential to transform the way health care is delivered even in limited-resource settings such as Africa. Objective: We aimed to pilot the development of a deep learning model for simple binary classification and confirmation of proper medication adherence to enhance efficiency in the use of video monitoring of patients in tuberculosis treatment. Methods: We used a secondary data set of 861 video images of medication intake that were collected from consenting adult patients with tuberculosis in an institutional review board–approved study evaluating video-observed therapy in Uganda. The video images were processed through a series of steps to prepare them for use in a training model. First, we annotated videos using a specific protocol to eliminate those with poor quality. After the initial annotation step, 497 videos had sufficient quality for training the models. Among them, 405 were positive samples, whereas 92 were negative samples. With some preprocessing techniques, we obtained 160 frames with a size of 224 × 224 in each video. We used a deep learning framework that leveraged 4 convolutional neural networks models to extract visual features from the video frames and automatically perform binary classification of adherence or nonadherence. We evaluated the diagnostic properties of the different models using sensitivity, specificity, F1-score, and precision. The area under the curve (AUC) was used to assess the discriminative performance and the speed per video review as a metric for model efficiency. We conducted a 5-fold internal cross-validation to determine the diagnostic and discriminative performance of the models. We did not conduct external validation due to a lack of publicly available data sets with specific medication intake video frames. Results: Diagnostic properties and discriminative performance from internal cross-validation were moderate to high in the binary classification tasks with 4 selected automated deep learning models. The sensitivity ranged from 92.8 to 95.8%, specificity from 43.5 to 55.4%, F1-score from 0.91 to 0.92, precision from 88% to 90.1%, and AUC from 0.78 to 0.85. The 3D ResNet model had the highest precision, AUC, and speed. Conclusions: All 4 deep learning models showed comparable diagnostic properties and discriminative performance. The findings serve as a reasonable proof of concept to support the potential application of AI in the binary classification of video frames to predict medication adherence.
- 23 February 2023
- Published by JMIR Publications Inc. in JMIR AI
- Vol. 2  (1) , e40167
Open AccessApplication of Artificial Intelligence to the Monitoring of Medication Adherence for Tuberculosis Treatment in Africa: Algorithm Development and Validation
Background: Artificial intelligence (AI) applications based on advanced deep learning methods in image recognition tasks can increase efficiency in the monitoring of medication adherence through automation. AI has sparsely been evaluated for the monitoring of medication adherence in clinical settings. However, AI has the potential to transform the way health care is delivered even in limited-resource settings such as Africa. Objective: We aimed to pilot the development of a deep learning model for simple binary classification and confirmation of proper medication adherence to enhance efficiency in the use of video monitoring of patients in tuberculosis treatment. Methods: We used a secondary data set of 861 video images of medication intake that were collected from consenting adult patients with tuberculosis in an institutional review board–approved study evaluating video-observed therapy in Uganda. The video images were processed through a series of steps to prepare them for use in a training model. First, we annotated videos using a specific protocol to eliminate those with poor quality. After the initial annotation step, 497 videos had sufficient quality for training the models. Among them, 405 were positive samples, whereas 92 were negative samples. With some preprocessing techniques, we obtained 160 frames with a size of 224 × 224 in each video. We used a deep learning framework that leveraged 4 convolutional neural networks models to extract visual features from the video frames and automatically perform binary classification of adherence or nonadherence. We evaluated the diagnostic properties of the different models using sensitivity, specificity, F1-score, and precision. The area under the curve (AUC) was used to assess the discriminative performance and the speed per video review as a metric for model efficiency. We conducted a 5-fold internal cross-validation to determine the diagnostic and discriminative performance of the models. We did not conduct external validation due to a lack of publicly available data sets with specific medication intake video frames. Results: Diagnostic properties and discriminative performance from internal cross-validation were moderate to high in the binary classification tasks with 4 selected automated deep learning models. The sensitivity ranged from 92.8 to 95.8%, specificity from 43.5 to 55.4%, F1-score from 0.91 to 0.92, precision from 88% to 90.1%, and AUC from 0.78 to 0.85. The 3D ResNet model had the highest precision, AUC, and speed. Conclusions: All 4 deep learning models showed comparable diagnostic properties and discriminative performance. The findings serve as a reasonable proof of concept to support the potential application of AI in the binary classification of video frames to predict medication adherence.
- Open Access
- 8 June 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Application of Artificial Intelligence to the Monitoring of Medication Adherence for Tuberculosis Treatment in Africa: Algorithm Development and Validation (Preprint)
BACKGROUND Artificial intelligence (AI) applications based on advanced deep learning methods in image recognition tasks can increase efficiency in the monitoring of medication adherence through automation. AI has sparsely been evaluated for the monitoring of medication adherence in clinical settings. However, AI has the potential to transform the way health care is delivered even in limited-resource settings such as Africa. OBJECTIVE We aimed to pilot the development of a deep learning model for simple binary classification and confirmation of proper medication adherence to enhance efficiency in the use of video monitoring of patients in tuberculosis treatment. METHODS We used a secondary data set of 861 video images of medication intake that were collected from consenting adult patients with tuberculosis in an institutional review board–approved study evaluating video-observed therapy in Uganda. The video images were processed through a series of steps to prepare them for use in a training model. First, we annotated videos using a specific protocol to eliminate those with poor quality. After the initial annotation step, 497 videos had sufficient quality for training the models. Among them, 405 were positive samples, whereas 92 were negative samples. With some preprocessing techniques, we obtained 160 frames with a size of 224 × 224 in each video. We used a deep learning framework that leveraged 4 convolutional neural networks models to extract visual features from the video frames and automatically perform binary classification of adherence or nonadherence. We evaluated the diagnostic properties of the different models using sensitivity, specificity, F1-score, and precision. The area under the curve (AUC) was used to assess the discriminative performance and the speed per video review as a metric for model efficiency. We conducted a 5-fold internal cross-validation to determine the diagnostic and discriminative performance of the models. We did not conduct external validation due to a lack of publicly available data sets with specific medication intake video frames. RESULTS Diagnostic properties and discriminative performance from internal cross-validation were moderate to high in the binary classification tasks with 4 selected automated deep learning models. The sensitivity ranged from 92.8 to 95.8%, specificity from 43.5 to 55.4%, F1-score from 0.91 to 0.92, precision from 88% to 90.1%, and AUC from 0.78 to 0.85. The 3D ResNet model had the highest precision, AUC, and speed. CONCLUSIONS All 4 deep learning models showed comparable diagnostic properties and discriminative performance. The findings serve as a reasonable proof of concept to support the potential application of AI in the binary classification of video frames to predict medication adherence.
- 8 June 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessApplication of Artificial Intelligence to the Monitoring of Medication Adherence for Tuberculosis Treatment in Africa: Algorithm Development and Validation (Preprint)
BACKGROUND Artificial intelligence (AI) applications based on advanced deep learning methods in image recognition tasks can increase efficiency in the monitoring of medication adherence through automation. AI has sparsely been evaluated for the monitoring of medication adherence in clinical settings. However, AI has the potential to transform the way health care is delivered even in limited-resource settings such as Africa. OBJECTIVE We aimed to pilot the development of a deep learning model for simple binary classification and confirmation of proper medication adherence to enhance efficiency in the use of video monitoring of patients in tuberculosis treatment. METHODS We used a secondary data set of 861 video images of medication intake that were collected from consenting adult patients with tuberculosis in an institutional review board–approved study evaluating video-observed therapy in Uganda. The video images were processed through a series of steps to prepare them for use in a training model. First, we annotated videos using a specific protocol to eliminate those with poor quality. After the initial annotation step, 497 videos had sufficient quality for training the models. Among them, 405 were positive samples, whereas 92 were negative samples. With some preprocessing techniques, we obtained 160 frames with a size of 224 × 224 in each video. We used a deep learning framework that leveraged 4 convolutional neural networks models to extract visual features from the video frames and automatically perform binary classification of adherence or nonadherence. We evaluated the diagnostic properties of the different models using sensitivity, specificity, F1-score, and precision. The area under the curve (AUC) was used to assess the discriminative performance and the speed per video review as a metric for model efficiency. We conducted a 5-fold internal cross-validation to determine the diagnostic and discriminative performance of the models. We did not conduct external validation due to a lack of publicly available data sets with specific medication intake video frames. RESULTS Diagnostic properties and discriminative performance from internal cross-validation were moderate to high in the binary classification tasks with 4 selected automated deep learning models. The sensitivity ranged from 92.8 to 95.8%, specificity from 43.5 to 55.4%, F1-score from 0.91 to 0.92, precision from 88% to 90.1%, and AUC from 0.78 to 0.85. The 3D ResNet model had the highest precision, AUC, and speed. CONCLUSIONS All 4 deep learning models showed comparable diagnostic properties and discriminative performance. The findings serve as a reasonable proof of concept to support the potential application of AI in the binary classification of video frames to predict medication adherence.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34  (8) , 3847-3858
Cross-Domain Graph Convolutions for Adversarial Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) has attracted increasing attention in recent years, which adapts classifiers to an unlabeled target domain by exploiting a labeled source domain. To reduce the discrepancy between source and target domains, adversarial learning methods are typically selected to seek domain-invariant representations by confusing the domain discriminator. However, classifiers may not be well adapted to such a domain-invariant representation space, as the sample- and class-level data structures could be distorted during adversarial learning. In this article, we propose a novel transferable feature learning approach on graphs (TFLG) for unsupervised adversarial domain adaptation (DA), which jointly incorporates sample- and class-level structure information across two domains. TFLG first constructs graphs for minibatch samples and identifies the classwise correspondence across domains. A novel cross-domain graph convolutional operation is designed to jointly align the sample- and class-level structures in two domains. Moreover, a memory bank is designed to further exploit the class-level information. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach compared to the state-of-the-art UDA methods.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34  (8) , 3847-3858
Cross-Domain Graph Convolutions for Adversarial Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) has attracted increasing attention in recent years, which adapts classifiers to an unlabeled target domain by exploiting a labeled source domain. To reduce the discrepancy between source and target domains, adversarial learning methods are typically selected to seek domain-invariant representations by confusing the domain discriminator. However, classifiers may not be well adapted to such a domain-invariant representation space, as the sample- and class-level data structures could be distorted during adversarial learning. In this article, we propose a novel transferable feature learning approach on graphs (TFLG) for unsupervised adversarial domain adaptation (DA), which jointly incorporates sample- and class-level structure information across two domains. TFLG first constructs graphs for minibatch samples and identifies the classwise correspondence across domains. A novel cross-domain graph convolutional operation is designed to jointly align the sample- and class-level structures in two domains. Moreover, a memory bank is designed to further exploit the class-level information. Extensive experiments on benchmark datasets demonstrate the effectiveness of our approach compared to the state-of-the-art UDA methods.
- Open Access
Co-embedding of Nodes and Edges with Graph Neural Networks
Graph, as an important data representation, is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space to a low dimensional and structural space, which is easily exploited by other machine learning algorithms. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as the graph convolutional networks (GCN). Deep learning approaches usually outperform the traditional methods in most graph learning benchmarks by building an end-to-end learning framework to optimize the loss function directly. However, most of the existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features, such as relations in knowledge graphs. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network, for learning tasks in graph-structured data with both node and edge features. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance in four graph learning tasks, including semi-supervised node classification, multi-task graph classification, graph regression, and link prediction.
Open AccessCo-embedding of Nodes and Edges with Graph Neural Networks
Graph, as an important data representation, is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode the data structure in high dimensional and non-Euclidean feature space to a low dimensional and structural space, which is easily exploited by other machine learning algorithms. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as the graph convolutional networks (GCN). Deep learning approaches usually outperform the traditional methods in most graph learning benchmarks by building an end-to-end learning framework to optimize the loss function directly. However, most of the existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features, such as relations in knowledge graphs. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network, for learning tasks in graph-structured data with both node and edge features. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance in four graph learning tasks, including semi-supervised node classification, multi-task graph classification, graph regression, and link prediction.
- Top Cited Papers
- 14 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45  (6) , 7075-7086
Co-Embedding of Nodes and Edges With Graph Neural Networks
Graph is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode data structure in high dimensional and Non-Euclidean feature space to a low dimensional and structural space. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as graph convolutional networks (GCN). However, most of existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network for learning tasks in graph-structured data with both node and edge features. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance, in four graph learning tasks including semi-supervised node classification, multi-task graph classification, graph regression and link prediction.
- 14 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45  (6) , 7075-7086
Top Cited PapersCo-Embedding of Nodes and Edges With Graph Neural Networks
Graph is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode data structure in high dimensional and Non-Euclidean feature space to a low dimensional and structural space. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as graph convolutional networks (GCN). However, most of existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network for learning tasks in graph-structured data with both node and edge features. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance, in four graph learning tasks including semi-supervised node classification, multi-task graph classification, graph regression and link prediction.