Liang Lan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liang Lan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Yupeng Li
Department of Interactive Media, Hong Kong Baptist University, Hong Kong, China
3 shared publications - Yifeng Luo
Department of Interactive Media, Hong Kong Baptist University, Hong Kong, China and AI and Social Good Lab, AI Media Centre, Hong Kong Baptist University, Hong Kong, China
2 shared publications - Yu Geng
Department of Computer Science, Hong Kong Baptist University, Kowloon Tsai, Hong Kong
2 shared publications - Dacheng Wen
Department of Interactive Media, Hong Kong Baptist University, Hong Kong, China and School of Computing and Data Science, The University of Hong Kong, Hong Kong, China
1 shared publication Jun Wang
School of Computer Science and Software Engineering, East China Normal University, Shanghai 200062, China
1 shared publicationJuyong Jiang
Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7352-7360
From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7352-7360
Open AccessFrom Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
- Open Access
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10257-10270
Convolution Filter Compression via Sparse Linear Combinations of Quantized Basis
Convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks. However, the large number of parameters in convolutional layers requires huge storage and computation resources, making it challenging to deploy CNNs on memory-constrained embedded devices. In this article, we propose a novel compression method that generates the convolution filters in each layer using a set of learnable low-dimensional quantized filter bases. The proposed method reconstructs the convolution filters by stacking the linear combinations of these filter bases. By using quantized values in weights, the compact filters can be represented using fewer bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficients through $L_1$ -ball projection when conducting linear combination to further reduce the storage consumption and prevent overfitting. We also provide a detailed analysis of the compression performance of the proposed method. Evaluations of image classification and object detection tasks using various network structures demonstrate that the proposed method achieves a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.
- 24 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10257-10270
Open AccessConvolution Filter Compression via Sparse Linear Combinations of Quantized Basis
Convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks. However, the large number of parameters in convolutional layers requires huge storage and computation resources, making it challenging to deploy CNNs on memory-constrained embedded devices. In this article, we propose a novel compression method that generates the convolution filters in each layer using a set of learnable low-dimensional quantized filter bases. The proposed method reconstructs the convolution filters by stacking the linear combinations of these filter bases. By using quantized values in weights, the compact filters can be represented using fewer bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficients through $L_1$ -ball projection when conducting linear combination to further reduce the storage consumption and prevent overfitting. We also provide a detailed analysis of the compression performance of the proposed method. Evaluations of image classification and object detection tasks using various network structures demonstrate that the proposed method achieves a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 4512-4522
Message Injection Attack on Rumor Detection under the Black-Box Evasion Setting Using Large Language Model
Recent analyses have disclosed that existing rumor detection techniques, despite playing a pivotal role in countering the dissemination of misinformation on social media, are vulnerable to both white-box and surrogate-based black-box adversarial attacks. However, such attacks depend heavily on unrealistic assumptions, e.g., modifiable user data and white-box access to the rumor detection models, or appropriate selections of surrogate models, which are impractical in the real world. Thus, existing analyses fail to uncover the robustness of rumor detectors in practice. In this work, we take a further step towards the investigation about the robustness of existing rumor detection solutions. Specifically, we focus on the state-of-the-art rumor detectors, which leverage graph neural network based models to predict whether a post is rumor based on the Message Propagation Tree (MPT), a conversation tree with the post as its root and the replies to the post as the descendants of the root. We propose a novel black-box attack method, HMIA-LLM, against these rumor detectors, which uses the Large Language Model to generate malicious messages and inject them into the targeted MPTs. Our extensive evaluation conducted across three rumor detection datasets, four target rumor detectors, and three baselines for comparison demonstrates the effectiveness of our proposed attack method in compromising the performance of the state-of-the-art rumor detectors.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 4512-4522
Open AccessMessage Injection Attack on Rumor Detection under the Black-Box Evasion Setting Using Large Language Model
Recent analyses have disclosed that existing rumor detection techniques, despite playing a pivotal role in countering the dissemination of misinformation on social media, are vulnerable to both white-box and surrogate-based black-box adversarial attacks. However, such attacks depend heavily on unrealistic assumptions, e.g., modifiable user data and white-box access to the rumor detection models, or appropriate selections of surrogate models, which are impractical in the real world. Thus, existing analyses fail to uncover the robustness of rumor detectors in practice. In this work, we take a further step towards the investigation about the robustness of existing rumor detection solutions. Specifically, we focus on the state-of-the-art rumor detectors, which leverage graph neural network based models to predict whether a post is rumor based on the Message Propagation Tree (MPT), a conversation tree with the post as its root and the replies to the post as the descendants of the root. We propose a novel black-box attack method, HMIA-LLM, against these rumor detectors, which uses the Large Language Model to generate malicious messages and inject them into the targeted MPTs. Our extensive evaluation conducted across three rumor detection datasets, four target rumor detectors, and three baselines for comparison demonstrates the effectiveness of our proposed attack method in compromising the performance of the state-of-the-art rumor detectors.
- Open Access
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 128633-128643
Toward Memory-Efficient and Interpretable Factorization Machines via Data and Model Binarization
Factorization Machines (FM) is a general predictor that can efficiently model feature interactions in linear time, and thus has been broadly used for regression, classification and ranking tasks. Subspace Encoding Factorization Machine (SEFM) is one of the recent approaches which is proposed to enhance FM’s effectiveness by explicit nonlinear feature mapping for both individual features and feature interactions through equal-width binning per input feature. SEFM, despite its effectiveness, has a major drawback of increasing the memory cost of FM by b times where b is the number of bins adopted for the binning. To reduce the memory cost of SEFM, we propose Binarized FM (BiFM) in which each model parameter takes only a binary value (i.e., 1 or -1) and thus can be efficiently stored using one bit. We derive an algorithm which can learn the proposed FM with binary constraints using Straight Through Estimator (STE) with Adaptive Gradient Descent (Adagrad). For performance evaluation, we compare our proposed methods with a number of baselines based on eight different classification datasets. Our experimental results demonstrated that BiFM can achieve higher accuracy than SEFM at much less memory cost. BiFM also inherits the interpretability property from SEFM, and together with adaptive data binning methods can result in a more compact and interpretable set of classification rules.
- 7 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 128633-128643
Open AccessToward Memory-Efficient and Interpretable Factorization Machines via Data and Model Binarization
Factorization Machines (FM) is a general predictor that can efficiently model feature interactions in linear time, and thus has been broadly used for regression, classification and ranking tasks. Subspace Encoding Factorization Machine (SEFM) is one of the recent approaches which is proposed to enhance FM’s effectiveness by explicit nonlinear feature mapping for both individual features and feature interactions through equal-width binning per input feature. SEFM, despite its effectiveness, has a major drawback of increasing the memory cost of FM by b times where b is the number of bins adopted for the binning. To reduce the memory cost of SEFM, we propose Binarized FM (BiFM) in which each model parameter takes only a binary value (i.e., 1 or -1) and thus can be efficiently stored using one bit. We derive an algorithm which can learn the proposed FM with binary constraints using Straight Through Estimator (STE) with Adaptive Gradient Descent (Adagrad). For performance evaluation, we compare our proposed methods with a number of baselines based on eight different classification datasets. Our experimental results demonstrated that BiFM can achieve higher accuracy than SEFM at much less memory cost. BiFM also inherits the interpretability property from SEFM, and together with adaptive data binning methods can result in a more compact and interpretable set of classification rules.
- 12 January 2023
- Published by World Scientific Pub Co Pte Ltd in World Scientific Annual Review of Artificial Intelligence
- Vol. 01
A Survey of Cross-Lingual Text Classification and Its Applications on Fake News Detection
Cross-lingual text classification is a challenging task in natural language processing. The objective is to build accurate text classification models for low-resource languages by transferring the knowledge learned from high-resource languages. The task has been studied since 2003 and has attracted significantly growing attention in the last decade due to the success of deep learning models in natural language processing. Many new methods have been proposed to address the challenges in cross-lingual text classification. Meanwhile, cross-lingual fake news detection is one of the most important applications of cross-lingual text classification. It has already created significant social impacts on alleviating the infodemic problem in low-resource languages. The research works on cross-lingual text classification and cross-lingual fake news detection have been growing rapidly in recent years. Therefore, a comprehensive survey is imperative to summarize existing algorithms for cross-lingual text classification and explain the connections among them. This paper systematically reviews research works on cross-lingual text classifications and their applications in cross-lingual fake news detection. We categorize the evolution of cross-lingual text classification methods into four phases: (1) Traditional text classification models with translation; (2) Cross-lingual word embedding-based methods, (3) Pretraining then finetuning-based methods, and (4) Pretraining then prompting-based methods. We first discuss and analyze the representative methods in each phase in detail. Second, we provide a detailed review of their applications in the emerging fake news detection problem. Finally, we explore the potential issues of this open problem and also discuss possible future directions.
- 12 January 2023
- Published by World Scientific Pub Co Pte Ltd in World Scientific Annual Review of Artificial Intelligence
- Vol. 01
A Survey of Cross-Lingual Text Classification and Its Applications on Fake News Detection
Cross-lingual text classification is a challenging task in natural language processing. The objective is to build accurate text classification models for low-resource languages by transferring the knowledge learned from high-resource languages. The task has been studied since 2003 and has attracted significantly growing attention in the last decade due to the success of deep learning models in natural language processing. Many new methods have been proposed to address the challenges in cross-lingual text classification. Meanwhile, cross-lingual fake news detection is one of the most important applications of cross-lingual text classification. It has already created significant social impacts on alleviating the infodemic problem in low-resource languages. The research works on cross-lingual text classification and cross-lingual fake news detection have been growing rapidly in recent years. Therefore, a comprehensive survey is imperative to summarize existing algorithms for cross-lingual text classification and explain the connections among them. This paper systematically reviews research works on cross-lingual text classifications and their applications in cross-lingual fake news detection. We categorize the evolution of cross-lingual text classification methods into four phases: (1) Traditional text classification models with translation; (2) Cross-lingual word embedding-based methods, (3) Pretraining then finetuning-based methods, and (4) Pretraining then prompting-based methods. We first discuss and analyze the representative methods in each phase in detail. Second, we provide a detailed review of their applications in the emerging fake news detection problem. Finally, we explore the potential issues of this open problem and also discuss possible future directions.
- Open Access
- 17 July 2019
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 4139-4146
Accurate and Interpretable Factorization Machines
Factorization Machines (FMs), a general predictor that can efficiently model high-order feature interactions, have been widely used for regression, classification and ranking problems. However, despite many successful applications of FMs, there are two main limitations of FMs: (1) FMs consider feature interactions among input features by using only polynomial expansion which fail to capture complex nonlinear patterns in data. (2) Existing FMs do not provide interpretable prediction to users. In this paper, we present a novel method named Subspace Encoding Factorization Machines (SEFM) to overcome these two limitations by using non-parametric subspace feature mapping. Due to the high sparsity of new feature representation, our proposed method achieves the same time complexity as the standard FMs but can capture more complex nonlinear patterns. Moreover, since the prediction score of our proposed model for a sample is a sum of contribution scores of the bins and grid cells that this sample lies in low-dimensional subspaces, it works similar like a scoring system which only involves data binning and score addition. Therefore, our proposed method naturally provides interpretable prediction. Our experimental results demonstrate that our proposed method efficiently provides accurate and interpretable prediction.
- 17 July 2019
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 4139-4146
Open AccessAccurate and Interpretable Factorization Machines
Factorization Machines (FMs), a general predictor that can efficiently model high-order feature interactions, have been widely used for regression, classification and ranking problems. However, despite many successful applications of FMs, there are two main limitations of FMs: (1) FMs consider feature interactions among input features by using only polynomial expansion which fail to capture complex nonlinear patterns in data. (2) Existing FMs do not provide interpretable prediction to users. In this paper, we present a novel method named Subspace Encoding Factorization Machines (SEFM) to overcome these two limitations by using non-parametric subspace feature mapping. Due to the high sparsity of new feature representation, our proposed method achieves the same time complexity as the standard FMs but can capture more complex nonlinear patterns. Moreover, since the prediction score of our proposed model for a sample is a sum of contribution scores of the bins and grid cells that this sample lies in low-dimensional subspaces, it works similar like a scoring system which only involves data binning and score addition. Therefore, our proposed method naturally provides interpretable prediction. Our experimental results demonstrate that our proposed method efficiently provides accurate and interpretable prediction.
- 21 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 30 (2) , 369-378
Scaling Up Kernel SVM on Limited Resources: A Low-Rank Linearization Approach
Kernel support vector machines (SVMs) deliver state-of-the-art results in many real-world nonlinear classification problems, but the computational cost can be quite demanding in order to maintain a large number of support vectors. Linear SVM, on the other hand, is highly scalable to large data but only suited for linearly separable problems. In this paper, we propose a novel approach called low-rank linearized SVM to scale up kernel SVM on limited resources. Our approach transforms a nonlinear SVM to a linear one via an approximate empirical kernel map computed from efficient kernel low-rank decompositions. We theoretically analyze the gap between the solutions of the approximate and optimal rank-k kernel map, which in turn provides guidance on the sampling scheme of the Nyström approximation. Furthermore, we extend it to a semisupervised metric learning scenario in which partially labeled samples can be exploited to further improve the quality of the low-rank embedding. Our approach inherits rich representability of kernel SVM and high efficiency of linear SVM. Experimental results demonstrate that our approach is more robust and achieves a better tradeoff between model representability and scalability against state-of-the-art algorithms for large-scale SVMs.
- 21 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 30 (2) , 369-378
Scaling Up Kernel SVM on Limited Resources: A Low-Rank Linearization Approach
Kernel support vector machines (SVMs) deliver state-of-the-art results in many real-world nonlinear classification problems, but the computational cost can be quite demanding in order to maintain a large number of support vectors. Linear SVM, on the other hand, is highly scalable to large data but only suited for linearly separable problems. In this paper, we propose a novel approach called low-rank linearized SVM to scale up kernel SVM on limited resources. Our approach transforms a nonlinear SVM to a linear one via an approximate empirical kernel map computed from efficient kernel low-rank decompositions. We theoretically analyze the gap between the solutions of the approximate and optimal rank-k kernel map, which in turn provides guidance on the sampling scheme of the Nyström approximation. Furthermore, we extend it to a semisupervised metric learning scenario in which partially labeled samples can be exploited to further improve the quality of the low-rank embedding. Our approach inherits rich representability of kernel SVM and high efficiency of linear SVM. Experimental results demonstrate that our approach is more robust and achieves a better tradeoff between model representability and scalability against state-of-the-art algorithms for large-scale SVMs.