Liang Chen
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
Liang Chen has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
Adam Kraft
1 shared publicationCheng Zeng
Central Southern China Electric Power Design Institute Wuhan China
1 shared publication- Cheng Zeng
Central Southern China Electric Power Design Institute
1 shared publication Daiyi Peng
1 shared publicationEsteban Real
1 shared publicationGabriel Bender
1 shared publication
Latest Publications
- Open Access
- 10 December 2024
- Published by Wiley in Security and Privacy
- Vol. 8 (1)
Managing Obligation Delegation: Incentive Model and Experiment
Obligations are essential part of security policies, which specify what actions a user is obliged to perform in the future. One interesting feature of obligations is unenforceable, that is, the system cannot guarantee that each obligation will be fulfilled. Indeed, obligations go unfulfilled for a variety of reasons. For example, a user may have a family emergency that leads her having little time to discharge assigned obligations. We argue that delegation of obligations can be regarded as a means of providing opportunity for obligations to be discharged. However, this opportunity will be wasted if users who received delegation do not fulfill the obligations eventually. In this paper, we propose a mechanism that incentivizes users to accept and fulfill obligations for others by rewarding users credits. The amount of credits that can be earned depends on their trust rating, which reflects precisely how diligent of individuals in fulfilling obligations in the past. Users are motivated to raise up their trust ratings by fulfilling obligations for others, in order to earn more credits in the future. To evaluate our approach, we develop a multiple‐agent system that simulates a number of different profiles for agents and run experiments for one‐hop delegation and cascaded delegation with those agents. The experiments show a rich set of results, one of which confirms that delegation with incentives achieves the best outcome in terms of the number of obligations being fulfilled. Also, we implemented the modified ‐greedy algorithm, one of the closely related existing works, in our experimental framework and compared its performance to our approach. The results show that our approach offers greater flexibility and efficiency, as well as a higher obligation fulfillment rate.
- 10 December 2024
- Published by Wiley in Security and Privacy
- Vol. 8 (1)
Open AccessManaging Obligation Delegation: Incentive Model and Experiment
Obligations are essential part of security policies, which specify what actions a user is obliged to perform in the future. One interesting feature of obligations is unenforceable, that is, the system cannot guarantee that each obligation will be fulfilled. Indeed, obligations go unfulfilled for a variety of reasons. For example, a user may have a family emergency that leads her having little time to discharge assigned obligations. We argue that delegation of obligations can be regarded as a means of providing opportunity for obligations to be discharged. However, this opportunity will be wasted if users who received delegation do not fulfill the obligations eventually. In this paper, we propose a mechanism that incentivizes users to accept and fulfill obligations for others by rewarding users credits. The amount of credits that can be earned depends on their trust rating, which reflects precisely how diligent of individuals in fulfilling obligations in the past. Users are motivated to raise up their trust ratings by fulfilling obligations for others, in order to earn more credits in the future. To evaluate our approach, we develop a multiple‐agent system that simulates a number of different profiles for agents and run experiments for one‐hop delegation and cascaded delegation with those agents. The experiments show a rich set of results, one of which confirms that delegation with incentives achieves the best outcome in terms of the number of obligations being fulfilled. Also, we implemented the modified ‐greedy algorithm, one of the closely related existing works, in our experimental framework and compared its performance to our approach. The results show that our approach offers greater flexibility and efficiency, as well as a higher obligation fulfillment rate.
- 14 May 2023
- Published by Springer Nature
- p. 191-206
An Incentive Mechanism for Managing Obligation Delegation
- 14 May 2023
- Published by Springer Nature
- p. 191-206
An Incentive Mechanism for Managing Obligation Delegation
- Open Access
- 25 April 2021
- Published by MDPI AG in Information
- Vol. 12 (5) , 186
Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory
Presently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity and low parallelizability because of the nature of complicated interconnected structure of their nodes. Network representation learning, also called network embedding, provides a practical and promising way to solve these issues. One of the foremost requirements of network embedding is preserving network topology properties in learned low-dimension representations. Community structure is a prominent characteristic of complex networks and thus should be well maintained. However, the difficulty lies in the fact that the properties of community structure are multivariate and complicated; therefore, it is insufficient to model community structure using a predefined model, the way that is popular in most state-of-the-art network embedding algorithms explicitly considering community structure preservation. In this paper, we introduce a multi-process parallel framework for network embedding that is enhanced by found partial community information and can preserve community properties well. We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information. A series of experiments are conducted to evaluate the performance of our methods and six state-of-the-art algorithms. The results demonstrate that our methods can effectively preserve community properties of networks in their low-dimension representations. Specifically, compared to the involved baselines, our algorithms behave the best and are the runners-up on networks with high overlapping diversity and density.
- 25 April 2021
- Published by MDPI AG in Information
- Vol. 12 (5) , 186
Open AccessNetwork Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory
Presently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity and low parallelizability because of the nature of complicated interconnected structure of their nodes. Network representation learning, also called network embedding, provides a practical and promising way to solve these issues. One of the foremost requirements of network embedding is preserving network topology properties in learned low-dimension representations. Community structure is a prominent characteristic of complex networks and thus should be well maintained. However, the difficulty lies in the fact that the properties of community structure are multivariate and complicated; therefore, it is insufficient to model community structure using a predefined model, the way that is popular in most state-of-the-art network embedding algorithms explicitly considering community structure preservation. In this paper, we introduce a multi-process parallel framework for network embedding that is enhanced by found partial community information and can preserve community properties well. We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information. A series of experiments are conducted to evaluate the performance of our methods and six state-of-the-art algorithms. The results demonstrate that our methods can effectively preserve community properties of networks in their low-dimension representations. Specifically, compared to the involved baselines, our algorithms behave the best and are the runners-up on networks with high overlapping diversity and density.
- Open Access
PyGlove: Symbolic Programming for Automated Machine Learning
Neural networks are sensitive to hyper-parameter and architecture choices. Automated Machine Learning (AutoML) is a promising paradigm for automating these choices. Current ML software libraries, however, are quite limited in handling the dynamic interactions among the components of AutoML. For example, efficientNAS algorithms, such as ENAS and DARTS, typically require an implementation coupling between the search space and search algorithm, the two key components in AutoML. Furthermore, implementing a complex search flow, such as searching architectures within a loop of searching hardware configurations, is difficult. To summarize, changing the search space, search algorithm, or search flow in current ML libraries usually requires a significant change in the program logic. In this paper, we introduce a new way of programming AutoML based on symbolic programming. Under this paradigm, ML programs are mutable, thus can be manipulated easily by another program. As a result, AutoML can be reformulated as an automated process of symbolic manipulation. With this formulation, we decouple the triangle of the search algorithm, the search space and the child program. This decoupling makes it easy to change the search space and search algorithm (without and with weight sharing), as well as to add search capabilities to existing code and implement complex search flows. We then introduce PyGlove, a new Python library that implements this paradigm. Through case studies on ImageNet and NAS-Bench-101, we show that with PyGlove users can easily convert a static program into a search space, quickly iterate on the search spaces and search algorithms, and craft complex search flows to achieve better results.
Open AccessPyGlove: Symbolic Programming for Automated Machine Learning
Neural networks are sensitive to hyper-parameter and architecture choices. Automated Machine Learning (AutoML) is a promising paradigm for automating these choices. Current ML software libraries, however, are quite limited in handling the dynamic interactions among the components of AutoML. For example, efficientNAS algorithms, such as ENAS and DARTS, typically require an implementation coupling between the search space and search algorithm, the two key components in AutoML. Furthermore, implementing a complex search flow, such as searching architectures within a loop of searching hardware configurations, is difficult. To summarize, changing the search space, search algorithm, or search flow in current ML libraries usually requires a significant change in the program logic. In this paper, we introduce a new way of programming AutoML based on symbolic programming. Under this paradigm, ML programs are mutable, thus can be manipulated easily by another program. As a result, AutoML can be reformulated as an automated process of symbolic manipulation. With this formulation, we decouple the triangle of the search algorithm, the search space and the child program. This decoupling makes it easy to change the search space and search algorithm (without and with weight sharing), as well as to add search capabilities to existing code and implement complex search flows. We then introduce PyGlove, a new Python library that implements this paradigm. Through case studies on ImageNet and NAS-Bench-101, we show that with PyGlove users can easily convert a static program into a search space, quickly iterate on the search spaces and search algorithms, and craft complex search flows to achieve better results.
- Open Access
Modelling High-Order Social Relations for Item Recommendation
The prevalence of online social network makes it compulsory to study how social relations affect user choice. However, most existing methods leverage only first-order social relations, that is, the direct neighbors that are connected to the target user. The high-order social relations, e.g., the friends of friends, which very informative to reveal user preference, have been largely ignored. In this work, we focus on modeling the indirect influence from the high-order neighbors in social networks to improve the performance of item recommendation. Distinct from mainstream social recommenders that regularize the model learning with social relations, we instead propose to directly factor social relations in the predictive model, aiming at learning better user embeddings to improve recommendation. To address the challenge that high-order neighbors increase dramatically with the order size, we propose to recursively "propagate" embeddings along the social network, effectively injecting the influence of high-order neighbors into user representation. We conduct experiments on two real datasets of Yelp and Douban to verify our High-Order Social Recommender (HOSR) model. Empirical results show that our HOSR significantly outperforms recent graph regularization-based recommenders NSCR and IF-BPR+, and graph convolutional network-based social influence prediction model DeepInf, achieving new state-of-the-arts of the task.
Open AccessModelling High-Order Social Relations for Item Recommendation
The prevalence of online social network makes it compulsory to study how social relations affect user choice. However, most existing methods leverage only first-order social relations, that is, the direct neighbors that are connected to the target user. The high-order social relations, e.g., the friends of friends, which very informative to reveal user preference, have been largely ignored. In this work, we focus on modeling the indirect influence from the high-order neighbors in social networks to improve the performance of item recommendation. Distinct from mainstream social recommenders that regularize the model learning with social relations, we instead propose to directly factor social relations in the predictive model, aiming at learning better user embeddings to improve recommendation. To address the challenge that high-order neighbors increase dramatically with the order size, we propose to recursively "propagate" embeddings along the social network, effectively injecting the influence of high-order neighbors into user representation. We conduct experiments on two real datasets of Yelp and Douban to verify our High-Order Social Recommender (HOSR) model. Empirical results show that our HOSR significantly outperforms recent graph regularization-based recommenders NSCR and IF-BPR+, and graph convolutional network-based social influence prediction model DeepInf, achieving new state-of-the-arts of the task.
- 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) , 6999-7006
DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization. Given any document-summary pair, we estimate a salience score, which is modeled using an attention-based deep neural network, to represent the salience degree of the summary for yielding the document. We devise a contrastive training strategy to learn the salience estimation network, and then use the learned salience score as a guide and iteratively extract the most salient sentences from the document as our generated summary. In experiments, our model not only achieves state-of-the-art ROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the out-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1 F-1 score of 39.41 on CNN/Daily Mail test set with merely 1/100 training set, demonstrating a tremendous data efficiency.
- 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) , 6999-7006
Open AccessDeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization. Given any document-summary pair, we estimate a salience score, which is modeled using an attention-based deep neural network, to represent the salience degree of the summary for yielding the document. We devise a contrastive training strategy to learn the salience estimation network, and then use the learned salience score as a guide and iteratively extract the most salient sentences from the document as our generated summary. In experiments, our model not only achieves state-of-the-art ROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the out-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1 F-1 score of 39.41 on CNN/Daily Mail test set with merely 1/100 training set, demonstrating a tremendous data efficiency.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Efficient image deblurring via blockwise non-blind deconvolution algorithm
Image deblurring aims to restore the quality of degraded images and plays an important role in many multimedia applications. Implementing a deblurring algorithm directly, however, is usually computationally expensive, especially for high-resolution images. In this paper, we propose to first partition the image in blocks (sub-images) and then implement the deblurring algorithm on a block basis for deblurring high-resolution or large-dimension images. Overlap regions among blocks are linearly filtered to reduce the distortion at the edge due to the block-based implementation. Simulations demonstrate that the proposed method achieves satisfactory result with much less computation time.
- 1 December 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Efficient image deblurring via blockwise non-blind deconvolution algorithm
Image deblurring aims to restore the quality of degraded images and plays an important role in many multimedia applications. Implementing a deblurring algorithm directly, however, is usually computationally expensive, especially for high-resolution images. In this paper, we propose to first partition the image in blocks (sub-images) and then implement the deblurring algorithm on a block basis for deblurring high-resolution or large-dimension images. Overlap regions among blocks are linearly filtered to reduce the distortion at the edge due to the block-based implementation. Simulations demonstrate that the proposed method achieves satisfactory result with much less computation time.