Yang Liu
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
Yang Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Fujun Wang
Yangzhou Polytechnic Institute
1 shared publication - Li Zhang
School of Computer Science and Technology, Soochow University, Suzhou, China
1 shared publication - Lixing Tan
School of Artificial Intelligence, Taizhou University, Taizhou 225300, China
1 shared publication Rui Li
1 shared publication- Tao Wang
School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing 210023, China
1 shared publication Yan Ma
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P. R. China and School of Computing, National University of Singapore, Singapore 117417, Singapore
1 shared publication
Latest Publications
- Open Access
TimeWeaver: Time-Aware Sequential Recommender System via Dual-Stream Temporal Network
Recommender systems are data-driven tools designed to assist or automate users’ decision-making. With the growing demand of personalized sequential recommendations in business intelligence or e-commerce, effectively capturing temporal information from massive user-sequence data has become a crucial challenge. State-of-the-art attention-based models often struggle to balance performance with computational cost, while traditional convolutional neural networks suffer from limited receptive fields and rigid architectures that inadequately model dynamic user interests. To address these limitations, this paper proposes TimeWeaver, a time-aware dual-stream network for sequential recommendation, whose core innovations comprise three key components. First, it employs a re-parameterized large-kernel convolution to expand the effective receptive field. Second, we design a Time-Aware Augmentation mechanism that integrates inter-event time-interval information into positional encodings of items. This allows it to perceive the temporal dynamics of user behavior. Finally, we propose a dual-stream architecture to jointly capture dependencies across different time scales. The context stream employs a modern Temporal Convolutional Network (TCN) structure to strengthen the memorization of users’ medium- and long-term interests. In parallel, the dynamic stream leverages an Exponential Moving Average (EMA) mechanism to weight recent behaviors for sensitively capturing users’ immediate interests. This dual-stream design allows TimeWeaver to comprehensively extract both long- and short-term sequential features. Extensive experiments on three public e-commerce datasets demonstrate TimeWeaver’s superiority. Compared to the strongest baseline model, TimeWeaver achieves average relative improvements of 4.62%, 9.59%, and 4.59% across all metrics on the Beauty, Sports, and Toys datasets, respectively.
Open AccessTimeWeaver: Time-Aware Sequential Recommender System via Dual-Stream Temporal Network
Recommender systems are data-driven tools designed to assist or automate users’ decision-making. With the growing demand of personalized sequential recommendations in business intelligence or e-commerce, effectively capturing temporal information from massive user-sequence data has become a crucial challenge. State-of-the-art attention-based models often struggle to balance performance with computational cost, while traditional convolutional neural networks suffer from limited receptive fields and rigid architectures that inadequately model dynamic user interests. To address these limitations, this paper proposes TimeWeaver, a time-aware dual-stream network for sequential recommendation, whose core innovations comprise three key components. First, it employs a re-parameterized large-kernel convolution to expand the effective receptive field. Second, we design a Time-Aware Augmentation mechanism that integrates inter-event time-interval information into positional encodings of items. This allows it to perceive the temporal dynamics of user behavior. Finally, we propose a dual-stream architecture to jointly capture dependencies across different time scales. The context stream employs a modern Temporal Convolutional Network (TCN) structure to strengthen the memorization of users’ medium- and long-term interests. In parallel, the dynamic stream leverages an Exponential Moving Average (EMA) mechanism to weight recent behaviors for sensitively capturing users’ immediate interests. This dual-stream design allows TimeWeaver to comprehensively extract both long- and short-term sequential features. Extensive experiments on three public e-commerce datasets demonstrate TimeWeaver’s superiority. Compared to the strongest baseline model, TimeWeaver achieves average relative improvements of 4.62%, 9.59%, and 4.59% across all metrics on the Beauty, Sports, and Toys datasets, respectively.
- 30 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Software Engineering and Knowledge Engineering
- Vol. 34 (11) , 1783-1805
A Formal Language for Performance Evaluation Based on Reinforcement Learning
Temporal Logics are a rich variety of logical systems designed for specifying properties over time, and about events and changes in the world over time. Traditional temporal logic, however, is limited to binary outcomes true or false and lacks the capacity to specify performance properties of a system such as the maximum, minimum, or average costs between states. Current languages do not accommodate the quantification of such performance properties, especially in scenarios involving infinite execution paths where performance property like cumulative sums may fail to converge. To this end, this paper introduces a novel formal language aimed at assessing system performance, which encapsulates not only temporal dynamics but also various performance-related properties. In this study, this paper utilizes reinforcement learning techniques to compute the values of performance property formulas. Finally, in the experimental part, a formal language representation of system performance properties was implemented, and the values of the performance property formulas were computed using reinforcement learning. The effectiveness and feasibility of the proposed method were validated.
- 30 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Software Engineering and Knowledge Engineering
- Vol. 34 (11) , 1783-1805
A Formal Language for Performance Evaluation Based on Reinforcement Learning
Temporal Logics are a rich variety of logical systems designed for specifying properties over time, and about events and changes in the world over time. Traditional temporal logic, however, is limited to binary outcomes true or false and lacks the capacity to specify performance properties of a system such as the maximum, minimum, or average costs between states. Current languages do not accommodate the quantification of such performance properties, especially in scenarios involving infinite execution paths where performance property like cumulative sums may fail to converge. To this end, this paper introduces a novel formal language aimed at assessing system performance, which encapsulates not only temporal dynamics but also various performance-related properties. In this study, this paper utilizes reinforcement learning techniques to compute the values of performance property formulas. Finally, in the experimental part, a formal language representation of system performance properties was implemented, and the values of the performance property formulas were computed using reinforcement learning. The effectiveness and feasibility of the proposed method were validated.
- Open Access
- 1 January 2020
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 8 (2) , 94-107
Compositional Stochastic Model Checking Probabilistic Automata via Assume-guarantee Reasoning
- 1 January 2020
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 8 (2) , 94-107
Open AccessCompositional Stochastic Model Checking Probabilistic Automata via Assume-guarantee Reasoning
- Open Access
- 24 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 83839-83851
A Probabilistic Assume-Guarantee Reasoning Framework Based on Genetic Algorithm
Probabilistic assume-guarantee reasoning is a theoretically feasible way to alleviate the state space explosion problem in stochastic model checking. The key for probabilistic assume-guarantee reasoning is how to generate assumption. At present, a main way to automatically generate assumption is the L* (or symbolic L*) learning algorithm. An important limitation of it is too many intermediate results are produced and needs to be stored. To overcome this, we propose a novel assumption generation method by genetic algorithm, and present a probabilistic assume-guarantee reasoning framework for MDP. Genetic algorithm is a randomized algorithm essentially, there are no intermediate results needs to be stored in the process of assumption generation, except encode of the problem domain and training set. It can obviously reduce the space complexity of probabilistic assume-guarantee reasoning framework. In order to improve the efficiency further, we combine the probabilistic assume-guarantee reasoning framework with interface alphabet refinement orthogonally. Moreover, we employ the diagnostic submodel as counterexample for guidance of augmenting training set. We implement a prototype tool for the probabilistic assume-guarantee reasoning framework and report encouraging results.
- 24 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 83839-83851
Open AccessA Probabilistic Assume-Guarantee Reasoning Framework Based on Genetic Algorithm
Probabilistic assume-guarantee reasoning is a theoretically feasible way to alleviate the state space explosion problem in stochastic model checking. The key for probabilistic assume-guarantee reasoning is how to generate assumption. At present, a main way to automatically generate assumption is the L* (or symbolic L*) learning algorithm. An important limitation of it is too many intermediate results are produced and needs to be stored. To overcome this, we propose a novel assumption generation method by genetic algorithm, and present a probabilistic assume-guarantee reasoning framework for MDP. Genetic algorithm is a randomized algorithm essentially, there are no intermediate results needs to be stored in the process of assumption generation, except encode of the problem domain and training set. It can obviously reduce the space complexity of probabilistic assume-guarantee reasoning framework. In order to improve the efficiency further, we combine the probabilistic assume-guarantee reasoning framework with interface alphabet refinement orthogonally. Moreover, we employ the diagnostic submodel as counterexample for guidance of augmenting training set. We implement a prototype tool for the probabilistic assume-guarantee reasoning framework and report encouraging results.