Liang Zhang

Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning

2018

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process …

Temporal Item Embedding with Static Similarity Regularization for Sequential Recommendation

2018

Recommender systems have attracted a significant amount of research interests in recent years. Traditional methods such as content-based approaches and collaborative filtering approaches mainly focus on modeling the general user preference by using the user's …

Redactable Blockchain with K-Time Controllable Editing

2022

Considering the immutability of traditional blockchain restricts the governance and regulation of sensitive data on chain, this paper proposes a redactable blockchain scheme with k-time controllable cheating editing (CCE-RB for short). In the CCE-RB scheme, …

Lightweight Certificateless Encryption Supporting Equality Test without Bilinear Pairing

2023

Certificateless cryptography enjoys the advantages of simplified certificate management and no key escrow problem. Equality test allows one to judge whether two ciphertexts are generated from two same plaintexts or not without decrypting them. Both …

Improving Power System Information Security: Analysis of the Saturnin Cipher Algorithm

2023

New power systems require efficient and secure communication technologies to facilitate information exchange between various devices and systems. Among these, encryption technology is key to ensuring communication security. The lightweight block cipher algorithm, Saturnin, is …

Medicare Fraud Detection Based on EP-GCN

2024

Although Graph Convolutional Networks (GCNs) have made significant progress in healthcare fraud detection, they still face challenges such as severe data imbalance and noise intentionally introduced by fraudsters. To address these issues, this study aims …

Data Exchange for the Metaverse With Accountable Decentralized TTPs and Incentive Mechanisms

2025 · IEEE Transactions on Big Data

As a global virtual environment, the metaverse poses various challenges regarding data storage, sharing, interoperability, and privacy preservation. Typically, a trusted third party (TTP) is considered necessary in these scenarios. However, relying on a single …

Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss

2025

Recent studies have explored Continual Instruction Tuning (CIT) in Multimodal Large Language Models (MLLMs), with a primary focus on Task-incremental CIT, where MLLMs are required to continuously acquire new tasks.However, the more practical and challenging …

Bridging Global Pretraining and Similarity-Based Local Fine-Tuning in GAIN for Imputing Sparse Learner Performance Data

2025

Learner performance data (e.g., correct or incorrect responses) from the interaction logs of Intelligent Tutoring Systems (ITSs) are often sparse, hindering accurate predictions of learner performance and the delivery of effective, adaptive feedback. To address …

Deep Reinforcement Learning for List-wise Recommendations

2017 · arXiv (Cornell University)

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process …

Deep reinforcement learning for page-wise recommendations

2018

Recommender systems can mitigate the information overload problem by suggesting users' personalized items. In real-world recommendations such as e-commerce, a typical interaction between the system and its users is - users are recommended a page …