Zhihao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhihao Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Bing Li
Wuhan University
5 shared publications - Jian Wang
School of Computer Science, Wuhan University, China
5 shared publications - Duantengchuan Li
School of Information Management, Wuhan University, Wuhan 430072, China
3 shared publications - Jingxiong Wang
Wuhan University
2 shared publications - Maodong Li
Wuhan University
2 shared publications - Neng Zhang
School of Computer Science & Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, China
2 shared publications
Latest Publications
- Open Access
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
What to Retrieve? Investigating Effective Call Information in Repository-level Code Generation
Retrieval-Augmented Generation (RAG) emerges as a widely adopted solution in repository-level code generation by retrieving functions for direct reuse or learning similar usage patterns. Nevertheless, it remains unexplored which types of contexts effectively assist LLMs. In this paper, we categorize the context of function calls and empirically analyze the performance of LLMs. Specifically, we define call information along two dimensions: call depth , including direct-level , inward expansion (to callees), and outward expansion (to callers), as well as call granularity , including function-level , module-level , and file-level . We investigate the utility of the context in two distinct scenarios: precision-oriented call extraction and relevance-oriented call retrieval , targeting precise call information and relevant call information , respectively. We conduct comprehensive experiments with three mainstream LLMs on two widely used benchmarks, CoderEval and DevEval. When precise call information is provided, the additional inclusion of inward expansion, outward expansion, module-level, and file-level context enhances the average Pass@1 of the studied LLMs by 2.11%, 79.59%, 37.54%, and 82.54%, respectively. When the relevant call information is provided, incorporating the same set of strategies leads to improvements of 18.00%, 4.77%, 26.07%, and 44.60% in average Pass@1, respectively. This empirical study offers practical insights for optimizing RAG strategies in repository-level code generation.
- 5 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessWhat to Retrieve? Investigating Effective Call Information in Repository-level Code Generation
Retrieval-Augmented Generation (RAG) emerges as a widely adopted solution in repository-level code generation by retrieving functions for direct reuse or learning similar usage patterns. Nevertheless, it remains unexplored which types of contexts effectively assist LLMs. In this paper, we categorize the context of function calls and empirically analyze the performance of LLMs. Specifically, we define call information along two dimensions: call depth , including direct-level , inward expansion (to callees), and outward expansion (to callers), as well as call granularity , including function-level , module-level , and file-level . We investigate the utility of the context in two distinct scenarios: precision-oriented call extraction and relevance-oriented call retrieval , targeting precise call information and relevant call information , respectively. We conduct comprehensive experiments with three mainstream LLMs on two widely used benchmarks, CoderEval and DevEval. When precise call information is provided, the additional inclusion of inward expansion, outward expansion, module-level, and file-level context enhances the average Pass@1 of the studied LLMs by 2.11%, 79.59%, 37.54%, and 82.54%, respectively. When the relevant call information is provided, incorporating the same set of strategies leads to improvements of 18.00%, 4.77%, 26.07%, and 44.60% in average Pass@1, respectively. This empirical study offers practical insights for optimizing RAG strategies in repository-level code generation.
- 12 September 2026
- Published by Springer Nature
- p. 598-616
Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization
- 12 September 2026
- Published by Springer Nature
- p. 598-616
Proposal Score Realignment Guided by Semantic Completeness for Weakly Supervised Temporal Action Localization
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5894-5909
Weakly Supervised Temporal Action Localization With Proposal-Level Action Consistency Learning
Existing weakly supervised temporal action localization (WTAL) methods typically follow a decoupled classification–localization pipeline: segment-level classifiers are trained first, and their predictions are then aggregated to score proposals at inference. Under this training–inference discrepancy, proposal scoring at inference relies on an additional aggregation step, which can accumulate errors from noisy segment responses and thus undermine score reliability. Moreover, proposal scores are often directly used as confidence without explicit score–quality modeling or quality-aware evaluation, further contributing to pronounced score–quality misalignment and thus widening the classification–localization gap. To address proposal score–quality misalignment, we propose ACL-Net, a framework for proposal score calibration. At its core is a dual-axis Proposal-level Action Consistency Learning (PACL) paradigm, implemented through two complementary modules: (i) a Semantic Consistency Module (SCM) that refines proposal representations by maintaining fused class centers to enforce compact and robust same-class features; within SCM, a cross-modal consistency–driven Classification Enhancement Module (CEM) denoises the fused class centers to mitigate error accumulation under weak supervision; and (ii) a Process Consistency Module (PCM) that derives geometry-aware reference scores from relative temporal relations among overlapping proposals, guiding the model to assess proposal quality in terms of relative process completeness and improve score–quality alignment. By jointly modeling semantic and process consistency to calibrate proposal scores, ACL-Net markedly improves localization accuracy. On THUMOS14 and ActivityNet1.3, it achieves state-of-the-art performance with uniform and substantial gains across multiple established baselines, while markedly lowering the expected calibration error (ECE).
- 2 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5894-5909
Weakly Supervised Temporal Action Localization With Proposal-Level Action Consistency Learning
Existing weakly supervised temporal action localization (WTAL) methods typically follow a decoupled classification–localization pipeline: segment-level classifiers are trained first, and their predictions are then aggregated to score proposals at inference. Under this training–inference discrepancy, proposal scoring at inference relies on an additional aggregation step, which can accumulate errors from noisy segment responses and thus undermine score reliability. Moreover, proposal scores are often directly used as confidence without explicit score–quality modeling or quality-aware evaluation, further contributing to pronounced score–quality misalignment and thus widening the classification–localization gap. To address proposal score–quality misalignment, we propose ACL-Net, a framework for proposal score calibration. At its core is a dual-axis Proposal-level Action Consistency Learning (PACL) paradigm, implemented through two complementary modules: (i) a Semantic Consistency Module (SCM) that refines proposal representations by maintaining fused class centers to enforce compact and robust same-class features; within SCM, a cross-modal consistency–driven Classification Enhancement Module (CEM) denoises the fused class centers to mitigate error accumulation under weak supervision; and (ii) a Process Consistency Module (PCM) that derives geometry-aware reference scores from relative temporal relations among overlapping proposals, guiding the model to assess proposal quality in terms of relative process completeness and improve score–quality alignment. By jointly modeling semantic and process consistency to calibrate proposal scores, ACL-Net markedly improves localization accuracy. On THUMOS14 and ActivityNet1.3, it achieves state-of-the-art performance with uniform and substantial gains across multiple established baselines, while markedly lowering the expected calibration error (ECE).
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 2762-2778
Enhancing Intent Understanding and Preference Learning for Sequential Recommendation
Sequential recommendation aims to derive insights from user interaction records and make predictions based on relationships between users and items. However, most existing approaches do not effectively integrate user intents and preferences, which limits their capability to capture user behavior patterns. Additionally, these methods often struggle with poor performance in sparse data scenarios. To address these challenges, we propose EL4SR, a sequential recommendation approach by integrating intent understanding and preference learning. EL4SR simultaneously learns user intents and preferences through a dual-channel recommendation module, modeling both item and popularity sequences to enable mutual learning that captures the combined effects of intent and preference. Moreover, we enhance intent learning through contrastive learning, improving adaptability in sparse data contexts. We design several augmentation operators to improve the performance and robustness of EL4SR. Extensive experiments on MovieLens and Amazon demonstrate the performance of our proposed method across various scenarios.
- 26 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (5) , 2762-2778
Enhancing Intent Understanding and Preference Learning for Sequential Recommendation
Sequential recommendation aims to derive insights from user interaction records and make predictions based on relationships between users and items. However, most existing approaches do not effectively integrate user intents and preferences, which limits their capability to capture user behavior patterns. Additionally, these methods often struggle with poor performance in sparse data scenarios. To address these challenges, we propose EL4SR, a sequential recommendation approach by integrating intent understanding and preference learning. EL4SR simultaneously learns user intents and preferences through a dual-channel recommendation module, modeling both item and popularity sequences to enable mutual learning that captures the combined effects of intent and preference. Moreover, we enhance intent learning through contrastive learning, improving adaptability in sparse data contexts. We design several augmentation operators to improve the performance and robustness of EL4SR. Extensive experiments on MovieLens and Amazon demonstrate the performance of our proposed method across various scenarios.
- Top Cited PapersOpen Access
- 20 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-39
TVDiag: A Task-oriented and View-invariant Failure Diagnosis Framework for Microservice-based Systems with Multimodal Data
Microservice-based systems often suffer from reliability issues due to their intricate interactions and expanding scale. With the rapid growth of observability techniques, various methods have been proposed to achieve failure diagnosis, including root cause localization and failure type identification, by leveraging diverse monitoring data such as logs, metrics, or traces. However, traditional failure diagnosis methods that use single-modal data can hardly cover all failure scenarios due to the restricted information. Several failure diagnosis methods have been recently proposed to integrate multimodal data based on deep learning. These methods, however, tend to combine modalities indiscriminately and treat them equally in failure diagnosis, ignoring the relationship between specific modalities and different diagnostic tasks. This oversight hinders the effective utilization of the unique advantages offered by each modality. To address the limitation, we propose TVDiag , a multimodal failure diagnosis framework for locating culprit microservice instances and identifying their failure types (e.g., Net-packets Corruption) in microservice-based systems. TVDiag employs task-oriented learning to enhance the potential advantages of each modality and establishes cross-modal associations based on contrastive learning to extract view-invariant failure information. Furthermore, we develop a graph-level data augmentation strategy that randomly inactivates the observability of some normal microservice instances to mitigate the shortage of training data. Experimental results on four datasets show that TVDiag outperforms the state-of-the-art methods in multimodal failure diagnosis by at least 20.16% and 3.08% in terms of \(HR@1\) and F1-score, respectively.- 20 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (2) , 1-39
Top Cited PapersOpen AccessTVDiag: A Task-oriented and View-invariant Failure Diagnosis Framework for Microservice-based Systems with Multimodal Data
Microservice-based systems often suffer from reliability issues due to their intricate interactions and expanding scale. With the rapid growth of observability techniques, various methods have been proposed to achieve failure diagnosis, including root cause localization and failure type identification, by leveraging diverse monitoring data such as logs, metrics, or traces. However, traditional failure diagnosis methods that use single-modal data can hardly cover all failure scenarios due to the restricted information. Several failure diagnosis methods have been recently proposed to integrate multimodal data based on deep learning. These methods, however, tend to combine modalities indiscriminately and treat them equally in failure diagnosis, ignoring the relationship between specific modalities and different diagnostic tasks. This oversight hinders the effective utilization of the unique advantages offered by each modality. To address the limitation, we propose TVDiag , a multimodal failure diagnosis framework for locating culprit microservice instances and identifying their failure types (e.g., Net-packets Corruption) in microservice-based systems. TVDiag employs task-oriented learning to enhance the potential advantages of each modality and establishes cross-modal associations based on contrastive learning to extract view-invariant failure information. Furthermore, we develop a graph-level data augmentation strategy that randomly inactivates the observability of some normal microservice instances to mitigate the shortage of training data. Experimental results on four datasets show that TVDiag outperforms the state-of-the-art methods in multimodal failure diagnosis by at least 20.16% and 3.08% in terms of \(HR@1\) and F1-score, respectively. - 12 May 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 177
Recommender system based on noise enhancement and multi-view graph contrastive learning
- 12 May 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 177
Recommender system based on noise enhancement and multi-view graph contrastive learning
- 16 July 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (6)
Homogeneous graph neural networks for third-party library recommendation
- 16 July 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (6)
Homogeneous graph neural networks for third-party library recommendation
- 5 February 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (3)
Integrating user short-term intentions and long-term preferences in heterogeneous hypergraph networks for sequential recommendation
- 5 February 2024
- Published by Elsevier in Information Processing & Management
- Vol. 61 (3)
Integrating user short-term intentions and long-term preferences in heterogeneous hypergraph networks for sequential recommendation