Haolong Xiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haolong Xiang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolong Xu
Nanjing University of Information Science and Technology
9 shared publications - Xuyun Zhang
School of Computing, Macquarie University, Sydney, NSW, Australia
9 shared publications - Lianyong Qi
China University of Petroleum (East China), Qingdao, China
8 shared publications - Wanchun Dou
Nanjing University
7 shared publications - Jianye Xie
College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China and Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software, Qingdao, China
4 shared publications - Amin Beheshti
Macquarie University, Sydney, NSW, Australia
3 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1198-1208
Fourier Kolmogorov-Arnold Network and Hypergraph Enhanced Contrastive Learning for Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1198-1208
Open AccessFourier Kolmogorov-Arnold Network and Hypergraph Enhanced Contrastive Learning for Recommendation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4680-4688
CIFAD: Causal-Invariant Subspace Learning for Few-Shot Anomaly Detection on Dynamic Relational Graphs
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 4680-4688
Open AccessCIFAD: Causal-Invariant Subspace Learning for Few-Shot Anomaly Detection on Dynamic Relational Graphs
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6218-6229
Joint Similar User Exploration and Informative Behavior Guidance for Multi-Modal New Item Recommendation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6218-6229
Open AccessJoint Similar User Exploration and Informative Behavior Guidance for Multi-Modal New Item Recommendation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3788-3799
PLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification
With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3788-3799
Open AccessPLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification
With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3755-3763
DyLogNet: A Dynamic Multi-Relational Graph Framework for Log Anomaly Detection
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3755-3763
Open AccessDyLogNet: A Dynamic Multi-Relational Graph Framework for Log Anomaly Detection
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 174-183
GSDiffRec: Enhancing Personalized Sequential Recommendation via Diffusion Augmentation and Guidance Optimization
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 174-183
Open AccessGSDiffRec: Enhancing Personalized Sequential Recommendation via Diffusion Augmentation and Guidance Optimization
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1027-1035
Automated C Vulnerability Detection via Structure-Enhanced Graph Transformer and RBM
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1027-1035
Open AccessAutomated C Vulnerability Detection via Structure-Enhanced Graph Transformer and RBM
- Open Access
- 26 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (2) , 1-2
Erratum: Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation
This is an erratum for the article “Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation” published in ACM Trans. Inf. Syst. 44, 1, Article 27 (December 2025), 30 pages.
- 26 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (2) , 1-2
Open AccessErratum: Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation
This is an erratum for the article “Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation” published in ACM Trans. Inf. Syst. 44, 1, Article 27 (December 2025), 30 pages.
- Open Access
- 15 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (1) , 1-30
Knowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation
API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.
- 15 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (1) , 1-30
Open AccessKnowledge-Driven Reasoning for Compatible and Interpretable API Recommendation via Teacher LLM Distillation
API recommendation is a crucial task in code intelligence, aiming to suggest suitable APIs for programming queries. Recent efforts have integrated Large Language Models (LLMs) into this task. However, these methods overlook the compatibility between recommended APIs and fail to fully utilize the factual knowledge of APIs. Moreover, these prompting-only methods are limited by the insufficient domain-specific knowledge of LLMs. In this article, we propose a novel fine-tuning method, KDRAR, designed to leverage knowledge-driven reasoning with LLMs for compatible and interpretable API recommendation. To fully utilize the factual knowledge, we introduce a dual matching strategy that leverages both function descriptions and keyword matching to retrieve candidate APIs. To handle compatibility, we translate compatibility information into descriptive knowledge, which is integrated into the recommendation process. Furthermore, we adopt a distilled fine-tuning strategy: a student LLM is trained via distillation from a teacher LLM to perform step-by-step reasoning for enhanced recommendation and explanation. By considering both function matching and compatibility information, the knowledge-driven reasoning not only improves API recommendation accuracy but also provides reasonable explanations for the recommendations. Experimental results show that our method significantly outperforms baseline methods on API recommendation tasks across multiple API domains.