Hao 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
Hao Liu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Le Wu
Hefei University of Technology
2 shared publications - Lei Guo
College of Computer Science and Technology, Shandong Normal University, Jinan, China
2 shared publications - Lei Zhu
Tongji University, Shanghai, China
2 shared publications - Min Hou
Hefei University of Technology
2 shared publications Chen Yehui
Department of Physics, University of Science and Technology of China, 230026 Hefei, China
1 shared publication- Chenxi Yu
Research Center of Big Data Technology Nanhu Laboratory,JiaXing,China
1 shared publication
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6342-6353
WeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging
Cross-Domain Sequential Recommendation (CDSR) seeks to improve user preference modeling by transferring knowledge from multiple domains. Despite the progress made in CDSR, most existing methods rely on overlapping users or items to establish cross-domain correlations-a requirement that rarely holds in real-world settings. The advent of large language models (LLM) and model-merging techniques appears to overcome this limitation by unifying multi-domain data without explicit overlaps. Yet, our empirical study shows that naively training an LLM on combined domains—or simply merging several domain-specific LLMs—often degrades performance relative to a model trained solely on the target domain. To address these challenges, we first experimentally investigate the cause of suboptimal performance in LLM-based cross-domain recommendation and model merging. Building on these insights, we introduce WeaveRec, which cross-trains multiple LoRA modules with source and target domain data in a ''weaving'' fashion, and fuses them via model merging. WeaveRec can be extended to multi-source domain scenarios and notably does not introduce additional inference-time cost in terms of latency or memory. Furthermore, we provide a theoretical guarantee that WeaveRec can reduce the upper bound of the expected error in the target domain. Extensive experiments on single-source, multi-source, and cross-platform cross-domain recommendation scenarios validate that WeaveRec effectively mitigates performance degradation and consistently outperforms baseline approaches in real?world recommendation tasks. Codes are available at https://github.com/mertell/WeaveRec.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6342-6353
Open AccessWeaveRec: An LLM-Based Cross-Domain Sequential Recommendation Framework with Model Merging
Cross-Domain Sequential Recommendation (CDSR) seeks to improve user preference modeling by transferring knowledge from multiple domains. Despite the progress made in CDSR, most existing methods rely on overlapping users or items to establish cross-domain correlations-a requirement that rarely holds in real-world settings. The advent of large language models (LLM) and model-merging techniques appears to overcome this limitation by unifying multi-domain data without explicit overlaps. Yet, our empirical study shows that naively training an LLM on combined domains—or simply merging several domain-specific LLMs—often degrades performance relative to a model trained solely on the target domain. To address these challenges, we first experimentally investigate the cause of suboptimal performance in LLM-based cross-domain recommendation and model merging. Building on these insights, we introduce WeaveRec, which cross-trains multiple LoRA modules with source and target domain data in a ''weaving'' fashion, and fuses them via model merging. WeaveRec can be extended to multi-source domain scenarios and notably does not introduce additional inference-time cost in terms of latency or memory. Furthermore, we provide a theoretical guarantee that WeaveRec can reduce the upper bound of the expected error in the target domain. Extensive experiments on single-source, multi-source, and cross-platform cross-domain recommendation scenarios validate that WeaveRec effectively mitigates performance degradation and consistently outperforms baseline approaches in real?world recommendation tasks. Codes are available at https://github.com/mertell/WeaveRec.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1603-1613
Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1603-1613
Open AccessMitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective
- Open Access
- 9 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (4) , 1-24
MCRPL: A Pretrain, Prompt, and Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation
Cross-domain Recommendation is the task that tends to improve the recommendations in the sparse target domain by leveraging the information from other rich domains. Existing methods of cross-domain recommendation mainly focus on overlapping scenarios by assuming users are totally or partially overlapped, which are taken as bridges to connect different domains. However, this assumption does not always hold, since it is illegal to leak users’ identity information to other domains. Conducting Non-overlapping MCR (NMCR) is challenging, since (1) the absence of overlapping information prevents us from directly aligning different domains, and this situation may get worse in the MCR scenario, and (2) the distribution between source and target domains makes it difficult for us to learn common information across domains. To overcome the above challenges, we focus on NMCR and devise MCRPL as our solution. To address Challenge 1, we first learn shared domain-agnostic and domain-dependent prompts and pre-train them in the pre-training stage. To address Challenge 2, we further update the domain-dependent prompts with other parameters kept fixed to transfer the domain knowledge to the target domain. We conduct experiments on five real-world domains, and the results show the advance of our MCRPL method compared with several recent SOTA baselines. Moreover, our source codes have been publicly released. 1
- 9 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (4) , 1-24
Open AccessMCRPL: A Pretrain, Prompt, and Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation
Cross-domain Recommendation is the task that tends to improve the recommendations in the sparse target domain by leveraging the information from other rich domains. Existing methods of cross-domain recommendation mainly focus on overlapping scenarios by assuming users are totally or partially overlapped, which are taken as bridges to connect different domains. However, this assumption does not always hold, since it is illegal to leak users’ identity information to other domains. Conducting Non-overlapping MCR (NMCR) is challenging, since (1) the absence of overlapping information prevents us from directly aligning different domains, and this situation may get worse in the MCR scenario, and (2) the distribution between source and target domains makes it difficult for us to learn common information across domains. To overcome the above challenges, we focus on NMCR and devise MCRPL as our solution. To address Challenge 1, we first learn shared domain-agnostic and domain-dependent prompts and pre-train them in the pre-training stage. To address Challenge 2, we further update the domain-dependent prompts with other parameters kept fixed to transfer the domain knowledge to the target domain. We conduct experiments on five real-world domains, and the results show the advance of our MCRPL method compared with several recent SOTA baselines. Moreover, our source codes have been publicly released. 1
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 173-177
Corddl: An Efficient and Extensible Connector between Relational Databases and Data Lakes
In the era of big data, data lakes have been widely used. However, enterprise applications generally do not interact directly with data lakes, but with relational databases. Relational databases may become data silos because they can only store structured data. In this paper, we proposed Corddl, a connector between relational databases and data lakes. For ingesting data from a relational database into a data lake, first, Corddl uses configuration files and parameters to match the data source class and data source instance for the analysis engine. Then, Corddl uses the JDBC driver to realize the connection to the relational database, and do data conversion according to the data type configuration file. Finally, the ingested data is written into the data lake. There is a similar process for ingesting data from a data lake into a relational database. Experimental results show that Corddl has high efficiency and strong extensibility.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 173-177
Corddl: An Efficient and Extensible Connector between Relational Databases and Data Lakes
In the era of big data, data lakes have been widely used. However, enterprise applications generally do not interact directly with data lakes, but with relational databases. Relational databases may become data silos because they can only store structured data. In this paper, we proposed Corddl, a connector between relational databases and data lakes. For ingesting data from a relational database into a data lake, first, Corddl uses configuration files and parameters to match the data source class and data source instance for the analysis engine. Then, Corddl uses the JDBC driver to realize the connection to the relational database, and do data conversion according to the data type configuration file. Finally, the ingested data is written into the data lake. There is a similar process for ingesting data from a data lake into a relational database. Experimental results show that Corddl has high efficiency and strong extensibility.
- Open Access
- 7 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (2) , 1-27
DA-DAN: A Dual Adversarial Domain Adaption Network for Unsupervised Non-overlapping Cross-domain Recommendation
Unsupervised Non-overlapping Cross-domain Recommendation (UNCR) is the task that recommends source domain items to the target domain users, which is more challenging as the users are non-overlapped, and its learning process is unsupervised. Unsupervised Non-overlapping Cross-domain Recommendation UNCR is still unsolved due to the following: (1) Previous studies need extra auxiliary information to learn transferable features when aligning two domains, which is unrealistic and hard to obtain due to privacy concerns. (2) Since the adoption of the shared network, existing works cannot well eliminate the domain-specific features in the common feature space, which may incorporate domain noise and harm the cross-domain recommendation. In this work, we propose a domain adaption-based method, namely DA-DAN, to address the above challenges. Specifically, to let DA-DAN be free of auxiliary information, we learn users’ preferences by only exploring their sequential patterns, and propose an improved self-attention layer to model them. To well eliminate the domain-specific features from the common feature space, we resort to a dual generative adversarial network with a multi-target adversarial loss, where two generators and discriminators are leveraged to model each domain separately. Experimental results on three real-world datasets demonstrate the advantage of DA-DAN compared with the state-of-the-art recommendation baselines. Moreover, our source codes have been publicly released. 1
- 7 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 42 (2) , 1-27
Open AccessDA-DAN: A Dual Adversarial Domain Adaption Network for Unsupervised Non-overlapping Cross-domain Recommendation
Unsupervised Non-overlapping Cross-domain Recommendation (UNCR) is the task that recommends source domain items to the target domain users, which is more challenging as the users are non-overlapped, and its learning process is unsupervised. Unsupervised Non-overlapping Cross-domain Recommendation UNCR is still unsolved due to the following: (1) Previous studies need extra auxiliary information to learn transferable features when aligning two domains, which is unrealistic and hard to obtain due to privacy concerns. (2) Since the adoption of the shared network, existing works cannot well eliminate the domain-specific features in the common feature space, which may incorporate domain noise and harm the cross-domain recommendation. In this work, we propose a domain adaption-based method, namely DA-DAN, to address the above challenges. Specifically, to let DA-DAN be free of auxiliary information, we learn users’ preferences by only exploring their sequential patterns, and propose an improved self-attention layer to model them. To well eliminate the domain-specific features from the common feature space, we resort to a dual generative adversarial network with a multi-target adversarial loss, where two generators and discriminators are leveraged to model each domain separately. Experimental results on three real-world datasets demonstrate the advantage of DA-DAN compared with the state-of-the-art recommendation baselines. Moreover, our source codes have been publicly released. 1
- Open Access
- 1 April 2016
- Published by Science Alert in Journal of Software Engineering
- Vol. 10 (4) , 408-415
Human Activity Recognition Based-on Conditional Random Fields with Human Body Parts
- 1 April 2016
- Published by Science Alert in Journal of Software Engineering
- Vol. 10 (4) , 408-415
Open AccessHuman Activity Recognition Based-on Conditional Random Fields with Human Body Parts