Huachi Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huachi Zhou has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Xiao Huang
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
13 shared publications - Qinggang Zhang
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
5 shared publications - Ninghao Liu
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
4 shared publications - Hao Chen
Faculty of Data Science, City University of Macau, Macao SAR, China
3 shared publications - Daochen Zha
Airbnb, San Francisco, USA
2 shared publications - Fu-Lai Chung
Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13044-13055
ReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13044-13055
Open AccessReLU: Refined Chunk Embeddings Learning for Ultra-long SNP Genomic Prediction in Crop Breeding
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3835-3846
LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3835-3846
Open AccessLoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
- Open Access
- 26 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
Self-Monitoring Large Language Models for Click-Through Rate Prediction
Click-through rate prediction tasks estimate interaction probabilities using user-item features (i.e., the combined set of user and item features). LLMs have emerged as a promising approach by organizing these features into prompts and fine-tuning LLMs to predict the interaction label. However, our feature-wise and interaction-wise analysis reveals two critical limitations, leading to incomplete relationship modeling between user-item features and interaction labels: (i) LLMs tend to utilize only a subset of available features, neglecting others, and (ii) they struggle with predictions for tail items that appear less frequently in the training samples. To bridge this gap, we propose F eature- I nstructed L arge language model for M onitoring ( FILM ), which introduces a self-monitoring temperature mechanism that dynamically guides LLMs to focus on informative features, and an auxiliary compaction loss that facilitates better feature-interaction relationship learning for tail items. By integrating these two designs, FILM not only improves feature utilization in LLMs but also enhances predictions for tail items. Furthermore, we demonstrate that FILM -generated interaction embeddings can be transferred to lightweight models, enabling efficient deployment. Extensive experiments demonstrate that FILM achieves significant performance improvements over state-of-the-art baselines by learning better relationships between user-item features and interaction labels and generalizes under different LLM backbones.
- 26 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
Open AccessSelf-Monitoring Large Language Models for Click-Through Rate Prediction
Click-through rate prediction tasks estimate interaction probabilities using user-item features (i.e., the combined set of user and item features). LLMs have emerged as a promising approach by organizing these features into prompts and fine-tuning LLMs to predict the interaction label. However, our feature-wise and interaction-wise analysis reveals two critical limitations, leading to incomplete relationship modeling between user-item features and interaction labels: (i) LLMs tend to utilize only a subset of available features, neglecting others, and (ii) they struggle with predictions for tail items that appear less frequently in the training samples. To bridge this gap, we propose F eature- I nstructed L arge language model for M onitoring ( FILM ), which introduces a self-monitoring temperature mechanism that dynamically guides LLMs to focus on informative features, and an auxiliary compaction loss that facilitates better feature-interaction relationship learning for tail items. By integrating these two designs, FILM not only improves feature utilization in LLMs but also enhances predictions for tail items. Furthermore, we demonstrate that FILM -generated interaction embeddings can be transferred to lightweight models, enabling efficient deployment. Extensive experiments demonstrate that FILM achieves significant performance improvements over state-of-the-art baselines by learning better relationships between user-item features and interaction labels and generalizes under different LLM backbones.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17548-17559
Each graph is a new language: Graph Learning with LLMs
Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17548-17559
Open AccessEach graph is a new language: Graph Learning with LLMs
Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3566-3575
Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendation
Recommendation systems help users find matched items based on their previous behaviors. Personalized recommendation becomes challenging in the absence of historical user-item interactions, a practical problem for startups known as the system cold-start recommendation. While existing research addresses cold-start issues for either users or items, we still lack solutions for system cold-start scenarios. To tackle the problem, we propose PromptRec, a simple but effective approach based on in-context learning of language models, where we transform the recommendation task into the sentiment analysis task on natural language containing user and item profiles. However, this naive approach heavily relies on the strong in-context learning ability emerged from large language models, which could suffer from significant latency for online recommendations. To solve the challenge, we propose to enhance small language models for recommender systems with a data-centric pipeline, which consists of: (1) constructing a refined corpus for model pre-training; (2) constructing a decomposed prompt template via prompt pre-training. They correspond to the development of training data and inference data, respectively. The pipeline is supported by a theoretical framework that formalizes the connection between in-context recommendation and language modeling. To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only 17% of the inference time. To the best of our knowledge, this is the first study to tackle the system cold-start recommendation problem. We believe our findings will provide valuable insights for future works. The benchmark and implementations are available at https://github.com/JacksonWuxs/PromptRec.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 3566-3575
Open AccessCould Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendation
Recommendation systems help users find matched items based on their previous behaviors. Personalized recommendation becomes challenging in the absence of historical user-item interactions, a practical problem for startups known as the system cold-start recommendation. While existing research addresses cold-start issues for either users or items, we still lack solutions for system cold-start scenarios. To tackle the problem, we propose PromptRec, a simple but effective approach based on in-context learning of language models, where we transform the recommendation task into the sentiment analysis task on natural language containing user and item profiles. However, this naive approach heavily relies on the strong in-context learning ability emerged from large language models, which could suffer from significant latency for online recommendations. To solve the challenge, we propose to enhance small language models for recommender systems with a data-centric pipeline, which consists of: (1) constructing a refined corpus for model pre-training; (2) constructing a decomposed prompt template via prompt pre-training. They correspond to the development of training data and inference data, respectively. The pipeline is supported by a theoretical framework that formalizes the connection between in-context recommendation and language modeling. To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only 17% of the inference time. To the best of our knowledge, this is the first study to tackle the system cold-start recommendation problem. We believe our findings will provide valuable insights for future works. The benchmark and implementations are available at https://github.com/JacksonWuxs/PromptRec.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (9) , 11439-11451
Collaborative Parking Vacancy Prediction for Cities With Partial Sensors Missing
City-wide short-term parking vacancy (PV) prediction is essential to transportation management. In many cities, only partial parking lots are equipped with sensors, causing severe data missing issues. Predicting PVs for parking lots without sensors is attractive but challenging. First, PV prediction itself is a nontrivial task since spatial dependencies among different regions in a city are complex and dynamic. By connecting parking lots based on geographical closeness using pre-designed rules, state-of-the-art PV prediction models achieve reasonable performance. However, those connectivities are not able to adapt to capture the changing dependencies in the graph. Second, node-to-node-based spatial and temporal dependencies will no longer be reliable since neighboring parking lot sensors may be intensely missing, which deteriorates the ability of the model to accurately impute PVs, leveraging the complex dependencies. To this end, we propose a novel framework named Collaborative graph Learning for pArking vacancy Prediction (CLaP). Specifically, to overcome the limitation of traditional pre-designed node connections, we propose a collaborative training method incorporating node attributes into graph augmentation, thus enhancing the ability to capture dynamic spatial dependencies through message aggregation. Besides, a recurrent PV recovering module is developed to impute missing embeddings by deeply coupling spatial-temporal dependencies. Experimental results on two real-world datasets demonstrate that CLaP outperforms state-of-the-art PV prediction models on city-wide PV prediction and imputation precision for parking lots without sensors.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (9) , 11439-11451
Collaborative Parking Vacancy Prediction for Cities With Partial Sensors Missing
City-wide short-term parking vacancy (PV) prediction is essential to transportation management. In many cities, only partial parking lots are equipped with sensors, causing severe data missing issues. Predicting PVs for parking lots without sensors is attractive but challenging. First, PV prediction itself is a nontrivial task since spatial dependencies among different regions in a city are complex and dynamic. By connecting parking lots based on geographical closeness using pre-designed rules, state-of-the-art PV prediction models achieve reasonable performance. However, those connectivities are not able to adapt to capture the changing dependencies in the graph. Second, node-to-node-based spatial and temporal dependencies will no longer be reliable since neighboring parking lot sensors may be intensely missing, which deteriorates the ability of the model to accurately impute PVs, leveraging the complex dependencies. To this end, we propose a novel framework named Collaborative graph Learning for pArking vacancy Prediction (CLaP). Specifically, to overcome the limitation of traditional pre-designed node connections, we propose a collaborative training method incorporating node attributes into graph augmentation, thus enhancing the ability to capture dynamic spatial dependencies through message aggregation. Besides, a recurrent PV recovering module is developed to impute missing embeddings by deeply coupling spatial-temporal dependencies. Experimental results on two real-world datasets demonstrate that CLaP outperforms state-of-the-art PV prediction models on city-wide PV prediction and imputation precision for parking lots without sensors.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2417-2429
Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering
Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, Xiao Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 2417-2429
Open AccessModality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering
Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, Xiao Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 11736-11748
Enhancing Explainable Rating Prediction through Annotated Macro Concepts
Huachi Zhou, Shuang Zhou, Hao Chen, Ninghao Liu, Fan Yang, Xiao Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 11736-11748
Open AccessEnhancing Explainable Rating Prediction through Annotated Macro Concepts
Huachi Zhou, Shuang Zhou, Hao Chen, Ninghao Liu, Fan Yang, Xiao Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-17
Adaptive Popularity Debiasing Aggregator for Graph Collaborative Filtering
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 7-17
Open AccessAdaptive Popularity Debiasing Aggregator for Graph Collaborative Filtering
- Open Access
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. In practice, people usually need to identify anomalies on new (sub)graphs to secure their business, but they may lack labels to train an effective detection model. One natural idea is to directly adopt a trained GAD model to the new (sub)graph for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issue, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the same graph. It may cause great troubles. In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers. Nevertheless, it is a challenging task since only limited labels are available, and the normal background may differ between training and testing data. Accordingly, we propose a data augmentation method named \textit{AugAN} (\uline{Aug}mentation for \uline{A}nomaly and \uline{N}ormal distributions) to enrich training data and boost the generalizability of GAD models. Experiments verify the effectiveness of our method in improving model generalizability.
Open AccessImproving Generalizability of Graph Anomaly Detection Models via Data Augmentation
Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. In practice, people usually need to identify anomalies on new (sub)graphs to secure their business, but they may lack labels to train an effective detection model. One natural idea is to directly adopt a trained GAD model to the new (sub)graph for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issue, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the same graph. It may cause great troubles. In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers. Nevertheless, it is a challenging task since only limited labels are available, and the normal background may differ between training and testing data. Accordingly, we propose a data augmentation method named \textit{AugAN} (\uline{Aug}mentation for \uline{A}nomaly and \uline{N}ormal distributions) to enrich training data and boost the generalizability of GAD models. Experiments verify the effectiveness of our method in improving model generalizability.