Publication

Preprints

• Haoyu Wang, Tianci Liu, Tuo Zhao, Jing Gao*, RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning. [paper]

• Haoyu Wang, Tuo Zhao, Jing Gao*, BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering. [paper]

• Taixi Lu, Haoyu Wang (equal contribution), Huajie Shao, Jing Gao, Huaxiu Yao, C$^{3}$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding. [paper]

Conference Paper

• Tianci Liu, Haoyu Wang, Shiyang Wang, Yu Cheng, Jing Gao*, LIDAO: Towards Limited Interventions for Debiasing (Large) Language Models. The 41st International Conference on Machine Learning (ICML 2024), Austria, Jul 2024.

• Tianci Liu, Haoyu Wang, Feijie Wu, Hengtong Zhang, Pan Li, Lu Su, Jing Gao*. Towards Poisoning Fair Representations, the 12th International Conference on Learning Representations (ICLR), Austria, May 2024.

• Haoyu Wang, Ruirui Li, Zhengyang Wang, Xianfeng Tang, Danqing Zhang, Monica Cheng, Bing Yin, Jasha Droppo, Suhang Wang, Jing Gao*. LightLT: a Lightweight Representation Quantization Framework for Long-tail Data, in Proceedings of the 40th IEEE International Conference on Data Engineering (ICDE 2024), Utrecht, Netherlands, May 2024.

• Haoyu Wang, Yaqing Wang, Tianci Liu, Tuo Zhao, Jing Gao*. HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference, Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), Singapore, Dec. 2023.

• Haoyu Wang, Yaqing Wang, Huaxiu Yao, Jing Gao*. Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding, Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2023), Singapore, Dec. 2023.

• Haoyu Wang, Ruirui Li, Haoming Jiang, Zhengyang Wang, Xianfeng Tang, Bin Bi, Monica Cheng, Bing Yin, Yaqing Wang, Tuo Zhao, Jing Gao*. LightToken: a Task and Model-agnostic Lightweight Token Embedding Framework for Pre-trained Language Models, in Proceedings of the 29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), Long Beach, California, United States, Aug. 2023. 

• Haoyu Wang, Yaqing Wang, Feijie Wu, Hongfei Xue, Jing Gao*. Macular: a Multi-Task Adversarial Framework for Cross-Lingual Natural Language Understanding, in Proceedings of the 29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), Long Beach, California, United States, Aug. 2023. 

• Tianci Liu, Haoyu Wang, Yaqing Wang, Xiaoqian Wang, Lu Su, Jing Gao*.  SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). Washington D.C., Feb 2023. (Distinguished Paper Award.)

• Hongfei Xue, Qiming Cao, Yan Ju, Haochen Hu, Haoyu Wang, Aidong Zhang, Lu Su. M4esh: mmWave-based 3D Human Mesh Construction for Multiple Subjects, in  Proceedings of the 20th ACM Conference on Embedded Networked Sensor System (SenSys 2022).

• Haoyu Wang, Handong Zhao, Yaqing Wang, Tong Yu, Jiuxiang Gu, and Jing Gao*. FedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding. The Web Conference (WWW 2022), online, April 2022.

• Haoyu Wang, Xuan Wang, Yaqing Wang, Guangxu Xun, Kishlay Jha, and Jing Gao*. InterHG: an Interpretable and Accurate Model for Hypothesis Generation. IEEE International Conference on Bioinformatics and Biomedicine 2021 (IEEE BIBM 2021, short paper), online, Dec. 2021.

• Haoyu Wang, Fenglong Ma, Yaqing Wang and Jing Gao*. Knowledge-Guided Paraphrase Identification. Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2021), online, Nov. 2021.

• Haoyu Wang, Yaqing Wang, Defu Lian, Jing Gao*. A Lightweight Knowledge Graph Embedding Framework for Efficient Inference and Storage. The 30th ACM International Conference on Information and Knowledge Management (CIKM 2021), online, Nov. 2021.

• Yaqing Wang, Fenglong Ma, Haoyu Wang, Kishlay Jha, Jing Gao*. Multi-modal Emergent Fake News Detection via Meta Neural Process Networks, in Proceedings of the 27th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021), Singapore, Aug. 2021. 

• Gangwei Jiang, Hao Wang, Jin Chen, Haoyu Wang, Defu Lian* and Enhong Chen. xLightFM: Extremely Memory-Efficient Factorization Machine. The 44th ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021), online, Jul. 2021

• Haoyu Wang, Hengtong Zhang, Yaqing Wang, Jing Gao*. Fair Classification Under Strict Unawareness. SIAM International Conference on Data Mining (SDM 2021), Alexandria, VA, April 2021. 

• Defu Lian, Haoyu Wang, Zheng Liu, Jianxun Lian, Enhong Chen and Xing Xie. LightRec: a Memory and Search-Efficient Recommender System. The 28th Web Conference (WWW 2020), Taipei, China, April, 2020. (Oral)[code]

• Haoyu Wang, Defu Lian*, Yong Ge. Binarized Collaborative Filtering with Distilling Graph Convolutional Network. The 27th International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao, China, August, 2019. (Oral)

• HaoYu Wang, Nan Shao, DeFu Lian*. Adversarial Binary Collaborative Filtering For Implicit Feedback, in Proceeding of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019), Honolulu, Hawaii, Jan. 2019. (Spotlight)

• Yan Zhang, Haoyu Wang, Defu Lian*, Ivor W. Tsang, Hongzhi Yin and Guowu Yang, Discrete Ranking-based Matrix Factorization with Self-Paced Learning, in Proceedings of the Twenty-fourth SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2018), London, UK, Aug. 2018. (Research track,Oral)