no code implementations • Findings (EMNLP) 2021 • Zhiwei Yang, Jing Ma, Hechang Chen, Yunke Zhang, Yi Chang
Specifically, we first utilize a two-phase module to generate span representations by aggregating context information based on a bottom-up and top-down transformer network.
no code implementations • 21 Oct 2024 • Jifeng Hu, Sili Huang, Li Shen, Zhejian Yang, Shengchao Hu, Shisong Tang, Hechang Chen, Yi Chang, DaCheng Tao, Lichao Sun
In the quantized spaces alignment, we leverage vector quantization to align the different state and action spaces of various tasks, facilitating continual training in the same space.
1 code implementation • 4 Sep 2024 • Jifeng Hu, Li Shen, Sili Huang, Zhejian Yang, Hechang Chen, Lichao Sun, Yi Chang, DaCheng Tao
Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static.
no code implementations • 13 Jun 2024 • Fan Li, Xu Si, Shisong Tang, Dingmin Wang, Kunyan Han, Bing Han, Guorui Zhou, Yang song, Hechang Chen
The diversity of recommendation is equally crucial as accuracy in improving user experience.
no code implementations • 31 May 2024 • Sili Huang, Jifeng Hu, Zhejian Yang, Liwei Yang, Tao Luo, Hechang Chen, Lichao Sun, Bo Yang
Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory.
1 code implementation • 31 May 2024 • Sili Huang, Jifeng Hu, Hechang Chen, Lichao Sun, Bo Yang
Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem.
no code implementations • 28 Apr 2024 • Zesheng Hong, Yubiao Yue, Yubin Chen, Lele Cong, Huanjie Lin, Yuanmei Luo, Mini Han Wang, Weidong Wang, Jialong Xu, Xiaoqi Yang, Hechang Chen, Zhenzhang Li, Sihong Xie
Recently, research has explored various out-of-distribution (OOD) detection situations and techniques to enable a trustworthy medical AI system.
1 code implementation • 27 Feb 2024 • Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, Jun Wang
In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models.
no code implementations • NeurIPS 2023 • Sili Huang, Yanchao Sun, Jifeng Hu, Siyuan Guo, Hechang Chen, Yi Chang, Lichao Sun, Bo Yang
Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.
no code implementations • 22 Aug 2023 • Xing Chen, Yijun Liu, Zhaogeng Liu, Hechang Chen, Hengshuai Yao, Yi Chang
In prior work, it has been shown that policy-based exploration is beneficial for continuous action space in deterministic policy reinforcement learning(DPRL).
no code implementations • 13 Jun 2023 • Siyuan Guo, Yanchao Sun, Jifeng Hu, Sili Huang, Hechang Chen, Haiyin Piao, Lichao Sun, Yi Chang
However, constrained by the limited quality of the offline dataset, its performance is often sub-optimal.
no code implementations • 8 Jun 2023 • Jifeng Hu, Yanchao Sun, Sili Huang, Siyuan Guo, Hechang Chen, Li Shen, Lichao Sun, Yi Chang, DaCheng Tao
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
1 code implementation • 18 Apr 2023 • Bo Yu, Hechang Chen, Yunke Zhang, Lele Cong, Shuchao Pang, Hongren Zhou, Ziye Wang, Xianling Cong
In this paper, we propose a Data and Knowledge Co-driving (D&K) model to replicate the process of cancer subtype classification on a histopathological slide like a pathologist.
no code implementations • 18 Apr 2023 • Bo Yu, Hechang Chen, Chengyou Jia, Hongren Zhou, Lele Cong, Xiankai Li, Jianhui Zhuang, Xianling Cong
Second, a probability matrix and a weight matrix are used to enhance the classification capacity by combining the RS and medical history data in the multi-modality data fusion module.
no code implementations • 28 Feb 2023 • Bohao Qu, Xiaofeng Cao, Jielong Yang, Hechang Chen, Chang Yi, Ivor W. Tsang, Yew-Soon Ong
To resolve this problem, this paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment, in which a policy dispersion scheme is designed for seeking diverse policy representation.
1 code implementation • 14 Oct 2022 • Jifeng Hu, Yanchao Sun, Hechang Chen, Sili Huang, Haiyin Piao, Yi Chang, Lichao Sun
Our main idea is to design the multi-action-branch reward estimation and policy-weighted reward aggregation for stabilized training.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+2
no code implementations • 8 Oct 2022 • Yixiang Shan, Jielong Yang, Xing Liu, Yixing Gao, Hechang Chen, Shuzhi Sam Ge
Our model solves the first issue by simultaneously learning multiple relation graphs of data samples as well as a relation network of graphs, and solves the second and the third issue by selecting important data features as well as important data sample relations.
1 code implementation • COLING 2022 • Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, Yi Chang
Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances.
Ranked #3 on
Fake News Detection
on RAWFC
1 code implementation • 20 May 2022 • Xing Chen, Dongcui Diao, Hechang Chen, Hengshuai Yao, Haiyin Piao, Zhixiao Sun, Zhiwei Yang, Randy Goebel, Bei Jiang, Yi Chang
The popular Proximal Policy Optimization (PPO) algorithm approximates the solution in a clipped policy space.
1 code implementation • 28 May 2021 • Siyuan Guo, Lixin Zou, Yiding Liu, Wenwen Ye, Suqi Cheng, Shuaiqiang Wang, Hechang Chen, Dawei Yin, Yi Chang
Based on it, a more robust doubly robust (MRDR) estimator has been proposed to further reduce its variance while retaining its double robustness.
1 code implementation • 8 Sep 2019 • Zhining Liu, Wei Cao, Zhifeng Gao, Jiang Bian, Hechang Chen, Yi Chang, Tie-Yan Liu
To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers.