no code implementations • NAACL 2022 • Haiyan Yin, Dingcheng Li, Ping Li
In this paper, we propose a new weakly supervised paraphrase generation approach that extends the success of a recent work that leverages reinforcement learning for effective model training with data selection.
no code implementations • 1 Dec 2022 • Linbo Luo, Yuanjing Li, Haiyan Yin, Shangwei Xie, Ruimin Hu, Wentong Cai
In this paper, we present a systematic study to tackle the important problem of VAD for CABs with a novel crowd motion learning framework, multi-scale motion consistency network (MSMC-Net).
1 code implementation • ICDM 21 2021 • Shaogang Ren, Haiyan Yin, Mingming Sun, Ping Li
Then we formulate a novel evaluation metric to infer the scores for each potential causal direction based on the variance of the conditional density estimation.
no code implementations • NeurIPS 2021 • Haiyan Yin, Peng Yang, Ping Li
Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.
no code implementations • NeurIPS 2021 • Haiyan Yin, Peng Yang, Ping Li
Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.
no code implementations • 9 May 2021 • Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin
We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI).
no code implementations • NeurIPS Workshop LMCA 2020 • Haiyan Yin, Yingzhen Li, Sinno Jialin Pan, Cheng Zhang, Sebastian Tschiatschek
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem.
no code implementations • 12 Mar 2020 • Haiyan Yin, Dingcheng Li, Xu Li, Ping Li
To this end, we introduce a cooperative training paradigm, where a language model is cooperatively trained with the generator and we utilize the language model to efficiently shape the data distribution of the generator against mode collapse.
no code implementations • 25 Sep 2019 • Haiyan Yin, Jianda Chen, Sinno Jialin Pan
First, we propose a new reasoning paradigm to infer the novelty for the partially observable states, which is built upon forward dynamics prediction.
no code implementations • 3 Jul 2017 • Haiyan Yin, Jianda Chen, Sinno Jialin Pan
In deep reinforcement learning (RL) tasks, an efficient exploration mechanism should be able to encourage an agent to take actions that lead to less frequent states which may yield higher accumulative future return.