no code implementations • ACL 2022 • Juncheng Wan, Dongyu Ru, Weinan Zhang, Yong Yu
In this work, we try to improve the span representation by utilizing retrieval-based span-level graphs, connecting spans and entities in the training data based on n-gram features.
1 code implementation • 20 Apr 2022 • Yunjia Xi, Weiwen Liu, Jieming Zhu, Xilong Zhao, Xinyi Dai, Ruiming Tang, Weinan Zhang, Rui Zhang, Yong Yu
MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list.
no code implementations • 30 Mar 2022 • Guan Yang, Minghuan Liu, Weijun Hong, Weinan Zhang, Fei Fang, Guangjun Zeng, Yue Lin
To this end, we characterize card and game features for DouDizhu to represent the perfect and imperfect information.
no code implementations • 26 Mar 2022 • Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, HuaWei Shen, HUI ZHANG, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan YAO, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, LiWei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
no code implementations • 20 Mar 2022 • Xihuai Wang, Zhicheng Zhang, Weinan Zhang
Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants.
no code implementations • 4 Mar 2022 • Minghuan Liu, Zhengbang Zhu, Yuzheng Zhuang, Weinan Zhang, Jianye Hao, Yong Yu, Jun Wang
Recent progress in state-only imitation learning extends the scope of applicability of imitation learning to real-world settings by relieving the need for observing expert actions.
1 code implementation • 25 Feb 2022 • Ting Long, Yutong Xie, Xianyu Chen, Weinan Zhang, Qinxiang Cao, Yong Yu
We thoroughly evaluate our proposed MVG approach in the context of algorithm detection, an important and challenging subfield of PLP.
1 code implementation • 14 Feb 2022 • Weiwen Liu, Yunjia Xi, Jiarui Qin, Fei Sun, Bo Chen, Weinan Zhang, Rui Zhang, Ruiming Tang
As the final stage of the multi-stage recommender system (MRS), re-ranking directly affects user experience and satisfaction by rearranging the input ranking lists, and thereby plays a critical role in MRS. With the advances in deep learning, neural re-ranking has become a trending topic and been widely applied in industrial applications.
no code implementations • 9 Feb 2022 • Jiarui Jin, Xianyu Chen, Yuanbo Chen, Weinan Zhang, Renting Rui, Zaifan Jiang, Zhewen Su, Yong Yu
With the prevalence of live broadcast business nowadays, a new type of recommendation service, called live broadcast recommendation, is widely used in many mobile e-commerce Apps.
no code implementations • 7 Feb 2022 • Jiarui Jin, Xianyu Chen, Weinan Zhang, JunJie Huang, Ziming Feng, Yong Yu
More concretely, we first design a search-based module to retrieve a user's relevant historical behaviors, which are then mixed up with her recent records to be fed into a time-aware sequential network for capturing her time-sensitive demands.
no code implementations • 28 Jan 2022 • Ming Zhou, Jingxiao Chen, Ying Wen, Weinan Zhang, Yaodong Yang, Yong Yu
Policy Space Response Oracle method (PSRO) provides a general solution to Nash equilibrium in two-player zero-sum games but suffers from two problems: (1) the computation inefficiency due to consistently evaluating current populations by simulations; and (2) the exploration inefficiency due to learning best responses against a fixed meta-strategy at each iteration.
no code implementations • 27 Jan 2022 • Weijun Hong, Menghui Zhu, Minghuan Liu, Weinan Zhang, Ming Zhou, Yong Yu, Peng Sun
Exploration is crucial for training the optimal reinforcement learning (RL) policy, where the key is to discriminate whether a state visiting is novel.
1 code implementation • 27 Jan 2022 • Weijun Hong, Guilin Li, Weinan Zhang, Ruiming Tang, Yunhe Wang, Zhenguo Li, Yong Yu
Neural architecture search (NAS) has shown encouraging results in automating the architecture design.
no code implementations • 24 Jan 2022 • Xiangkun Hu, Hang Yan, Qipeng Guo, Xipeng Qiu, Weinan Zhang, Zheng Zhang
Knowledge and expertise in the real-world can be disjointedly owned.
1 code implementation • 20 Jan 2022 • Minghuan Liu, Menghui Zhu, Weinan Zhang
Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios.
no code implementations • 6 Jan 2022 • Juncheng Wan, Jian Yang, Shuming Ma, Dongdong Zhang, Weinan Zhang, Yong Yu, Furu Wei
In this paper, we propose a phrase-level adversarial example generation (PAEG) method to enhance the robustness of the model.
1 code implementation • 6 Dec 2021 • Linghui Meng, Muning Wen, Yaodong Yang, Chenyang Le, Xiyun Li, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Bo Xu
In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL.
no code implementations • NeurIPS 2021 • Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, Tie-Yan Liu
However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies.
1 code implementation • 19 Nov 2021 • Jianfeng Chi, Jian Shen, Xinyi Dai, Weinan Zhang, Yuan Tian, Han Zhao
We first provide a decomposition theorem for return disparity, which decomposes the return disparity of any two MDPs sharing the same state and action spaces into the distance between group-wise reward functions, the discrepancy of group policies, and the discrepancy between state visitation distributions induced by the group policies.
no code implementations • 16 Nov 2021 • Handong Ma, Jiawei Hou, Chenxu Zhu, Weinan Zhang, Ruiming Tang, Jincai Lai, Jieming Zhu, Xiuqiang He, Yong Yu
Pseudo relevance feedback (PRF) automatically performs query expansion based on top-retrieved documents to better represent the user's information need so as to improve the search results.
1 code implementation • NeurIPS 2021 • Hang Lai, Jian Shen, Weinan Zhang, Yimin Huang, Xing Zhang, Ruiming Tang, Yong Yu, Zhenguo Li
Model-based reinforcement learning has attracted wide attention due to its superior sample efficiency.
1 code implementation • EMNLP 2021 • Dongyu Ru, Changzhi Sun, Jiangtao Feng, Lin Qiu, Hao Zhou, Weinan Zhang, Yong Yu, Lei LI
LogiRE treats logic rules as latent variables and consists of two modules: a rule generator and a relation extractor.
Ranked #18 on
Relation Extraction
on DocRED
1 code implementation • 5 Nov 2021 • Chenxu Zhu, Bo Chen, Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu
To address these three issues mentioned above, we propose Automatic Interaction Machine (AIM) with three core components, namely, Feature Interaction Search (FIS), Interaction Function Search (IFS) and Embedding Dimension Search (EDS), to select significant feature interactions, appropriate interaction functions and necessary embedding dimensions automatically in a unified framework.
1 code implementation • 3 Nov 2021 • Minghuan Liu, Hanye Zhao, Zhengyu Yang, Jian Shen, Weinan Zhang, Li Zhao, Tie-Yan Liu
However, IL is usually limited in the capability of the behavioral policy and tends to learn a mediocre behavior from the dataset collected by the mixture of policies.
no code implementations • 18 Oct 2021 • Yunjia Xi, Weiwen Liu, Xinyi Dai, Ruiming Tang, Weinan Zhang, Qing Liu, Xiuqiang He, Yong Yu
As a critical task for large-scale commercial recommender systems, reranking has shown the potential of improving recommendation results by uncovering mutual influence among items.
no code implementations • ICLR 2022 • Yangkun Wang, Jiarui Jin, Weinan Zhang, Yongyi Yang, Jiuhai Chen, Quan Gan, Yong Yu, Zheng Zhang, Zengfeng Huang, David Wipf
In this regard, it has recently been proposed to use a randomly-selected portion of the training labels as GNN inputs, concatenated with the original node features for making predictions on the remaining labels.
no code implementations • ICLR 2022 • Jiarui Jin, Yangkun Wang, Kounianhua Du, Weinan Zhang, Zheng Zhang, David Wipf, Yong Yu, Quan Gan
Prevailing methods for relation prediction in heterogeneous graphs aim at learning latent representations (i. e., embeddings) of observed nodes and relations, and thus are limited to the transductive setting where the relation types must be known during training.
no code implementations • ICLR 2022 • Jiarui Jin, Sijin Zhou, Weinan Zhang, Tong He, Yong Yu, Rasool Fakoor
Goal-oriented Reinforcement Learning (GoRL) is a promising approach for scaling up RL techniques on sparse reward environments requiring long horizon planning.
no code implementations • NeurIPS 2021 • Minghuan Liu, Zhengbang Zhu, Yuzheng Zhuang, Weinan Zhang, Jian Shen, Jianye Hao, Yong Yu, Jun Wang
State-only imitation learning (SOIL) enables agents to learn from massive demonstrations without explicit action or reward information.
no code implementations • 29 Sep 2021 • Tairan He, Yuge Zhang, Kan Ren, Che Wang, Weinan Zhang, Dongsheng Li, Yuqing Yang
A good state representation is crucial to reinforcement learning (RL) while an ideal representation is hard to learn only with signals from the RL objective.
no code implementations • 29 Sep 2021 • Zhengyu Yang, Kan Ren, Xufang Luo, Weiqing Liu, Jiang Bian, Weinan Zhang, Dongsheng Li
Ensemble learning, which can consistently improve the prediction performance in supervised learning, has drawn increasing attentions in reinforcement learning (RL).
no code implementations • 29 Sep 2021 • Linghui Meng, Muning Wen, Yaodong Yang, Chenyang Le, Xi yun Li, Haifeng Zhang, Ying Wen, Weinan Zhang, Jun Wang, Bo Xu
Offline reinforcement learning leverages static datasets to learn optimal policies with no necessity to access the environment.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
no code implementations • 16 Aug 2021 • Mingcheng Chen, Zhenghui Wang, Zhiyun Zhao, Weinan Zhang, Xiawei Guo, Jian Shen, Yanru Qu, Jieli Lu, Min Xu, Yu Xu, Tiange Wang, Mian Li, Wei-Wei Tu, Yong Yu, Yufang Bi, Weiqing Wang, Guang Ning
To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency.
1 code implementation • 11 Aug 2021 • Jiarui Qin, Weinan Zhang, Rong Su, Zhirong Liu, Weiwen Liu, Ruiming Tang, Xiuqiang He, Yong Yu
Prediction over tabular data is an essential task in many data science applications such as recommender systems, online advertising, medical treatment, etc.
no code implementations • Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 2021 • Jianghao Lin, Weiwen Liu, Xinyi Dai, Weinan Zhang, Shuai Li, Ruiming Tang, Xiuqiang He, Jianye Hao, Yong Yu
To better exploit search logs and model users' behavior patterns, numerous click models are proposed to extract users' implicit interaction feedback.
1 code implementation • 5 Jun 2021 • Ming Zhou, Ziyu Wan, Hanjing Wang, Muning Wen, Runzhe Wu, Ying Wen, Yaodong Yang, Weinan Zhang, Jun Wang
Our framework is comprised of three key components: (1) a centralized task dispatching model, which supports the self-generated tasks and scalable training with heterogeneous policy combinations; (2) a programming architecture named Actor-Evaluator-Learner, which achieves high parallelism for both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible deployments on different distributed computing paradigms.
no code implementations • 28 May 2021 • Zeren Huang, Kerong Wang, Furui Liu, Hui-Ling Zhen, Weinan Zhang, Mingxuan Yuan, Jianye Hao, Yong Yu, Jun Wang
In the online A/B testing of the product planning problems with more than $10^7$ variables and constraints daily, Cut Ranking has achieved the average speedup ratio of 12. 42% over the production solver without any accuracy loss of solution.
1 code implementation • 13 May 2021 • Menghui Zhu, Minghuan Liu, Jian Shen, Zhicheng Zhang, Sheng Chen, Weinan Zhang, Deheng Ye, Yong Yu, Qiang Fu, Wei Yang
In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem.
1 code implementation • 7 May 2021 • Weinan Zhang, Xihuai Wang, Jian Shen, Ming Zhou
We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound.
no code implementations • 21 Apr 2021 • Weinan Zhang, Jiarui Qin, Wei Guo, Ruiming Tang, Xiuqiang He
In this survey, we provide a comprehensive review of deep learning models for CTR estimation tasks.
1 code implementation • 13 Apr 2021 • Xinyi Dai, Jianghao Lin, Weinan Zhang, Shuai Li, Weiwen Liu, Ruiming Tang, Xiuqiang He, Jianye Hao, Jun Wang, Yong Yu
Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback.
1 code implementation • 24 Mar 2021 • Yangkun Wang, Jiarui Jin, Weinan Zhang, Yong Yu, Zheng Zhang, David Wipf
Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
1 code implementation • ICLR 2021 • Yutong Xie, Chence Shi, Hao Zhou, Yuwei Yang, Weinan Zhang, Yong Yu, Lei LI
Searching for novel molecules with desired chemical properties is crucial in drug discovery.
3 code implementations • 1 Feb 2021 • Rongjun Qin, Songyi Gao, Xingyuan Zhang, Zhen Xu, Shengkai Huang, Zewen Li, Weinan Zhang, Yang Yu
We evaluate existing offline RL algorithms on NeoRL and argue that the performance of a policy should also be compared with the deterministic version of the behavior policy, instead of the dataset reward.
no code implementations • 28 Jan 2021 • Yuchen Fang, Kan Ren, Weiqing Liu, Dong Zhou, Weinan Zhang, Jiang Bian, Yong Yu, Tie-Yan Liu
As a fundamental problem in algorithmic trading, order execution aims at fulfilling a specific trading order, either liquidation or acquirement, for a given instrument.
no code implementations • 1 Jan 2021 • Jiarui Jin, Cong Chen, Ming Zhou, Weinan Zhang, Rasool Fakoor, David Wipf, Yong Yu, Jun Wang, Alex Smola
Goal-oriented reinforcement learning algorithms are often good at exploration, not exploitation, while episodic algorithms excel at exploitation, not exploration.
no code implementations • 1 Jan 2021 • Jiarui Jin, Sijin Zhou, Weinan Zhang, Rasool Fakoor, David Wipf, Tong He, Yong Yu, Zheng Zhang, Alex Smola
In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.
no code implementations • 1 Jan 2021 • Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei LI
Although non-autoregressive models with one-iteration generation achieves remarkable inference speed-up, they still falls behind their autoregressive counterparts inprediction accuracy.
no code implementations • 18 Dec 2020 • Sheng Chen, Menghui Zhu, Deheng Ye, Weinan Zhang, Qiang Fu, Wei Yang
Hero drafting is essential in MOBA game playing as it builds the team of each side and directly affects the match outcome.
1 code implementation • 16 Dec 2020 • Huifeng Guo, Bo Chen, Ruiming Tang, Weinan Zhang, Zhenguo Li, Xiuqiang He
In this paper, we propose a novel embedding learning framework for numerical features in CTR prediction (AutoDis) with high model capacity, end-to-end training and unique representation properties preserved.
1 code implementation • 14 Dec 2020 • Qipeng Guo, Zhijing Jin, Ziyu Wang, Xipeng Qiu, Weinan Zhang, Jun Zhu, Zheng Zhang, David Wipf
Cycle-consistent training is widely used for jointly learning a forward and inverse mapping between two domains of interest without the cumbersome requirement of collecting matched pairs within each domain.
1 code implementation • 7 Dec 2020 • Minkai Xu, Zhiming Zhou, Guansong Lu, Jian Tang, Weinan Zhang, Yong Yu
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models.
1 code implementation • 5 Dec 2020 • Minkai Xu, Mingxuan Wang, Zhouhan Lin, Hao Zhou, Weinan Zhang, Lei LI
Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT).
1 code implementation • 25 Nov 2020 • Jiarui Jin, Kounianhua Du, Weinan Zhang, Jiarui Qin, Yuchen Fang, Yong Yu, Zheng Zhang, Alexander J. Smola
Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations.
no code implementations • 1 Nov 2020 • Xinyi Dai, Jiawei Hou, Qing Liu, Yunjia Xi, Ruiming Tang, Weinan Zhang, Xiuqiang He, Jun Wang, Yong Yu
To this end, we propose a novel ranking framework called U-rank that directly optimizes the expected utility of the ranking list.
no code implementations • NeurIPS 2020 • Cheng Chen, Luo Luo, Weinan Zhang, Yong Yu
The Frank-Wolfe algorithm is a classic method for constrained optimization problems.
1 code implementation • NeurIPS 2020 • Jian Shen, Han Zhao, Weinan Zhang, Yong Yu
However, due to the potential distribution mismatch between simulated data and real data, this could lead to degraded performance.
3 code implementations • 19 Oct 2020 • Ming Zhou, Jun Luo, Julian Villella, Yaodong Yang, David Rusu, Jiayu Miao, Weinan Zhang, Montgomery Alban, Iman Fadakar, Zheng Chen, Aurora Chongxi Huang, Ying Wen, Kimia Hassanzadeh, Daniel Graves, Dong Chen, Zhengbang Zhu, Nhat Nguyen, Mohamed Elsayed, Kun Shao, Sanjeevan Ahilan, Baokuan Zhang, Jiannan Wu, Zhengang Fu, Kasra Rezaee, Peyman Yadmellat, Mohsen Rohani, Nicolas Perez Nieves, Yihan Ni, Seyedershad Banijamali, Alexander Cowen Rivers, Zheng Tian, Daniel Palenicek, Haitham Bou Ammar, Hongbo Zhang, Wulong Liu, Jianye Hao, Jun Wang
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
no code implementations • 11 Sep 2011 • Tianqi Chen, Zhao Zheng, Qiuxia Lu, Weinan Zhang, Yong Yu
Recommender system has been more and more popular and widely used in many applications recently.