Search Results for author: Bo An

Found 56 papers, 9 papers with code

Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games

no code implementations ICML 2020 Youzhi Zhang, Bo An

Second, we design an ISG variant for TMEs (ISGT) by exploiting that a TME is an NE maximizing the team’s utility and show that ISGT converges to a TME and the impossibility of relaxing conditions in ISGT.

Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets

1 code implementation17 Jun 2022 Hongxin Wei, Lue Tao, Renchunzi Xie, Lei Feng, Bo An

Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.

ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor

no code implementations1 Jun 2022 Wanqi Xue, Qingpeng Cai, Ruohan Zhan, Dong Zheng, Peng Jiang, Bo An

However, due to expensive online interactions, it is very difficult for RL algorithms to perform state-action value estimation, exploration and feature extraction when optimizing long-term engagement.

Sequential Recommendation

Mitigating Neural Network Overconfidence with Logit Normalization

1 code implementation19 May 2022 Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, Yixuan Li

Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output.

NSGZero: Efficiently Learning Non-Exploitable Policy in Large-Scale Network Security Games with Neural Monte Carlo Tree Search

no code implementations17 Jan 2022 Wanqi Xue, Bo An, Chai Kiat Yeo

Second, we enable neural MCTS with decentralized control, making NSGZero applicable to NSGs with many resources.

GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation

no code implementations16 Jan 2022 Renchunzi Xie, Hongxin Wei, Lei Feng, Bo An

Although there have been a few studies on this problem, most of them only exploit unidirectional relationships from the source domain to the target domain.

Domain Adaptation

DeepScalper: A Risk-Aware Deep Reinforcement Learning Framework for Intraday Trading with Micro-level Market Embedding

no code implementations15 Dec 2021 Shuo Sun, Rundong Wang, Xu He, Junlei Zhu, Jian Li, Bo An

However, it is hard to apply existing RL methods to intraday trading due to the following three limitations: 1) overlooking micro-level market information (e. g., limit order book); 2) only focusing on local price fluctuation and failing to capture the overall trend of the whole trading day; 3) neglecting the impact of market risk.

Algorithmic Trading reinforcement-learning

Pretrained Cost Model for Distributed Constraint Optimization Problems

1 code implementation8 Dec 2021 Yanchen Deng, Shufeng Kong, Bo An

Our model, GAT-PCM, is then pretrained with optimally labelled data in an offline manner, so as to construct effective heuristics to boost a broad range of DCOP algorithms where evaluating the quality of a partial assignment is critical, such as local search or backtracking search.

Combinatorial Optimization Graph Attention

RMIX: Learning Risk-Sensitive Policies forCooperative Reinforcement Learning Agents

no code implementations NeurIPS 2021 Wei Qiu, Xinrun Wang, Runsheng Yu, Rundong Wang, Xu He, Bo An, Svetlana Obraztsova, Zinovi Rabinovich

Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE).

Multi-agent Reinforcement Learning reinforcement-learning +2

Online Ad Hoc Teamwork under Partial Observability

no code implementations ICLR 2022 Pengjie Gu, Mengchen Zhao, Jianye Hao, Bo An

Autonomous agents often need to work together as a team to accomplish complex cooperative tasks.

Learning Pseudometric-based Action Representations for Offline Reinforcement Learning

no code implementations29 Sep 2021 Pengjie Gu, Mengchen Zhao, Chen Chen, Dong Li, Jianye Hao, Bo An

Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments.

Offline RL Recommendation Systems +2

Open-sampling: Re-balancing Long-tailed Datasets with Out-of-Distribution Data

no code implementations29 Sep 2021 Hongxin Wei, Lue Tao, Renchunzi Xie, Lei Feng, Bo An

Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.

Reinforcement Learning for Quantitative Trading

no code implementations28 Sep 2021 Shuo Sun, Rundong Wang, Bo An

RL's impact is pervasive, recently demonstrating its ability to conquer many challenging QT tasks.

Decision Making reinforcement-learning

Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning

no code implementations9 Aug 2021 Wanqi Xue, Wei Qiu, Bo An, Zinovi Rabinovich, Svetlana Obraztsova, Chai Kiat Yeo

Empirical results demonstrate that many state-of-the-art MACRL methods are vulnerable to message attacks, and our method can significantly improve their robustness.

Multi-agent Reinforcement Learning reinforcement-learning

Multi-Class Classification from Single-Class Data with Confidences

no code implementations16 Jun 2021 Yuzhou Cao, Lei Feng, Senlin Shu, Yitian Xu, Bo An, Gang Niu, Masashi Sugiyama

We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i. e., the class-posterior probabilities for all the classes) are available.

Classification Multi-class Classification

Contingency-Aware Influence Maximization: A Reinforcement Learning Approach

1 code implementation13 Jun 2021 Haipeng Chen, Wei Qiu, Han-Ching Ou, Bo An, Milind Tambe

Empirical results show that our method achieves influence as high as the state-of-the-art methods for contingency-aware IM, while having negligible runtime at test phase.

Combinatorial Optimization reinforcement-learning

On the Robustness of Average Losses for Partial-Label Learning

no code implementations11 Jun 2021 Jiaqi Lv, Lei Feng, Miao Xu, Bo An, Gang Niu, Xin Geng, Masashi Sugiyama

Partial-label (PL) learning is a typical weakly supervised classification problem, where a PL of an instance is a set of candidate labels such that a fixed but unknown candidate is the true label.

Partial Label Learning Weakly Supervised Classification

CFR-MIX: Solving Imperfect Information Extensive-Form Games with Combinatorial Action Space

no code implementations18 May 2021 Shuxin Li, Youzhi Zhang, Xinrun Wang, Wanqi Xue, Bo An

The challenge of solving this type of game is that the team's joint action space grows exponentially with the number of agents, which results in the inefficiency of the existing algorithms, e. g., Counterfactual Regret Minimization (CFR).

L2E: Learning to Exploit Your Opponent

no code implementations18 Feb 2021 Zhe Wu, Kai Li, Enmin Zhao, Hang Xu, Meng Zhang, Haobo Fu, Bo An, Junliang Xing

In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling.

DO-GAN: A Double Oracle Framework for Generative Adversarial Networks

no code implementations CVPR 2022 Aye Phyu Phyu Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, XiaoLi Li

In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles.

Continual Learning

RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents

no code implementations16 Feb 2021 Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich

Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE).

Multi-agent Reinforcement Learning reinforcement-learning +2

Learning from Similarity-Confidence Data

no code implementations13 Feb 2021 Yuzhou Cao, Lei Feng, Yitian Xu, Bo An, Gang Niu, Masashi Sugiyama

Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data.

Safe Coupled Deep Q-Learning for Recommendation Systems

no code implementations8 Jan 2021 Runsheng Yu, Yu Gong, Rundong Wang, Bo An, Qingwen Liu, Wenwu Ou

Firstly, we introduce a novel training scheme with two value functions to maximize the accumulated long-term reward under the safety constraint.

Q-Learning Recommendation Systems

RMIX: Risk-Sensitive Multi-Agent Reinforcement Learning

no code implementations1 Jan 2021 Wei Qiu, Xinrun Wang, Runsheng Yu, Xu He, Rundong Wang, Bo An, Svetlana Obraztsova, Zinovi Rabinovich

Centralized training with decentralized execution (CTDE) has become an important paradigm in multi-agent reinforcement learning (MARL).

Multi-agent Reinforcement Learning reinforcement-learning +2

Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution

no code implementations23 Dec 2020 Rundong Wang, Hongxin Wei, Bo An, Zhouyan Feng, Jun Yao

Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error.

Hierarchical Reinforcement Learning Portfolio Optimization +1

Personalized Adaptive Meta Learning for Cold-start User Preference Prediction

no code implementations22 Dec 2020 Runsheng Yu, Yu Gong, Xu He, Bo An, Yu Zhu, Qingwen Liu, Wenwu Ou

Recently, many existing studies regard the cold-start personalized preference prediction as a few-shot learning problem, where each user is the task and recommended items are the classes, and the gradient-based meta learning method (MAML) is leveraged to address this challenge.

Few-Shot Learning

MetaInfoNet: Learning Task-Guided Information for Sample Reweighting

no code implementations9 Dec 2020 Hongxin Wei, Lei Feng, Rundong Wang, Bo An

Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance.

Meta-Learning

SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning

no code implementations2 Dec 2020 Zhuowei Wang, Jing Jiang, Bo Han, Lei Feng, Bo An, Gang Niu, Guodong Long

We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.

Learning with noisy labels

Pointwise Binary Classification with Pairwise Confidence Comparisons

no code implementations5 Oct 2020 Lei Feng, Senlin Shu, Nan Lu, Bo Han, Miao Xu, Gang Niu, Bo An, Masashi Sugiyama

To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed.

Classification General Classification

Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player Games

no code implementations30 Sep 2020 David Milec, Jakub Černý, Viliam Lisý, Bo An

This paper aims to analyze and propose scalable algorithms for computing effective and robust strategies against a quantal opponent in normal-form and extensive-form games.

Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation

no code implementations21 Aug 2020 Xu He, Bo An, Yanghua Li, Haikai Chen, Qingyu Guo, Xin Li, Zhirong Wang

First, since we concern the reward of a set of recommended items, we model the online recommendation as a contextual combinatorial bandit problem and define the reward of a recommended set.

Provably Consistent Partial-Label Learning

no code implementations NeurIPS 2020 Lei Feng, Jiaqi Lv, Bo Han, Miao Xu, Gang Niu, Xin Geng, Bo An, Masashi Sugiyama

Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels.

Multi-class Classification Partial Label Learning

Learning Behaviors with Uncertain Human Feedback

1 code implementation7 Jun 2020 Xu He, Haipeng Chen, Bo An

However, previous works rarely consider the uncertainty when humans provide feedback, especially in cases that the optimal actions are not obvious to the trainers.

Learning Expensive Coordination: An Event-Based Deep RL Approach

no code implementations ICLR 2020 Zhenyu Shi*, Runsheng Yu*, Xinrun Wang*, Rundong Wang, Youzhi Zhang, Hanjiang Lai, Bo An

The main difficulties of expensive coordination are that i) the leader has to consider the long-term effect and predict the followers' behaviors when assigning bonuses and ii) the complex interactions between followers make the training process hard to converge, especially when the leader's policy changes with time.

Decision Making Multi-agent Reinforcement Learning

Combating noisy labels by agreement: A joint training method with co-regularization

1 code implementation CVPR 2020 Hongxin Wei, Lei Feng, Xiangyu Chen, Bo An

The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels.

Learning with noisy labels

Learning with Multiple Complementary Labels

no code implementations ICML 2020 Lei Feng, Takuo Kaneko, Bo Han, Gang Niu, Bo An, Masashi Sugiyama

In this paper, we propose a novel problem setting to allow MCLs for each example and two ways for learning with MCLs.

Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning

no code implementations18 Nov 2019 Runsheng Yu, Zhenyu Shi, Xinrun Wang, Rundong Wang, Buhong Liu, Xinwen Hou, Hanjiang Lai, Bo An

Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme, where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently.

reinforcement-learning

EUSP: An Easy-to-Use Semantic Parsing PlatForm

no code implementations IJCNLP 2019 Bo An, Chen Bo, Xianpei Han, Le Sun

Semantic parsing aims to map natural language utterances into structured meaning representations.

Semantic Parsing

Manipulating a Learning Defender and Ways to Counteract

no code implementations NeurIPS 2019 Jiarui Gan, Qingyu Guo, Long Tran-Thanh, Bo An, Michael Wooldridge

We then apply a game-theoretic framework at a higher level to counteract such manipulation, in which the defender commits to a policy that specifies her strategy commitment according to the learned information.

Competitive Bridge Bidding with Deep Neural Networks

no code implementations3 Mar 2019 Jiang Rong, Tao Qin, Bo An

Second, based on the analysis of the impact of other players' unknown cards on one's final rewards, we design two neural networks to deal with imperfect information, the first one inferring the cards of the partner and the second one taking the outputs of the first one as part of its input to select a bid.

Collaboration based Multi-Label Learning

no code implementations8 Feb 2019 Lei Feng, Bo An, Shuo He

It is well-known that exploiting label correlations is crucially important to multi-label learning.

Multi-Label Learning

Partial Label Learning with Self-Guided Retraining

no code implementations8 Feb 2019 Lei Feng, Bo An

We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems.

Partial Label Learning

Sentence Rewriting for Semantic Parsing

no code implementations ACL 2016 Bo Chen, Le Sun, Xianpei Han, Bo An

A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology.

Semantic Parsing Sentence ReWriting

Model-Free Context-Aware Word Composition

no code implementations COLING 2018 Bo An, Xianpei Han, Le Sun

Word composition is a promising technique for representation learning of large linguistic units (e. g., phrases, sentences and documents).

Dimensionality Reduction Learning Word Embeddings +3

Accurate Text-Enhanced Knowledge Graph Representation Learning

no code implementations NAACL 2018 Bo An, Bo Chen, Xianpei Han, Le Sun

Previous representation learning techniques for knowledge graph representation usually represent the same entity or relation in different triples with the same representation, without considering the ambiguity of relations and entities.

General Classification Graph Representation Learning +3

Vehicle Traffic Driven Camera Placement for Better Metropolis Security Surveillance

1 code implementation1 Apr 2017 Yihui He, Xiaobo Ma, Xiapu Luo, Jianfeng Li, Mengchen Zhao, Bo An, Xiaohong Guan

Security surveillance is one of the most important issues in smart cities, especially in an era of terrorism.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.