Search Results for author: Xiangyu Liu

Found 26 papers, 12 papers with code

Do LLM Agents Have Regret? A Case Study in Online Learning and Games

no code implementations25 Mar 2024 Chanwoo Park, Xiangyu Liu, Asuman Ozdaglar, Kaiqing Zhang

To better understand the limits of LLM agents in these interactive environments, we propose to study their interactions in benchmark decision-making settings in online learning and game theory, through the performance metric of \emph{regret}.

Decision Making

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

1 code implementation20 Feb 2024 Xiangyu Liu, ChengHao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang

In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust to adversarial attacks during test time.

Adversarial Attack Reinforcement Learning (RL)

Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment

no code implementations6 Dec 2023 Gokul Puthumanaillam, Xiangyu Liu, Negar Mehr, Melkior Ornik

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments.

Decision Making

Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing

no code implementations16 Aug 2023 Xiangyu Liu, Kaiqing Zhang

Furthermore, we develop a partially observable MARL algorithm that is both statistically and computationally quasi-efficient.

Computational Efficiency Multi-agent Reinforcement Learning

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

no code implementations22 Jul 2023 Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Xiangyu Liu, Tuomas Sandholm, Furong Huang, Stephen Mcaleer

To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially-observable two-player zero-sum game.

Continuous Control reinforcement-learning +1

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

no code implementations27 May 2023 Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang

To address these limitations, we introduce a generalized attack framework that has the flexibility to model to what extent the adversary is able to control the agent, and allows the attacker to regulate the state distribution shift and produce stealthier adversarial policies.

FairRec: Fairness Testing for Deep Recommender Systems

1 code implementation14 Apr 2023 Huizhong Guo, Jinfeng Li, Jingyi Wang, Xiangyu Liu, Dongxia Wang, Zehong Hu, Rong Zhang, Hui Xue

Given the testing report, by adopting a simple re-ranking mitigation strategy on these identified disadvantaged groups, we show that the fairness of DRSs can be significantly improved.

Fairness Recommendation Systems +1

Deep Reinforcement Learning for Localizability-Enhanced Navigation in Dynamic Human Environments

no code implementations22 Mar 2023 Yuan Chen, Quecheng Qiu, Xiangyu Liu, Guangda Chen, Shunyi Yao, Jie Peng, Jianmin Ji, Yanyong Zhang

The planner learns to assign different importance to the geometric features and encourages the robot to navigate through areas that are helpful for laser localization.

Navigate reinforcement-learning

A Survey on Knowledge-Enhanced Pre-trained Language Models

no code implementations27 Dec 2022 Chaoqi Zhen, Yanlei Shang, Xiangyu Liu, Yifei Li, Yong Chen, Dell Zhang

Natural Language Processing (NLP) has been revolutionized by the use of Pre-trained Language Models (PLMs) such as BERT.

RoChBert: Towards Robust BERT Fine-tuning for Chinese

1 code implementation28 Oct 2022 Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Despite of the superb performance on a wide range of tasks, pre-trained language models (e. g., BERT) have been proved vulnerable to adversarial texts.

Data Augmentation Language Modelling

SemAttack: Natural Textual Attacks via Different Semantic Spaces

1 code implementation Findings (NAACL) 2022 Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li

In particular, SemAttack optimizes the generated perturbations constrained on generic semantic spaces, including typo space, knowledge space (e. g., WordNet), contextualized semantic space (e. g., the embedding space of BERT clusterings), or the combination of these spaces.

Adversarial Text

Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

1 code implementation NeurIPS 2021 Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu

With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning.

Instrumental Variable-Driven Domain Generalization with Unobserved Confounders

no code implementations4 Oct 2021 Junkun Yuan, Xu Ma, Ruoxuan Xiong, Mingming Gong, Xiangyu Liu, Fei Wu, Lanfen Lin, Kun Kuang

Meanwhile, the existing of unobserved confounders which affect the input features and labels simultaneously cause spurious correlation and hinder the learning of the invariant relationship contained in the conditional distribution.

Domain Generalization valid

Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

no code implementations9 Jun 2021 Xiangyu Liu, Hangtian Jia, Ying Wen, Yaodong Yang, Yujing Hu, Yingfeng Chen, Changjie Fan, Zhipeng Hu

With this unified diversity measure, we design the corresponding diversity-promoting objective and population effectivity when seeking the best responses in open-ended learning.

Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising

no code implementations7 Jun 2021 Xiangyu Liu, Chuan Yu, Zhilin Zhang, Zhenzhe Zheng, Yu Rong, Hongtao Lv, Da Huo, YiQing Wang, Dagui Chen, Jian Xu, Fan Wu, Guihai Chen, Xiaoqiang Zhu

In e-commerce advertising, it is crucial to jointly consider various performance metrics, e. g., user experience, advertiser utility, and platform revenue.

Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation

no code implementations23 Feb 2021 Jinfeng Li, Tianyu Du, Xiangyu Liu, Rong Zhang, Hui Xue, Shouling Ji

Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i. e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.

Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising

no code implementations5 Dec 2020 Zhilin Zhang, Xiangyu Liu, Zhenzhe Zheng, Chenrui Zhang, Miao Xu, Junwei Pan, Chuan Yu, Fan Wu, Jian Xu, Kun Gai

In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue.

PSGAN: A Generative Adversarial Network for Remote Sensing Image Pan-Sharpening

1 code implementation9 May 2018 Qingjie Liu, Huanyu Zhou, Qizhi Xu, Xiangyu Liu, Yunhong Wang

This paper addresses the problem of remote sensing image pan-sharpening from the perspective of generative adversarial learning.

Generative Adversarial Network

Invisible Mask: Practical Attacks on Face Recognition with Infrared

no code implementations13 Mar 2018 Zhe Zhou, Di Tang, Xiao-Feng Wang, Weili Han, Xiangyu Liu, Kehuan Zhang

We propose a kind of brand new attack against face recognition systems, which is realized by illuminating the subject using infrared according to the adversarial examples worked out by our algorithm, thus face recognition systems can be bypassed or misled while simultaneously the infrared perturbations cannot be observed by raw eyes.

Cryptography and Security

Understanding Android Obfuscation Techniques: A Large-Scale Investigation in the Wild

no code implementations5 Jan 2018 Shuaike Dong, Menghao Li, Wenrui Diao, Xiangyu Liu, Jian Liu, Zhou Li, Fenghao Xu, Kai Chen, Xiao-Feng Wang, Kehuan Zhang

In this paper, we seek to better understand Android obfuscation and depict a holistic view of the usage of obfuscation through a large-scale investigation in the wild.

Cryptography and Security

Remote Sensing Image Fusion Based on Two-stream Fusion Network

1 code implementation7 Nov 2017 Xiangyu Liu, Qingjie Liu, Yunhong Wang

Unlike previous CNN based methods that consider pan-sharpening as a super resolution problem and perform pan-sharpening in pixel level, the proposed TFNet aims to fuse PAN and MS images in feature level and reconstruct the pan-sharpened image from the fused features.

Image Reconstruction Super-Resolution +1

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