Search Results for author: Yufeng Zhang

Found 29 papers, 5 papers with code

Can Large Language Models Play Games? A Case Study of A Self-Play Approach

no code implementations8 Mar 2024 Hongyi Guo, Zhihan Liu, Yufeng Zhang, Zhaoran Wang

Large Language Models (LLMs) harness extensive data from the Internet, storing a broad spectrum of prior knowledge.

Decision Making Hallucination

Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge

no code implementations12 Sep 2023 Yufeng Zhang, Meng-xiang Wang, Jianxing Yu

We first retrieve all answer-related clues from multiple knowledge sources on facts and opinions.

An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models

no code implementations30 Dec 2022 Yufeng Zhang, Boyi Liu, Qi Cai, Lingxiao Wang, Zhaoran Wang

In particular, such a representation instantiates the posterior distribution of the latent variable given input tokens, which plays a central role in predicting output labels and solving downstream tasks.

Image-Text Retrieval with Binary and Continuous Label Supervision

no code implementations20 Oct 2022 Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, Ying Jin, Yufeng Zhang

Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent relevance degrees between images and texts described by continuous labels such as image captions.

Image Captioning Retrieval +2

Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction

1 code implementation3 Sep 2022 Yufeng Zhang, Weiqing Wang, Hongzhi Yin, Pengpeng Zhao, Wei Chen, Lei Zhao

A more challenging scenario is that emerging KGs consist of only unseen entities, called as disconnected emerging KGs (DEKGs).

Contrastive Learning Inductive Link Prediction +2

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

no code implementations NeurIPS 2021 Yufeng Zhang, Siyu Chen, Zhuoran Yang, Michael I. Jordan, Zhaoran Wang

Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates.

Representation Learning

Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration

no code implementations NeurIPS 2021 Runzhe Wu, Yufeng Zhang, Zhuoran Yang, Zhaoran Wang

In constrained multi-objective RL, the goal is to learn a policy that achieves the best performance specified by a multi-objective preference function under a constraint.

Multi-Objective Reinforcement Learning reinforcement-learning

Relation-aware Heterogeneous Graph for User Profiling

1 code implementation14 Oct 2021 Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang

User profiling has long been an important problem that investigates user interests in many real applications.

Node Classification Relation

Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation

no code implementations19 Aug 2021 Zhihan Liu, Yufeng Zhang, Zuyue Fu, Zhuoran Yang, Zhaoran Wang

In generative adversarial imitation learning (GAIL), the agent aims to learn a policy from an expert demonstration so that its performance cannot be discriminated from the expert policy on a certain predefined reward set.

Imitation Learning

Deep Active Learning for Text Classification with Diverse Interpretations

no code implementations15 Aug 2021 Qiang Liu, Yanqiao Zhu, Zhaocheng Liu, Yufeng Zhang, Shu Wu

To train high-performing models with the minimal annotation cost, active learning is proposed to select and label the most informative samples, yet it is still challenging to measure informativeness of samples used in DNNs.

Active Learning Informativeness +3

Prevalent Behavior of Smooth Strongly Monotone Discrete-Time Dynamical Systems

no code implementations8 Mar 2021 Yi Wang, Jinxiang Yao, Yufeng Zhang

For C1-smooth strongly monotone discrete-time dynamical systems, it is shown that ``convergence to linearly stable cycles" is a prevalent asymptotic behavior in the measuretheoretic sense.

Dynamical Systems

A Graph-based Relevance Matching Model for Ad-hoc Retrieval

1 code implementation28 Jan 2021 Yufeng Zhang, Jinghao Zhang, Zeyu Cui, Shu Wu, Liang Wang

To retrieve more relevant, appropriate and useful documents given a query, finding clues about that query through the text is crucial.

Retrieval

No Feature Is An Island: Adaptive Collaborations Between Features Improve Adversarial Robustness

no code implementations1 Jan 2021 Yufeng Zhang, Yunan Zhang, ChengXiang Zhai

To classify images, neural networks extract features from raw inputs and then sum them up with fixed weights via the fully connected layer.

Adversarial Robustness counterfactual

Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization

no code implementations21 Dec 2020 Zhuoran Yang, Yufeng Zhang, Yongxin Chen, Zhaoran Wang

Specifically, we prove that moving along the geodesic in the direction of functional gradient with respect to the second-order Wasserstein distance is equivalent to applying a pushforward mapping to a probability distribution, which can be approximated accurately by pushing a set of particles.

Generative Adversarial Network Variational Inference

Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory

no code implementations NeurIPS 2020 Yufeng Zhang, Qi Cai, Zhuoran Yang, Yongxin Chen, Zhaoran Wang

Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks.

Q-Learning reinforcement-learning +1

Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory

no code implementations8 Jun 2020 Yufeng Zhang, Qi Cai, Zhuoran Yang, Yongxin Chen, Zhaoran Wang

We aim to answer the following questions: When the function approximator is a neural network, how does the associated feature representation evolve?

Q-Learning

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

1 code implementation ACL 2020 Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, Liang Wang

We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document.

Document Embedding General Classification +2

Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate

no code implementations8 Mar 2020 Yufeng Zhang, Qi Cai, Zhuoran Yang, Zhaoran Wang

Generative adversarial imitation learning (GAIL) demonstrates tremendous success in practice, especially when combined with neural networks.

Imitation Learning reinforcement-learning +1

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