Search Results for author: Han Zhao

Found 58 papers, 20 papers with code

EventKE: Event-Enhanced Knowledge Graph Embedding

no code implementations Findings (EMNLP) 2021 Zixuan Zhang, Hongwei Wang, Han Zhao, Hanghang Tong, Heng Ji

Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities.

Knowledge Graph Embedding Knowledge Graphs

Algorithms and Theory for Supervised Gradual Domain Adaptation

no code implementations25 Apr 2022 Jing Dong, Shiji Zhou, Baoxiang Wang, Han Zhao

We thus study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory, and we aim to learn a classifier on a target data distribution of interest.

Domain Adaptation

Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

1 code implementation18 Apr 2022 Haoxiang Wang, Bo Li, Han Zhao

Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.

Unsupervised Domain Adaptation

Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning

no code implementations9 Mar 2022 Zhenhailong Wang, Hang Yu, Manling Li, Han Zhao, Heng Ji

Due to the uniform task sampling procedure, MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.

Meta-Learning Transfer Learning

Conditional Contrastive Learning with Kernel

1 code implementation ICLR 2022 Yao-Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis-Philippe Morency, Ruslan Salakhutdinov

Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables.

Contrastive Learning

Provable Domain Generalization via Invariant-Feature Subspace Recovery

1 code implementation30 Jan 2022 Haoxiang Wang, Haozhe Si, Bo Li, Han Zhao

Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).

Domain Generalization

Towards Return Parity in Markov Decision Processes

1 code implementation19 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.

Fairness Recommendation Systems

A Nearly Optimal Chattering Reduction Method of Sliding Mode Control With an Application to a Two-wheeled Mobile Robot

no code implementations25 Oct 2021 Lei Guo, Han Zhao, Yuan Song

First, the deficiency of chattering in traditional SMC and the quasi-SMC method are analyzed in this paper.

FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

1 code implementation16 Oct 2021 Yan Shen, Jian Du, Han Zhao, Benyu Zhang, Zhanghexuan Ji, Mingchen Gao

Federated adversary domain adaptation is a unique distributed minimax training task due to the prevalence of label imbalance among clients, with each client only seeing a subset of the classes of labels required to train a global model.

Domain Adaptation

Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer

no code implementations ICLR 2022 Ruicheng Xian, Heng Ji, Han Zhao

Recent advances in neural modeling have produced deep multilingual language models capable of extracting cross-lingual knowledge from unparallel texts, as evidenced by their decent zero-shot transfer performance.

Cross-Lingual Transfer Domain Adaptation

Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach

no code implementations29 Sep 2021 Xiaoyang Wang, Han Zhao, Klara Nahrstedt, Oluwasanmi O Koyejo

To this end, we propose a strategy to mitigate the effect of spurious features based on our observation that the global model in the federated learning step has a low accuracy disparity due to statistical heterogeneity.

Personalized Federated Learning

Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation

1 code implementation16 Jun 2021 Haoxiang Wang, Han Zhao, Bo Li

Despite the subtle difference between MTL and meta-learning in the problem formulation, both learning paradigms share the same insight that the shared structure between existing training tasks could lead to better generalization and adaptation.

Few-Shot Image Classification Meta-Learning +1

Costs and Benefits of Fair Regression

no code implementations16 Jun 2021 Han Zhao

In this paper, we characterize the inherent tradeoff between statistical parity and accuracy in the regression setting by providing a lower bound on the error of any fair regressor.

Fairness Representation Learning

Invariant Information Bottleneck for Domain Generalization

no code implementations11 Jun 2021 Bo Li, Yifei Shen, Yezhen Wang, Wenzhen Zhu, Colorado J. Reed, Jun Zhang, Dongsheng Li, Kurt Keutzer, Han Zhao

IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.

Domain Generalization

Online Continual Adaptation with Active Self-Training

no code implementations11 Jun 2021 Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang, Zhi Wang, Wenwu Zhu

Our theoretical results show that OSAMD can fast adapt to changing environments with active queries.

online learning

Quantifying and Improving Transferability in Domain Generalization

2 code implementations NeurIPS 2021 Guojun Zhang, Han Zhao, YaoLiang Yu, Pascal Poupart

We then prove that our transferability can be estimated with enough samples and give a new upper bound for the target error based on our transferability.

Domain Generalization Out-of-Distribution Generalization

Online Adaptive Optimal Control Algorithm Based on Synchronous Integral Reinforcement Learning With Explorations

no code implementations19 May 2021 Lei Guo, Han Zhao

In this paper, we present a novel algorithm named synchronous integral Q-learning, which is based on synchronous policy iteration, to solve the continuous-time infinite horizon optimal control problems of input-affine system dynamics.

Q-Learning reinforcement-learning

Adaptive Fractional-Order Sliding Mode Controller with Neural Network Compensator for an Ultrasonic Motor

no code implementations23 Mar 2021 Xiaolong Chen, Wenyu Liang, Han Zhao, Abdullah Al Mamun

Ultrasonic motors (USMs) are commonly used in aerospace, robotics, and medical devices, where fast and precise motion is needed.

Self-supervised Representation Learning with Relative Predictive Coding

1 code implementation ICLR 2021 Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Han Zhao, Louis-Philippe Morency, Ruslan Salakhutdinov

This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance.

Representation Learning Self-Supervised Learning

Understanding and Mitigating Accuracy Disparity in Regression

1 code implementation24 Feb 2021 Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon, Han Zhao

With the widespread deployment of large-scale prediction systems in high-stakes domains, e. g., face recognition, criminal justice, etc., disparity in prediction accuracy between different demographic subgroups has called for fundamental understanding on the source of such disparity and algorithmic intervention to mitigate it.

Face Recognition

Acoustic Structure Inverse Design and Optimization Using Deep Learning

no code implementations29 Jan 2021 Xuecong Sun, Han Jia, Yuzhen Yang, Han Zhao, Yafeng Bi, Zhaoyong Sun, Jun Yang

From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves.

Speech Enhancement

Fundamental Limits and Tradeoffs in Invariant Representation Learning

no code implementations19 Dec 2020 Han Zhao, Chen Dan, Bryon Aragam, Tommi S. Jaakkola, Geoffrey J. Gordon, Pradeep Ravikumar

A wide range of machine learning applications such as privacy-preserving learning, algorithmic fairness, and domain adaptation/generalization among others, involve learning \emph{invariant representations} of the data that aim to achieve two competing goals: (a) maximize information or accuracy with respect to a target response, and (b) maximize invariance or independence with respect to a set of protected features (e. g.\ for fairness, privacy, etc).

Domain Adaptation Fairness +2

Model-based Policy Optimization with Unsupervised Model Adaptation

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.

Continuous Control Model-based Reinforcement Learning +1

Information Obfuscation of Graph Neural Networks

1 code implementation28 Sep 2020 Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka, Ruslan Salakhutdinov

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes.

Adversarial Defense Graph Representation Learning +2

DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning

no code implementations15 Sep 2020 Huajie Shao, Haohong Lin, Qinmin Yang, Shuochao Yao, Han Zhao, Tarek Abdelzaher

Existing methods, such as $\beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement.


A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

1 code implementation1 Sep 2020 Sicheng Zhao, Xiangyu Yue, Shanghang Zhang, Bo Li, Han Zhao, Bichen Wu, Ravi Krishna, Joseph E. Gonzalez, Alberto L. Sangiovanni-Vincentelli, Sanjit A. Seshia, Kurt Keutzer

To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.

Unsupervised Domain Adaptation

On Learning Language-Invariant Representations for Universal Machine Translation

no code implementations ICML 2020 Han Zhao, Junjie Hu, Andrej Risteski

The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages.

Machine Translation Translation

Neural Methods for Point-wise Dependency Estimation

1 code implementation NeurIPS 2020 Yao-Hung Hubert Tsai, Han Zhao, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov

Since its inception, the neural estimation of mutual information (MI) has demonstrated the empirical success of modeling expected dependency between high-dimensional random variables.

Cross-Modal Retrieval Representation Learning

Continual Learning with Adaptive Weights (CLAW)

no code implementations ICLR 2020 Tameem Adel, Han Zhao, Richard E. Turner

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner.

Continual Learning Transfer Learning +1

Conditional Learning of Fair Representations

no code implementations ICLR 2020 Han Zhao, Amanda Coston, Tameem Adel, Geoffrey J. Gordon

We propose a novel algorithm for learning fair representations that can simultaneously mitigate two notions of disparity among different demographic subgroups in the classification setting.

Classification Fairness +1

Adversarial Privacy Preservation under Attribute Inference Attack

no code implementations25 Sep 2019 Han Zhao, Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon

With the prevalence of machine learning services, crowdsourced data containing sensitive information poses substantial privacy challenges.

Inference Attack Representation Learning

Learning Neural Networks with Adaptive Regularization

1 code implementation NeurIPS 2019 Han Zhao, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Geoffrey J. Gordon

Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis.

Inherent Tradeoffs in Learning Fair Representations

no code implementations NeurIPS 2019 Han Zhao, Geoffrey J. Gordon

On the upside, we prove that if the group-wise Bayes optimal classifiers are close, then learning fair representations leads to an alternative notion of fairness, known as the accuracy parity, which states that the error rates are close between groups.


On Learning Invariant Representation for Domain Adaptation

2 code implementations27 Jan 2019 Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoffrey J. Gordon

Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target.

Representation Learning Unsupervised Domain Adaptation

Adversarial Multiple Source Domain Adaptation

no code implementations NeurIPS 2018 Han Zhao, Shanghang Zhang, Guanhang Wu, José M. F. Moura, Joao P. Costeira, Geoffrey J. Gordon

In this paper we propose new generalization bounds and algorithms under both classification and regression settings for unsupervised multiple source domain adaptation.

Classification Domain Adaptation +4

On Strategyproof Conference Peer Review

1 code implementation16 Jun 2018 Yichong Xu, Han Zhao, Xiaofei Shi, Jeremy Zhang, Nihar B. Shah

We then empirically show that the requisite property on the authorship graph is indeed satisfied in the submission data from the ICLR conference, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review.

Convolutional-Recurrent Neural Networks for Speech Enhancement

no code implementations2 May 2018 Han Zhao, Shuayb Zarar, Ivan Tashev, Chin-Hui Lee

By incorporating prior knowledge of speech signals into the design of model structures, we build a model that is more data-efficient and achieves better generalization on both seen and unseen noise.

Speech Enhancement

Multiple Source Domain Adaptation with Adversarial Learning

no code implementations ICLR 2018 Han Zhao, Shanghang Zhang, Guanhang Wu, Jo\~{a}o P. Costeira, Jos\'{e} M. F. Moura, Geoffrey J. Gordon

We propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.

Domain Adaptation Sentiment Analysis

Discovering Order in Unordered Datasets: Generative Markov Networks

no code implementations ICLR 2018 Yao-Hung Hubert Tsai, Han Zhao, Nebojsa Jojic, Ruslan Salakhutdinov

The assumption that data samples are independently identically distributed is the backbone of many learning algorithms.

Learning Markov Chain in Unordered Dataset

no code implementations ICLR 2018 Yao-Hung Hubert Tsai, Han Zhao, Ruslan Salakhutdinov, Nebojsa Jojic

In this technical report, we introduce OrderNet that can be used to extract the order of data instances in an unsupervised way.

Frank-Wolfe Optimization for Symmetric-NMF under Simplicial Constraint

no code implementations20 Jun 2017 Han Zhao, Geoff Gordon

Symmetric nonnegative matrix factorization has found abundant applications in various domains by providing a symmetric low-rank decomposition of nonnegative matrices.

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

3 code implementations26 May 2017 Han Zhao, Shanghang Zhang, Guanhang Wu, João P. Costeira, José M. F. Moura, Geoffrey J. Gordon

As a step toward bridging the gap, we propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances.

Domain Adaptation Sentiment Analysis

Principled Hybrids of Generative and Discriminative Domain Adaptation

no code implementations ICLR 2018 Han Zhao, Zhenyao Zhu, Junjie Hu, Adam Coates, Geoff Gordon

This provides us a very general way to interpolate between generative and discriminative extremes through different choices of priors.

Domain Adaptation

Linear Time Computation of Moments in Sum-Product Networks

no code implementations NeurIPS 2017 Han Zhao, Geoff Gordon

We propose a dynamic programming method to further reduce the computation of the moments of all the edges in the graph from quadratic to linear.

Efficient Multitask Feature and Relationship Learning

no code implementations14 Feb 2017 Han Zhao, Otilia Stretcu, Alex Smola, Geoff Gordon

In this paper, we consider a formulation of multitask learning that learns the relationships both between tasks and between features, represented through a task covariance and a feature covariance matrix, respectively.

Self-Adaptive Hierarchical Sentence Model

1 code implementation20 Apr 2015 Han Zhao, Zhengdong Lu, Pascal Poupart

The ability to accurately model a sentence at varying stages (e. g., word-phrase-sentence) plays a central role in natural language processing.

General Classification Subjectivity Analysis

On the Relationship between Sum-Product Networks and Bayesian Networks

no code implementations6 Jan 2015 Han Zhao, Mazen Melibari, Pascal Poupart

We conclude the paper with some discussion of the implications of the proof and establish a connection between the depth of an SPN and a lower bound of the tree-width of its corresponding BN.

A Sober Look at Spectral Learning

no code implementations18 Jun 2014 Han Zhao, Pascal Poupart

In contrast, maximum likelihood estimates may get trapped in local optima due to the non-convex nature of the likelihood function of latent variable models.

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