Search Results for author: Mingyuan Zhou

Found 144 papers, 81 papers with code

Friendly Topic Assistant for Transformer Based Abstractive Summarization

no code implementations EMNLP 2020 Zhengjue Wang, Zhibin Duan, Hao Zhang, Chaojie Wang, Long Tian, Bo Chen, Mingyuan Zhou

Abstractive document summarization is a comprehensive task including document understanding and summary generation, in which area Transformer-based models have achieved the state-of-the-art performance.

Abstractive Text Summarization Document Summarization +2

Advancing Graph Generation through Beta Diffusion

1 code implementation13 Jun 2024 Yilin He, Xinyang Liu, Bo Chen, Mingyuan Zhou

Diffusion models have demonstrated effectiveness in generating natural images and have been extended to generate diverse data types, including graphs.

Graph Generation

Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

1 code implementation10 Jun 2024 Yi Gu, Zhendong Wang, Yueqin Yin, Yujia Xie, Mingyuan Zhou

Aligning large language models with human preferences has emerged as a critical focus in language modeling research.

Language Modelling

Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation

2 code implementations3 Jun 2024 Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang

Specifically, its data-free distillation of Stable Diffusion 1. 5 achieves a record low FID of 8. 15 on the COCO-2014 validation set, with a CLIP score of 0. 304 at an LSG scale of 1. 5, and a FID of 9. 56 with a CLIP score of 0. 313 at an LSG scale of 2.

Text-to-Image Generation

Diffusion Boosted Trees

no code implementations3 Jun 2024 Xizewen Han, Mingyuan Zhou

Combining the merits of both denoising diffusion probabilistic models and gradient boosting, the diffusion boosting paradigm is introduced for tackling supervised learning problems.

Denoising Fraud Detection

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment

1 code implementation31 May 2024 Yueqin Yin, Zhendong Wang, Yujia Xie, Weizhu Chen, Mingyuan Zhou

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability.

Language Modelling

Diffusion Policies creating a Trust Region for Offline Reinforcement Learning

1 code implementation30 May 2024 Tianyu Chen, Zhendong Wang, Mingyuan Zhou

Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of offline RL.

D4RL Denoising +4

Switchable Decision: Dynamic Neural Generation Networks

no code implementations7 May 2024 Shujian Zhang, Korawat Tanwisuth, Chengyue Gong, Pengcheng He, Mingyuan Zhou

Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications.

Question Answering

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation

2 code implementations5 Apr 2024 Mingyuan Zhou, Huangjie Zheng, Zhendong Wang, Mingzhang Yin, Hai Huang

This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation.

Image Generation

Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization

1 code implementation22 Feb 2024 Xuxi Chen, Zhendong Wang, Daouda Sow, Junjie Yang, Tianlong Chen, Yingbin Liang, Mingyuan Zhou, Zhangyang Wang

Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets, with a specific focus on selective retention of samples that incur moderately high losses.

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference

1 code implementation13 Feb 2024 Shentao Yang, Tianqi Chen, Mingyuan Zhou

In this paper, we take on a finer dense reward perspective and derive a tractable alignment objective that emphasizes the initial steps of the T2I reverse chain.

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

1 code implementation12 Feb 2024 Yueqin Yin, Zhendong Wang, Yi Gu, Hai Huang, Weizhu Chen, Mingyuan Zhou

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge.

Improving Unsupervised Hierarchical Representation with Reinforcement Learning

1 code implementation CVPR 2024 Ruyi An, Yewen Li, Xu He, Pengjie Gu, Mengchen Zhao, Dong Li, Jianye Hao, Chaojie Wang, Bo An, Mingyuan Zhou

To address this issue we first analyze the shortcomings of existing methods for mitigating the "posterior collapse" from an information theory perspective then highlight the necessity of regularization for explicitly propagating data information to higher-level latent variables while maintaining the dependency between different levels.

reinforcement-learning Reinforcement Learning (RL)

Improving In-Context Learning in Diffusion Models with Visual Context-Modulated Prompts

no code implementations3 Dec 2023 Tianqi Chen, Yongfei Liu, Zhendong Wang, Jianbo Yuan, Quanzeng You, Hongxia Yang, Mingyuan Zhou

In light of the remarkable success of in-context learning in large language models, its potential extension to the vision domain, particularly with visual foundation models like Stable Diffusion, has sparked considerable interest.

In-Context Learning

OmniMotionGPT: Animal Motion Generation with Limited Data

no code implementations CVPR 2024 Zhangsihao Yang, Mingyuan Zhou, Mengyi Shan, Bingbing Wen, Ziwei Xuan, Mitch Hill, Junjie Bai, Guo-Jun Qi, Yalin Wang

Our paper aims to generate diverse and realistic animal motion sequences from textual descriptions, without a large-scale animal text-motion dataset.

Diversity Motion Synthesis

Beta Diffusion

1 code implementation NeurIPS 2023 Mingyuan Zhou, Tianqi Chen, Zhendong Wang, Huangjie Zheng

We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges.

Denoising

PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification

1 code implementation ICCV 2023 Miaoge Li, Dongsheng Wang, Xinyang Liu, Zequn Zeng, Ruiying Lu, Bo Chen, Mingyuan Zhou

We find that by formulating the multi-label classification as a CT problem, we can exploit the interactions between the image and label efficiently by minimizing the bidirectional CT cost.

Multi-Label Classification Multi-Label Image Classification

Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling

1 code implementation28 May 2023 Tianqi Chen, Mingyuan Zhou

However, it is found in this paper to have limited ability in modeling some other types of data, such as count and non-negative continuous data, that are often highly sparse, skewed, heavy-tailed, and/or overdispersed.

AutoML-GPT: Automatic Machine Learning with GPT

no code implementations4 May 2023 Shujian Zhang, Chengyue Gong, Lemeng Wu, Xingchao Liu, Mingyuan Zhou

Ultimately, with this prompt paragraph, AutoML-GPT will automatically conduct the experiments from data processing to model architecture, hyperparameter tuning, and predicted training log.

AutoML

Class-Balancing Diffusion Models

1 code implementation CVPR 2023 Yiming Qin, Huangjie Zheng, Jiangchao Yao, Mingyuan Zhou, Ya zhang

To tackle this problem, we set from the hypothesis that the data distribution is not class-balanced, and propose Class-Balancing Diffusion Models (CBDM) that are trained with a distribution adjustment regularizer as a solution.

Diversity

POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models

1 code implementation29 Apr 2023 Korawat Tanwisuth, Shujian Zhang, Huangjie Zheng, Pengcheng He, Mingyuan Zhou

Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years.

Image Classification Natural Language Inference +1

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models

1 code implementation NeurIPS 2023 Zhendong Wang, Yifan Jiang, Huangjie Zheng, Peihao Wang, Pengcheng He, Zhangyang Wang, Weizhu Chen, Mingyuan Zhou

Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e. g.$, as few as 5, 000 images to train from scratch.

Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond

1 code implementation11 Apr 2023 Mohammadreza Armandpour, Ali Sadeghian, Huangjie Zheng, Amir Sadeghian, Mingyuan Zhou

Although text-to-image diffusion models have made significant strides in generating images from text, they are sometimes more inclined to generate images like the data on which the model was trained rather than the provided text.

Text to 3D

Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models

no code implementations16 Mar 2023 Xinyang Liu, Dongsheng Wang, Bowei Fang, Miaoge Li, Zhibin Duan, Yishi Xu, Bo Chen, Mingyuan Zhou

For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts.

Prompt Engineering Transfer Learning

A Prototype-Oriented Clustering for Domain Shift with Source Privacy

no code implementations8 Feb 2023 Korawat Tanwisuth, Shujian Zhang, Pengcheng He, Mingyuan Zhou

Finally, it refines the target model on the target domain data without guidance from the source model.

Clustering

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

1 code implementation16 Oct 2022 Yishi Xu, Dongsheng Wang, Bo Chen, Ruiying Lu, Zhibin Duan, Mingyuan Zhou

With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics.

Graph structure learning Topic Models

A Unified Framework for Alternating Offline Model Training and Policy Learning

1 code implementation12 Oct 2022 Shentao Yang, Shujian Zhang, Yihao Feng, Mingyuan Zhou

In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the environment.

Continuous Control Model-based Reinforcement Learning +2

Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

no code implementations9 Oct 2022 Dandan Guo, Long Tian, He Zhao, Mingyuan Zhou, Hongyuan Zha

A recent solution to this problem is calibrating the distribution of these few sample classes by transferring statistics from the base classes with sufficient examples, where how to decide the transfer weights from base classes to novel classes is the key.

Domain Generalization Few-Shot Learning

Knowledge-Aware Bayesian Deep Topic Model

1 code implementation20 Sep 2022 Dongsheng Wang, Yishi Xu, Miaoge Li, Zhibin Duan, Chaojie Wang, Bo Chen, Mingyuan Zhou

We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling.

Topic Models

Ordinal Graph Gamma Belief Network for Social Recommender Systems

no code implementations12 Sep 2022 Dongsheng Wang, Chaojie Wang, Bo Chen, Mingyuan Zhou

To build recommender systems that not only consider user-item interactions represented as ordinal variables, but also exploit the social network describing the relationships between the users, we develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions.

Recommendation Systems

Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

3 code implementations12 Aug 2022 Zhendong Wang, Jonathan J Hunt, Mingyuan Zhou

In our approach, we learn an action-value function and we add a term maximizing action-values into the training loss of the conditional diffusion model, which results in a loss that seeks optimal actions that are near the behavior policy.

D4RL Offline RL +3

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

no code implementations5 Aug 2022 Dandan Guo, Zhuo Li, Meixi Zheng, He Zhao, Mingyuan Zhou, Hongyuan Zha

Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set.

Bilevel Optimization imbalanced classification

CARD: Classification and Regression Diffusion Models

2 code implementations15 Jun 2022 Xizewen Han, Huangjie Zheng, Mingyuan Zhou

In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model and a pre-trained conditional mean estimator, to accurately predict the distribution of $\boldsymbol y$ given $\boldsymbol x$.

Classification Denoising +1

Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning

1 code implementation14 Jun 2022 Shentao Yang, Yihao Feng, Shujian Zhang, Mingyuan Zhou

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process.

Continuous Control Offline RL +2

Probabilistic Conformal Prediction Using Conditional Random Samples

1 code implementation14 Jun 2022 Zhendong Wang, Ruijiang Gao, Mingzhang Yin, Mingyuan Zhou, David M. Blei

This paper proposes probabilistic conformal prediction (PCP), a predictive inference algorithm that estimates a target variable by a discontinuous predictive set.

Conformal Prediction Prediction Intervals

Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

2 code implementations ICLR 2022 Dongsheng Wang, Dandan Guo, He Zhao, Huangjie Zheng, Korawat Tanwisuth, Bo Chen, Mingyuan Zhou

This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space.

Word Embeddings

Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

1 code implementation19 Feb 2022 Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou

Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain.

Text-to-Image Generation

A Behavior Regularized Implicit Policy for Offline Reinforcement Learning

no code implementations19 Feb 2022 Shentao Yang, Zhendong Wang, Huangjie Zheng, Yihao Feng, Mingyuan Zhou

For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy.

D4RL reinforcement-learning +1

Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs

2 code implementations14 Feb 2022 Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou

In this paper, to exploit both global and local dependencies without self-attention, we present Mix-Shift-MLP (MS-MLP) which makes the size of the local receptive field used for mixing increase with respect to the amount of spatial shifting.

A Variational Edge Partition Model for Supervised Graph Representation Learning

1 code implementation7 Feb 2022 Yilin He, Chaojie Wang, Hao Zhang, Bo Chen, Mingyuan Zhou

This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities, each of which contributes to the edges via a logical OR mechanism.

Classification Graph Representation Learning +1

Bayesian Graph Contrastive Learning

no code implementations15 Dec 2021 Arman Hasanzadeh, Mohammadreza Armandpour, Ehsan Hajiramezanali, Mingyuan Zhou, Nick Duffield, Krishna Narayanan

By learning distributional representations, we provide uncertainty estimates in downstream graph analytics tasks and increase the expressive power of the predictive model.

Contrastive Learning Self-Supervised Learning +1

Convex Polytope Trees and its Application to VAE

no code implementations NeurIPS 2021 Mohammadreza Armandpour, Ali Sadeghian, Mingyuan Zhou

The splitting function at each node of CPT is based on the logical disjunction of a community of differently weighted probabilistic linear decision-makers, which also geometrically corresponds to a convex polytope in the covariate space.

TopicNet: Semantic Graph-Guided Topic Discovery

1 code implementation NeurIPS 2021 Zhibin Duan, Yishi Xu, Bo Chen, Dongsheng Wang, Chaojie Wang, Mingyuan Zhou

Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy.

Inductive Bias Topic Models +1

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

1 code implementation NeurIPS 2021 Alek Dimitriev, Mingyuan Zhou

Accurately backpropagating the gradient through categorical variables is a challenging task that arises in various domains, such as training discrete latent variable models.

Alignment Attention by Matching Key and Query Distributions

1 code implementation NeurIPS 2021 Shujian Zhang, Xinjie Fan, Huangjie Zheng, Korawat Tanwisuth, Mingyuan Zhou

The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains.

Graph Attention Question Answering +1

A Prototype-Oriented Framework for Unsupervised Domain Adaptation

1 code implementation NeurIPS 2021 Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng, Shujian Zhang, Hao Zhang, Bo Chen, Mingyuan Zhou

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.

Unsupervised Domain Adaptation

Learning Prototype-oriented Set Representations for Meta-Learning

no code implementations ICLR 2022 Dandan Guo, Long Tian, Minghe Zhang, Mingyuan Zhou, Hongyuan Zha

Since our plug-and-play framework can be applied to many meta-learning problems, we further instantiate it to the cases of few-shot classification and implicit meta generative modeling.

Meta-Learning

Crossformer: Transformer with Alternated Cross-Layer Guidance

no code implementations29 Sep 2021 Shujian Zhang, Zhibin Duan, Huangjie Zheng, Pengcheng He, Bo Chen, Weizhu Chen, Mingyuan Zhou

Crossformer with states sharing not only provides the desired cross-layer guidance and regularization but also reduces the memory requirement.

Inductive Bias Machine Translation +3

State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning

no code implementations29 Sep 2021 Shentao Yang, Zhendong Wang, Huangjie Zheng, Mingyuan Zhou

For training more effective agents, we propose a framework that supports learning a flexible and well-regularized policy, which consists of a fully implicit policy and a regularization through the state-action visitation frequency induced by the current policy and that induced by the data-collecting behavior policy.

D4RL reinforcement-learning +1

Edge Partition Modulated Graph Convolutional Networks

no code implementations29 Sep 2021 Yilin He, Chaojie Wang, Hao Zhang, Bo Chen, Mingyuan Zhou

In this paper, we introduce a relational graph generative process to model how the observed edges are generated by aggregating the node interactions over multiple overlapping node communities, each of which represents a particular type of relation that contributes to the edges via a logical OR mechanism.

Relation Variational Inference

EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

1 code implementation ACL 2021 Zhibin Duan, Hao Zhang, Chaojie Wang, Zhengjue Wang, Bo Chen, Mingyuan Zhou

As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features.

Clustering Diversity +1

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

1 code implementation30 Jun 2021 Zhibin Duan, Dongsheng Wang, Bo Chen, Chaojie Wang, Wenchao Chen, Yewen Li, Jie Ren, Mingyuan Zhou

However, they often assume in the prior that the topics at each layer are independently drawn from the Dirichlet distribution, ignoring the dependencies between the topics both at the same layer and across different layers.

Topic Models Variational Inference

Probabilistic Margins for Instance Reweighting in Adversarial Training

1 code implementation NeurIPS 2021 Qizhou Wang, Feng Liu, Bo Han, Tongliang Liu, Chen Gong, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights.

Adversarial Robustness

Bayesian Attention Belief Networks

no code implementations9 Jun 2021 Shujian Zhang, Xinjie Fan, Bo Chen, Mingyuan Zhou

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks.

Decoder Machine Translation +3

ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

1 code implementation28 May 2021 Alek Dimitriev, Mingyuan Zhou

ARMS uses a copula to generate any number of mutually antithetic samples.

Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning

1 code implementation10 May 2021 Dandan Guo, Ruiying Lu, Bo Chen, Zequn Zeng, Mingyuan Zhou

Inspired by recent successes in integrating semantic topics into this task, this paper develops a plug-and-play hierarchical-topic-guided image paragraph generation framework, which couples a visual extractor with a deep topic model to guide the learning of a language model.

Image Paragraph Captioning Language Modelling +1

Contrastive Attraction and Contrastive Repulsion for Representation Learning

1 code implementation8 May 2021 Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang, Chunyuan Li, Ya zhang, Hao Zhang, Ivor Tsang, Jingren Zhou, Mingyuan Zhou

We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.

Contrastive Learning Representation Learning

Partition-Guided GANs

1 code implementation CVPR 2021 Mohammadreza Armandpour, Ali Sadeghian, Chunyuan Li, Mingyuan Zhou

We formulate two desired criteria for the space partitioner that aid the training of our mixture of generators: 1) to produce connected partitions and 2) provide a proxy of distance between partitions and data samples, along with a direction for reducing that distance.

Image Generation

Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

1 code implementation ICLR 2022 Haoang Chi, Feng Liu, Bo Han, Wenjing Yang, Long Lan, Tongliang Liu, Gang Niu, Mingyuan Zhou, Masashi Sugiyama

In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes.

Clustering Meta-Learning +1

Polarimetric Helmholtz Stereopsis

no code implementations ICCV 2021 Yuqi Ding, Yu Ji, Mingyuan Zhou, Sing Bing Kang, Jinwei Ye

Helmholtz stereopsis (HS) exploits the reciprocity principle of light propagation (i. e., the Helmholtz reciprocity) for 3D reconstruction of surfaces with arbitrary reflectance.

3D Reconstruction

Topic-aware Contextualized Transformers

no code implementations1 Jan 2021 Ruiying Lu, Bo Chen, Dan dan Guo, Dongsheng Wang, Mingyuan Zhou

Moving beyond conventional Transformers that ignore longer-range word dependencies and contextualize their word representations at the segment level, the proposed method not only captures global semantic coherence of all segments and global word concurrence patterns, but also enriches the representation of each token by adapting it to its local context, which is not limited to the segment it resides in and can be flexibly defined according to the task.

Word Embeddings

Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions

1 code implementation NeurIPS 2021 Huangjie Zheng, Mingyuan Zhou

The forward CT is the expected cost of moving a source data point to a target one, with their joint distribution defined by the product of the source probability density function (PDF) and a source-dependent conditional distribution, which is related to the target PDF via Bayes' theorem.

Generative Adversarial Network

Deep Relational Topic Modeling via Graph Poisson Gamma Belief Network

no code implementations NeurIPS 2020 Chaojie Wang, Hao Zhang, Bo Chen, Dongsheng Wang, Zhengjue Wang, Mingyuan Zhou

To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability.

Topic Models

Bidirectional Convolutional Poisson Gamma Dynamical Systems

1 code implementation NeurIPS 2020 Wenchao Chen, Chaojie Wang, Bo Chen, Yicheng Liu, Hao Zhang, Mingyuan Zhou

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions.

Bayesian Inference Sentence +1

Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference

1 code implementation31 Oct 2020 Ali Lotfi Rezaabad, Rahi Kalantari, Sriram Vishwanath, Mingyuan Zhou, Jonathan Tamir

We show that the existing semi-implicit variational inference objective provably reduces information in the observed graph.

Graph Embedding Link Prediction +2

Convex Polytope Trees

1 code implementation21 Oct 2020 Mohammadreza Armandpour, Mingyuan Zhou

The splitting function at each node of CPT is based on the logical disjunction of a community of differently weighted probabilistic linear decision-makers, which also geometrically corresponds to a convex polytope in the covariate space.

Bayesian Attention Modules

1 code implementation NeurIPS 2020 Xinjie Fan, Shujian Zhang, Bo Chen, Mingyuan Zhou

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability.

Image Captioning Machine Translation +4

MCMC-Interactive Variational Inference

no code implementations2 Oct 2020 Quan Zhang, Huangjie Zheng, Mingyuan Zhou

Leveraging well-established MCMC strategies, we propose MCMC-interactive variational inference (MIVI) to not only estimate the posterior in a time constrained manner, but also facilitate the design of MCMC transitions.

Variational Inference

ACT: Asymptotic Conditional Transport

no code implementations28 Sep 2020 Huangjie Zheng, Mingyuan Zhou

We propose conditional transport (CT) as a new divergence to measure the difference between two probability distributions.

Generative Adversarial Network

Variational Temporal Deep Generative Model for Radar HRRP Target Recognition

no code implementations28 Sep 2020 Dandan Guo, Bo Chen, Wenchao Chen, Chaojie Wang, Hongwei Liu, Mingyuan Zhou

We develop a recurrent gamma belief network (rGBN) for radar automatic target recognition (RATR) based on high-resolution range profile (HRRP), which characterizes the temporal dependence across the range cells of HRRP.

Variational Inference

Graph Gamma Process Generalized Linear Dynamical Systems

1 code implementation25 Jul 2020 Rahi Kalantari, Mingyuan Zhou

We use the generated random graph, whose number of nonzero-degree nodes is finite, to define both the sparsity pattern and dimension of the latent state transition matrix of a (generalized) linear dynamical system.

Time Series Time Series Analysis

Implicit Distributional Reinforcement Learning

3 code implementations NeurIPS 2020 Yuguang Yue, Zhendong Wang, Mingyuan Zhou

To improve the sample efficiency of policy-gradient based reinforcement learning algorithms, we propose implicit distributional actor-critic (IDAC) that consists of a distributional critic, built on two deep generator networks (DGNs), and a semi-implicit actor (SIA), powered by a flexible policy distribution.

Distributional Reinforcement Learning OpenAI Gym +2

Deep Autoencoding Topic Model with Scalable Hybrid Bayesian Inference

no code implementations15 Jun 2020 Hao Zhang, Bo Chen, Yulai Cong, Dandan Guo, Hongwei Liu, Mingyuan Zhou

Given a posterior sample of the global parameters, in order to efficiently infer the local latent representations of a document under DATM across all stochastic layers, we propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a Weibull distribution based stochastic downward generative model.

Bayesian Inference

Probabilistic Best Subset Selection via Gradient-Based Optimization

1 code implementation11 Jun 2020 Mingzhang Yin, Nhat Ho, Bowei Yan, Xiaoning Qian, Mingyuan Zhou

This paper proposes a novel optimization method to solve the exact L0-regularized regression problem, which is also known as the best subset selection.

Methodology

Bayesian Graph Neural Networks with Adaptive Connection Sampling

1 code implementation ICML 2020 Arman Hasanzadeh, Ehsan Hajiramezanali, Shahin Boluki, Mingyuan Zhou, Nick Duffield, Krishna Narayanan, Xiaoning Qian

We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs.

Node Classification

Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator

no code implementations21 May 2020 Siamak Zamani Dadaneh, Shahin Boluki, Mingzhang Yin, Mingyuan Zhou, Xiaoning Qian

Semantic hashing has become a crucial component of fast similarity search in many large-scale information retrieval systems, in particular, for text data.

Information Retrieval Retrieval

Mutual Information Gradient Estimation for Representation Learning

1 code implementation ICLR 2020 Liangjian Wen, Yiji Zhou, Lirong He, Mingyuan Zhou, Zenglin Xu

To this end, we propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions.

Representation Learning

Learnable Bernoulli Dropout for Bayesian Deep Learning

no code implementations12 Feb 2020 Shahin Boluki, Randy Ardywibowo, Siamak Zamani Dadaneh, Mingyuan Zhou, Xiaoning Qian

In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters.

Collaborative Filtering Image Classification +2

Discrete Action On-Policy Learning with Action-Value Critic

1 code implementation10 Feb 2020 Yuguang Yue, Yunhao Tang, Mingzhang Yin, Mingyuan Zhou

Reinforcement learning (RL) in discrete action space is ubiquitous in real-world applications, but its complexity grows exponentially with the action-space dimension, making it challenging to apply existing on-policy gradient based deep RL algorithms efficiently.

OpenAI Gym Reinforcement Learning (RL)

Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation

1 code implementation ICLR 2020 Xinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou

To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control.

Image Captioning Program Synthesis

Recurrent Hierarchical Topic-Guided RNN for Language Generation

1 code implementation ICML 2020 Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou

To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation.

Language Modelling Sentence +1

Meta-Learning without Memorization

1 code implementation ICLR 2020 Mingzhang Yin, George Tucker, Mingyuan Zhou, Sergey Levine, Chelsea Finn

If this is not done, the meta-learner can ignore the task training data and learn a single model that performs all of the meta-training tasks zero-shot, but does not adapt effectively to new image classes.

Few-Shot Image Classification Memorization +1

Weibull Racing Survival Analysis with Competing Events, Left Truncation, and Time-varying Covariates

no code implementations2 Nov 2019 Quan Zhang, Qiang Gao, Mingfeng Lin, Mingyuan Zhou

Specifically, we study time to death of three types of lymphoma and show the potential of WDR in modeling nonlinear covariate effects and discovering new diseases.

Survival Analysis Methodology

ARSM Gradient Estimator for Supervised Learning to Rank

no code implementations1 Nov 2019 Siamak Zamani Dadaneh, Shahin Boluki, Mingyuan Zhou, Xiaoning Qian

Learning-to-rank methods can generally be categorized into pointwise, pairwise, and listwise approaches.

Learning-To-Rank

Thompson Sampling via Local Uncertainty

1 code implementation ICML 2020 Zhendong Wang, Mingyuan Zhou

Variational inference is used to approximate the posterior of the local variable, and semi-implicit structure is further introduced to enhance its expressiveness.

Decision Making Multi-Armed Bandits +2

Poisson-Randomized Gamma Dynamical Systems

1 code implementation NeurIPS 2019 Aaron Schein, Scott W. Linderman, Mingyuan Zhou, David M. Blei, Hanna Wallach

This paper presents the Poisson-randomized gamma dynamical system (PRGDS), a model for sequentially observed count tensors that encodes a strong inductive bias toward sparsity and burstiness.

Inductive Bias

Semi-Implicit Stochastic Recurrent Neural Networks

no code implementations28 Oct 2019 Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna Narayanan, Mingyuan Zhou, Xiaoning Qian

Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models.

Variational Inference

Recurrent Hierarchical Topic-Guided Neural Language Models

no code implementations25 Sep 2019 Dandan Guo, Bo Chen, Ruiying Lu, Mingyuan Zhou

To simultaneously capture syntax and semantics from a text corpus, we propose a new larger-context language model that extracts recurrent hierarchical semantic structure via a dynamic deep topic model to guide natural language generation.

Language Modelling Sentence +1

Variational Graph Recurrent Neural Networks

2 code implementations NeurIPS 2019 Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna R. Narayanan, Mingyuan Zhou, Xiaoning Qian

Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant.

Attribute Dynamic Link Prediction +2

Semi-Implicit Graph Variational Auto-Encoders

1 code implementation NeurIPS 2019 Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Krishna R. Narayanan, Mingyuan Zhou, Xiaoning Qian

Compared to VGAE, the derived graph latent representations by SIG-VAE are more interpretable, due to more expressive generative model and more faithful inference enabled by the flexible semi-implicit construction.

Decoder Variational Inference

Semi-Implicit Generative Model

no code implementations29 May 2019 Mingzhang Yin, Mingyuan Zhou

To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framework.

Diversity Generative Adversarial Network

Variational Hetero-Encoder Randomized GANs for Joint Image-Text Modeling

1 code implementation ICLR 2020 Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou

For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework.

Decoder Generative Adversarial Network

Convolutional Poisson Gamma Belief Network

1 code implementation14 May 2019 Chaojie Wang, Bo Chen, Sucheng Xiao, Mingyuan Zhou

For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector.

ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables

1 code implementation4 May 2019 Mingzhang Yin, Yuguang Yue, Mingyuan Zhou

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance.

Variational Autoencoders for Sparse and Overdispersed Discrete Data

1 code implementation2 May 2019 He Zhao, Piyush Rai, Lan Du, Wray Buntine, Mingyuan Zhou

Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data.

Collaborative Filtering Multi-Label Learning +1

VHEGAN: Variational Hetero-Encoder Randomized GAN for Zero-Shot Learning

no code implementations ICLR 2019 Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou

To extract and relate visual and linguistic concepts from images and textual descriptions for text-based zero-shot learning (ZSL), we develop variational hetero-encoder (VHE) that decodes text via a deep probabilisitic topic model, the variational posterior of whose local latent variables is encoded from an image via a Weibull distribution based inference network.

Image Generation Retrieval +3

Deep Topic Models for Multi-label Learning

no code implementations13 Apr 2019 Rajat Panda, Ankit Pensia, Nikhil Mehta, Mingyuan Zhou, Piyush Rai

We present a probabilistic framework for multi-label learning based on a deep generative model for the binary label vector associated with each observation.

Multi-Label Learning Topic Models

Non-Lambertian Surface Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field

no code implementations9 Apr 2019 Mingyuan Zhou, Yu Ji, Yuqi Ding, Jinwei Ye, S. Susan Young, Jingyi Yu

In this paper, we introduce a novel concentric multi-spectral light field (CMSLF) design that is able to recover the shape and reflectance of surfaces with arbitrary material in one shot.

Depth Estimation

3D Face Reconstruction Using Color Photometric Stereo with Uncalibrated Near Point Lights

no code implementations4 Apr 2019 Zhang Chen, Yu Ji, Mingyuan Zhou, Sing Bing Kang, Jingyi Yu

We avoid the need for spatial constancy of albedo; instead, we use a new measure for albedo similarity that is based on the albedo norm profile.

3D Face Reconstruction Semantic Segmentation

Augment-Reinforce-Merge Policy Gradient for Binary Stochastic Policy

no code implementations13 Mar 2019 Yunhao Tang, Mingzhang Yin, Mingyuan Zhou

Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency.

Dirichlet belief networks for topic structure learning

2 code implementations NeurIPS 2018 He Zhao, Lan Du, Wray Buntine, Mingyuan Zhou

Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures.

Topic Models

Deep Poisson gamma dynamical systems

no code implementations NeurIPS 2018 Dandan Guo, Bo Chen, Hao Zhang, Mingyuan Zhou

We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies.

Data Augmentation Time Series +1

Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data

no code implementations NeurIPS 2018 Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian

Second, compared to the number of involved molecules and system complexity, the number of available samples for studying complex disease, such as cancer, is often limited, especially considering disease heterogeneity.

Multi-Task Learning

Nonparametric Bayesian Lomax delegate racing for survival analysis with competing risks

1 code implementation NeurIPS 2018 Quan Zhang, Mingyuan Zhou

We propose Lomax delegate racing (LDR) to explicitly model the mechanism of survival under competing risks and to interpret how the covariates accelerate or decelerate the time to event.

Data Augmentation Survival Analysis

ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks

1 code implementation ICLR 2019 Mingzhang Yin, Mingyuan Zhou

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity.

Data Augmentation Variational Inference

Semi-Implicit Variational Inference

1 code implementation ICML 2018 Mingzhang Yin, Mingyuan Zhou

Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution.

Bayesian Inference Variational Inference

Parsimonious Bayesian deep networks

2 code implementations NeurIPS 2018 Mingyuan Zhou

Combining Bayesian nonparametrics and a forward model selection strategy, we construct parsimonious Bayesian deep networks (PBDNs) that infer capacity-regularized network architectures from the data and require neither cross-validation nor fine-tuning when training the model.

Model Selection

Masking: A New Perspective of Noisy Supervision

2 code implementations NeurIPS 2018 Bo Han, Jiangchao Yao, Gang Niu, Mingyuan Zhou, Ivor Tsang, Ya zhang, Masashi Sugiyama

It is important to learn various types of classifiers given training data with noisy labels.

Ranked #42 on Image Classification on Clothing1M (using extra training data)

Image Classification

Locally Private Bayesian Inference for Count Models

1 code implementation22 Mar 2018 Aaron Schein, Zhiwei Steven Wu, Alexandra Schofield, Mingyuan Zhou, Hanna Wallach

We present a general method for privacy-preserving Bayesian inference in Poisson factorization, a broad class of models that includes some of the most widely used models in the social sciences.

Bayesian Inference Link Prediction +1

Differential Expression Analysis of Dynamical Sequencing Count Data with a Gamma Markov Chain

no code implementations7 Mar 2018 Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Paul de Figueiredo, Sing-Hoi Sze, Mingyuan Zhou, Xiaoning Qian

Next-generation sequencing (NGS) to profile temporal changes in living systems is gaining more attention for deriving better insights into the underlying biological mechanisms compared to traditional static sequencing experiments.

Data Augmentation

WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling

1 code implementation ICLR 2018 Hao Zhang, Bo Chen, Dandan Guo, Mingyuan Zhou

To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes.

Nonparametric Bayesian Sparse Graph Linear Dynamical Systems

no code implementations21 Feb 2018 Rahi Kalantari, Joydeep Ghosh, Mingyuan Zhou

A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is proposed to model sequentially observed multivariate data.

Time Series Time Series Analysis

Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC

no code implementations ICML 2017 Yulai Cong, Bo Chen, Hongwei Liu, Mingyuan Zhou

It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers.

Data Augmentation

Poisson--Gamma Dynamical Systems

1 code implementation19 Jan 2017 Aaron Schein, Mingyuan Zhou, Hanna Wallach

We introduce a new dynamical system for sequentially observed multivariate count data.

Inductive Bias

Permuted and Augmented Stick-Breaking Bayesian Multinomial Regression

no code implementations30 Dec 2016 Quan Zhang, Mingyuan Zhou

To model categorical response variables given their covariates, we propose a permuted and augmented stick-breaking (paSB) construction that one-to-one maps the observed categories to randomly permuted latent sticks.

regression

Poisson-Gamma dynamical systems

1 code implementation NeurIPS 2016 Aaron Schein, Hanna Wallach, Mingyuan Zhou

This paper presents a dynamical system based on the Poisson-Gamma construction for sequentially observed multivariate count data.

Inductive Bias

Softplus Regressions and Convex Polytopes

no code implementations23 Aug 2016 Mingyuan Zhou

To construct flexible nonlinear predictive distributions, the paper introduces a family of softplus function based regression models that convolve, stack, or combine both operations by convolving countably infinite stacked gamma distributions, whose scales depend on the covariates.

Bayesian Inference Data Augmentation +1

Bayesian Poisson Tucker Decomposition for Learning the Structure of International Relations

1 code implementation6 Jun 2016 Aaron Schein, Mingyuan Zhou, David M. Blei, Hanna Wallach

We introduce Bayesian Poisson Tucker decomposition (BPTD) for modeling country--country interaction event data.

Rotational Crossed-Slit Light Field

no code implementations CVPR 2016 Nianyi Li, Haiting Lin, Bilin Sun, Mingyuan Zhou, Jingyi Yu

In this paper, we present a novel LF sampling scheme by exploiting a special non-centric camera called the crossed-slit or XSlit camera.

Stereo Matching Stereo Matching Hand

Nonparametric Bayesian Negative Binomial Factor Analysis

no code implementations25 Apr 2016 Mingyuan Zhou

A common approach to analyze a covariate-sample count matrix, an element of which represents how many times a covariate appears in a sample, is to factorize it under the Poisson likelihood.

Nonparametric Bayesian Factor Analysis for Dynamic Count Matrices

no code implementations30 Dec 2015 Ayan Acharya, Joydeep Ghosh, Mingyuan Zhou

A gamma process dynamic Poisson factor analysis model is proposed to factorize a dynamic count matrix, whose columns are sequentially observed count vectors.

Data Augmentation

Gamma Belief Networks

no code implementations9 Dec 2015 Mingyuan Zhou, Yulai Cong, Bo Chen

To infer multilayer deep representations of high-dimensional discrete and nonnegative real vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its hidden layers into the product of a sparse connection weight matrix and the nonnegative real hidden units of the next layer.

The Poisson Gamma Belief Network

no code implementations NeurIPS 2015 Mingyuan Zhou, Yulai Cong, Bo Chen

Example results on text analysis illustrate interesting relationships between the width of the first layer and the inferred network structure, and demonstrate that the PGBN, whose hidden units are imposed with correlated gamma priors, can add more layers to increase its performance gains over Poisson factor analysis, given the same limit on the width of the first layer.

Infinite Edge Partition Models for Overlapping Community Detection and Link Prediction

no code implementations25 Jan 2015 Mingyuan Zhou

A hierarchical gamma process infinite edge partition model is proposed to factorize the binary adjacency matrix of an unweighted undirected relational network under a Bernoulli-Poisson link.

Community Detection Data Augmentation +1

Beta-Negative Binomial Process and Exchangeable Random Partitions for Mixed-Membership Modeling

no code implementations NeurIPS 2014 Mingyuan Zhou

The beta-negative binomial process (BNBP), an integer-valued stochastic process, is employed to partition a count vector into a latent random count matrix.

Beta-Negative Binomial Process and Exchangeable Random Partitions for Mixed-Membership Modeling

no code implementations28 Oct 2014 Mingyuan Zhou

The beta-negative binomial process (BNBP), an integer-valued stochastic process, is employed to partition a count vector into a latent random count matrix.

Priors for Random Count Matrices Derived from a Family of Negative Binomial Processes

no code implementations12 Apr 2014 Mingyuan Zhou, Oscar Hernan Madrid Padilla, James G. Scott

We define a family of probability distributions for random count matrices with a potentially unbounded number of rows and columns.

feature selection text-classification +1

Generalized Negative Binomial Processes and the Representation of Cluster Structures

no code implementations7 Oct 2013 Mingyuan Zhou

The paper introduces the concept of a cluster structure to define a joint distribution of the sample size and its exchangeable random partitions.

Clustering

Augment-and-Conquer Negative Binomial Processes

no code implementations NeurIPS 2012 Mingyuan Zhou, Lawrence Carin

By developing data augmentation methods unique to the negative binomial (NB) distribution, we unite seemingly disjoint count and mixture models under the NB process framework.

Data Augmentation

Negative Binomial Process Count and Mixture Modeling

1 code implementation15 Sep 2012 Mingyuan Zhou, Lawrence Carin

A gamma process is employed to model the rate measure of a Poisson process, whose normalization provides a random probability measure for mixture modeling and whose marginalization leads to an NB process for count modeling.

Bayesian Inference

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