181 citations · 1.7k across the 107 of their papers we have counts for
16 papers · 1 filter
Bayesian Graph Contrastive Learning
Arman Hasanzadeh, Mohammadreza Armandpour, Ehsan Hajiramezanali +3
Contrastive learning has become a key component of self-supervised learning approaches for graph-structured data. Despite their success, existing graph contrastive learning methods…
TopicNet: Semantic Graph-Guided Topic Discovery
Zhibin Duan, Yishi Xu, Bo Chen +3
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…
Alignment Attention by Matching Key and Query Distributions
Shujian Zhang, Xinjie Fan, Huangjie Zheng +2
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains. Most such models use multi-head self-atte…
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng +4
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampl…
Learning Prototype-oriented Set Representations for Meta-Learning
Dandan Guo, Long Tian, Minghe Zhang +2
Learning from set-structured data is a fundamental problem that has recently attracted increasing attention, where a series of summary networks are introduced to deal with the set…
Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network
Zhibin Duan, Dongsheng Wang, Bo Chen +5
Hierarchical topic models such as the gamma belief network (GBN) have delivered promising results in mining multi-layer document representations and discovering interpretable topic…
Bayesian Attention Belief Networks
Shujian Zhang, Xinjie Fan, Bo Chen +1
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less exp…
Probabilistic Margins for Instance Reweighting in Adversarial Training
Qizhou Wang, Feng Liu, Bo Han +5
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 cr…
Adversarially Adaptive Normalization for Single Domain Generalization
Xinjie Fan, Qifei Wang, Junjie Ke +3
Single domain generalization aims to learn a model that performs well on many unseen domains with only one domain data for training. Existing works focus on studying the adversaria…
ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
Alek Dimitriev, Mingyuan Zhou
Estimating the gradients for binary variables is a task that arises frequently in various domains, such as training discrete latent variable models. What has been commonly used is…
Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
Dandan Guo, Ruiying Lu, Bo Chen +2
Observing a set of images and their corresponding paragraph-captions, a challenging task is to learn how to produce a semantically coherent paragraph to describe the visual content…
Contrastive Attraction and Contrastive Repulsion for Representation Learning
Huangjie Zheng, Xu Chen, Jiangchao Yao +7
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative sampl…
Partition-Guided GANs
Mohammadreza Armandpour, Ali Sadeghian, Chunyuan Li +1
Despite the success of Generative Adversarial Networks (GANs), their training suffers from several well-known problems, including mode collapse and difficulties learning a disconne…
Contextual Dropout: An Efficient Sample-Dependent Dropout Module
Xinjie Fan, Shujian Zhang, Korawat Tanwisuth +2
Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for…
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
Haoang Chi, Feng Liu, Bo Han +6
In novel class discovery (NCD), we are given labeled data from seen classes and unlabeled data from unseen classes, and we train clustering models for the unseen classes. However,…
Self-supervised Pre-training with Hard Examples Improves Visual Representations
Chunyuan Li, Xiujun Li, Lei Zhang +3
Self-supervised pre-training (SSP) employs random image transformations to generate training data for visual representation learning. In this paper, we first present a modeling fra…