864 citations · 1.9k across the 57 of their papers we have counts for
21 papers · 1 filter
Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
Shuai Lin, Pan Zhou, Xiaodan Liang +4
Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledge-grounded di…
Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation
Daizong Liu, Shuangjie Xu, Xiao-Yang Liu +3
This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these…
F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation
Daizong Liu, Dongdong Yu, Changhu Wang +1
Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearanc…
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
Yubei Xiao, Ke Gong, Pan Zhou +3
Low-resource automatic speech recognition (ASR) is challenging, as the low-resource target language data cannot well train an ASR model. To solve this issue, meta-learning formulat…
User-based Network Embedding for Collective Opinion Spammer Detection
Ziyang Wang, Wei Wei, Xian-Ling Mao +3
Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the infl…
Target Guided Emotion Aware Chat Machine
Wei Wei, Jiayi Liu, Xianling Mao +5
The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge i…
Video-based Facial Expression Recognition using Graph Convolutional Networks
Daizong Liu, Hongting Zhang, Pan Zhou
Facial expression recognition (FER), aiming to classify the expression present in the facial image or video, has attracted a lot of research interests in the field of artificial in…
Iterative Graph Self-Distillation
Hanlin Zhang, Shuai Lin, Weiyang Liu +4
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distilla…
How Important is the Train-Validation Split in Meta-Learning?
Yu Bai, Minshuo Chen, Pan Zhou +5
Meta-learning aims to perform fast adaptation on a new task through learning a "prior" from multiple existing tasks. A common practice in meta-learning is to perform a train-valida…
Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning
Pan Zhou, Jiashi Feng, Chao Ma +3
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide…
Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization
Pan Zhou, Xiaotong Yuan
Stochastic variance-reduced gradient (SVRG) algorithms have been shown to work favorably in solving large-scale learning problems. Despite the remarkable success, the stochastic gr…
Federated Mutual Learning
Tao Shen, Jie Zhang, Xinkang Jia +6
Federated learning (FL) enables collaboratively training deep learning models on decentralized data. However, there are three types of heterogeneities in FL setting bringing about…
Theory-Inspired Path-Regularized Differential Network Architecture Search
Pan Zhou, Caiming Xiong, Richard Socher +1
Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradati…
Learning Decomposed Representation for Counterfactual Inference
Anpeng Wu, Kun Kuang, Junkun Yuan +5
The fundamental problem in treatment effect estimation from observational data is confounder identification and balancing. Most of the previous methods realized confounder balancin…
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
Yue Wu, Pan Zhou, Andrew Gordon Wilson +2
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially fo…
Data Augmentation Imbalance For Imbalanced Attribute Classification
Yang Hu, Xiaying Bai, Pan Zhou +2
Pedestrian attribute recognition is an important multi-label classification problem. Although the convolutional neural networks are prominent in learning discriminative features fr…
Prototypical Contrastive Learning of Unsupervised Representations
Junnan Li, Pan Zhou, Caiming Xiong +1
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive…
Crowd Counting via Hierarchical Scale Recalibration Network
Zhikang Zou, Yifan Liu, Shuangjie Xu +3
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenati…
Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels
Daizong Liu, Shuangjie Xu, Pan Zhou +3
Disease diagnosis on chest X-ray images is a challenging multi-label classification task. Previous works generally classify the diseases independently on the input image without co…
Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach
Zeyue Xue, Shuang Luo, Chao Wu +3
Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying o…
Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
Huawei Huang, Kangying Lin, Song Guo +2
Although the challenge of the device connection is much relieved in 5G networks, the training latency is still an obstacle preventing Federated Learning (FL) from being largely ado…