activity
20182022
most citedLabel-invariant Augmentation for Semi-Supervised Graph Classification

10 citations · 30 across the 9 of their papers we have counts for

collaborators

10 papers

cs.LG20221 cited

Contrastive Graph Few-Shot Learning

Chunhui Zhang, Hongfu Liu, Jundong Li +2

Prevailing deep graph learning models often suffer from label sparsity issue. Although many graph few-shot learning (GFL) methods have been developed to avoid performance degradati…

cs.CV20222 cited

Learnable Visual Words for Interpretable Image Recognition

Wenxiao Xiao, Zhengming Ding, Hongfu Liu

To interpret deep models' predictions, attention-based visual cues are widely used in addressing \textit{why} deep models make such predictions. Beyond that, the current research c…

cs.CV202210 cited

Label-invariant Augmentation for Semi-Supervised Graph Classification

Han Yue, Chunhui Zhang, Chuxu Zhang +1

Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated a…

cs.LG2021

IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation

Sibo Zhu, Handong Zhao, Hongfu Liu

Outlier detection is one of the most popular and continuously rising topics in the data mining field due to its crucial academic value and extensive industrial applications. Among…

cs.LG2021

Deep Clustering based Fair Outlier Detection

Hanyu Song, Peizhao Li, Hongfu Liu

In this paper, we focus on the fairness issues regarding unsupervised outlier detection. Traditional algorithms, without a specific design for algorithmic fairness, could implicitl…

cs.CV20217 cited

SelfDoc: Self-Supervised Document Representation Learning

Peizhao Li, Jiuxiang Gu, Jason Kuen +5

We propose SelfDoc, a task-agnostic pre-training framework for document image understanding. Because documents are multimodal and are intended for sequential reading, our framework…