Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Huan Liu

Huan Liu

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Dec 24, 2022
Ujun Jeong, Kaize Ding, Lu Cheng, Ruocheng Guo, Kai Shu, Huan Liu

Figure 1 for Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Figure 2 for Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Figure 3 for Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Figure 4 for Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

* Accepted in IEEE Big Data 22

Access Paper or Ask Questions

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Dec 11, 2022
Zhen Tan, Song Wang, Kaize Ding, Jundong Li, Huan Liu

Figure 1 for Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Figure 2 for Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Figure 3 for Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Figure 4 for Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

* Accepted to the First Learning on Graph Conference (LoG 2022)

Access Paper or Ask Questions

FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Dec 02, 2022
Maowei Jiang, Pengyu Zeng, Kai Wang, Huan Liu, Wenbo Chen, Haoran Liu

Figure 1 for FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Figure 2 for FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Figure 3 for FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

Figure 4 for FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series Forecasting

* 11pages.10 figures,conference. arXiv admin note: text overlap with arXiv:2205.14415 by other authors

Access Paper or Ask Questions

GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Nov 08, 2022
Yixin Liu, Kaize Ding, Huan Liu, Shirui Pan

Figure 1 for GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Figure 2 for GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Figure 3 for GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Figure 4 for GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

* Accepted by WSDM 2023. 10 pages, 4 figures

Access Paper or Ask Questions

Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

Oct 01, 2022
Li Gu, Zhixiang Chi, Huan Liu, Yuanhao Yu, Yang Wang

Figure 1 for Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

Figure 2 for Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

Figure 3 for Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

Figure 4 for Improving ProtoNet for Few-Shot Video Object Recognition: Winner of ORBIT Challenge 2022

* Winner of ORBIT Challenge 2022

Access Paper or Ask Questions

Debiasing Word Embeddings with Nonlinear Geometry

Aug 29, 2022
Lu Cheng, Nayoung Kim, Huan Liu

Figure 1 for Debiasing Word Embeddings with Nonlinear Geometry

Figure 2 for Debiasing Word Embeddings with Nonlinear Geometry

Figure 3 for Debiasing Word Embeddings with Nonlinear Geometry

Figure 4 for Debiasing Word Embeddings with Nonlinear Geometry

* Accepted to COLING2022

Access Paper or Ask Questions

Learning with Few Labeled Nodes via Augmented Graph Self-Training

Aug 26, 2022
Kaize Ding, Elnaz Nouri, Guoqing Zheng, Huan Liu, Ryen White

Figure 1 for Learning with Few Labeled Nodes via Augmented Graph Self-Training

Figure 2 for Learning with Few Labeled Nodes via Augmented Graph Self-Training

Figure 3 for Learning with Few Labeled Nodes via Augmented Graph Self-Training

Figure 4 for Learning with Few Labeled Nodes via Augmented Graph Self-Training

* Under Review

Access Paper or Ask Questions