1 code implementation • 24 Dec 2024 • Jingyu Li, Zhiyong Feng, Dongxiao He, Hongqi Chen, Qinghang Gao, Guoli Wu
To tackle this problem, we propose Contrastive Representation for Interactive Recommendation (CRIR).
no code implementations • 12 Dec 2024 • Sheng Wu, Xiaobao Wang, Longbiao Wang, Dongxiao He, Jianwu Dang
Multimodal Sentiment Analysis (MSA) stands as a critical research frontier, seeking to comprehensively unravel human emotions by amalgamating text, audio, and visual data.
no code implementations • 12 Apr 2024 • Sheng Wu, Jiaxing Liu, Longbiao Wang, Dongxiao He, Xiaobao Wang, Jianwu Dang
On the other hand, the Modality Interaction Network performs interaction fusion of extracted inter-modal features and intra-modal features.
no code implementations • 29 Mar 2024 • Yucheng Jin, Yun Xiong, Juncheng Fang, Xixi Wu, Dongxiao He, Xing Jia, Bingchen Zhao, Philip Yu
Inter-class correlations are subsequently eliminated by the prototypical attention network, leading to distinctive representations for different classes.
1 code implementation • 10 Jan 2024 • Luzhi Wang, Dongxiao He, He Zhang, Yixin Liu, Wenjie Wang, Shirui Pan, Di Jin, Tat-Seng Chua
To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN.
no code implementations • 24 Dec 2022 • Cuiying Huo, Di Jin, Yawen Li, Dongxiao He, Yu-Bin Yang, Lingfei Wu
A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i. e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors.
no code implementations • 28 Jun 2022 • Di Jin, Rui Wang, Meng Ge, Dongxiao He, Xiang Li, Wei Lin, Weixiong Zhang
Due to the homophily assumption of Graph Convolutional Networks (GCNs) that these methods use, they are not suitable for heterophily graphs where nodes with different labels or dissimilar attributes tend to be adjacent.
no code implementations • 25 May 2022 • Cuiying Huo, Di Jin, Chundong Liang, Dongxiao He, Tie Qiu, Lingfei Wu
In this work, we propose a new GNN based trust evaluation method named TrustGNN, which integrates smartly the propagative and composable nature of trust graphs into a GNN framework for better trust evaluation.
no code implementations • 30 Apr 2022 • Cuiying Huo, Dongxiao He, Yawen Li, Di Jin, Jianwu Dang, Weixiong Zhang, Witold Pedrycz, Lingfei Wu
However, the existing contrastive learning methods are inadequate for heterogeneous graphs because they construct contrastive views only based on data perturbation or pre-defined structural properties (e. g., meta-path) in graph data while ignore the noises that may exist in both node attributes and graph topologies.
1 code implementation • 27 Dec 2021 • Dongxiao He, Chundong Liang, Huixin Liu, Mingxiang Wen, Pengfei Jiao, Zhiyong Feng
Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation.
no code implementations • 27 Dec 2021 • Tao Wang, Rui Wang, Di Jin, Dongxiao He, Yuxiao Huang
To address this problem, in this paper we design a novel propagation mechanism, which can automatically change the propagation and aggregation process according to homophily or heterophily between node pairs.
1 code implementation • NeurIPS 2021 • Di Jin, Zhizhi Yu, Cuiying Huo, Rui Wang, Xiao Wang, Dongxiao He, Jiawei Han
So can we reasonably utilize these segmentation rules to design a universal propagation mechanism independent of the network structural assumption?
1 code implementation • NAACL 2021 • Zhongfen Deng, Hao Peng, Dongxiao He, JianXin Li, Philip S. Yu
The second one encourages the structure encoder to learn better representations with desired characteristics for all labels which can better handle label imbalance in hierarchical text classification.
no code implementations • 3 Jan 2021 • Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip S. Yu, Weixiong Zhang
We conclude with discussions of the challenges of the field and suggestions of possible directions for future research.
no code implementations • 6 Jul 2020 • Di Jin, Zhizhi Yu, Dongxiao He, Carl Yang, Philip S. Yu, Jiawei Han
Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors.
no code implementations • International Conference on Tools with Artificial Intelligence (ICTAI) 2017 • Di Jin, Meng Ge, Zhixuan Li, Wenhuan Lu, Dongxiao He, Francoise Fogelman-Soulie
Thanks to spectral clustering which is one of the best community detection methods, the proposed new method is also good at community discovery task.