Journal Article10.1109/tkde.2022.3220789
Dual Feature Interaction-Based Graph Convolutional Network
27
TL;DR: In this article , a dual feature interaction-based graph convolutional network (DFI-GCN) is proposed to capture the pairwise interactions among nodes in the neighborhood to expand a weighted sum operation.
read more
Abstract: Graphs are widely used to model various practical applications. In recent years, graph convolution networks (GCNs) have attracted increasing attention due to the extension of convolution operation from traditional grid data to graph one. However, the representation ability of current GCNs is undoubtedly limited because existing work fails to consider feature interactions. Toward this end, we propose a Dual Feature Interaction-based GCN. Specifically, it models feature interaction in the aspects of 1) node features where we use Newton's identity to extract different-order cross features implicit in the original features and design an attention mechanism to fuse them; and 2) graph convolution where we capture the pairwise interactions among nodes in the neighborhood to expand a weighted sum operation. We evaluate the proposed model with graph data from different fields, and the experimental results on semi-supervised node classification and link prediction demonstrate the effectiveness of the proposed GCN. The data and source codes of this work are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ZZY-GraphMiningLab/DFI-GCN</uri> .
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Self-supervised contrastive learning on heterogeneous graphs with mutual constraints of structure and feature
TL;DR: Zhou et al. as discussed by the authors proposed a self-supervised contrastive learning method on heterogeneous graphs with mutual constraints of structure and feature called HeMuc to handle the noises in graphs effectively.
20
Skill-transferring Knowledge Distillation Method
TL;DR: Zhang et al. as discussed by the authors proposed a skill-transferring knowledge distillation (SKD) method to boost a student network's ability to create new valuable knowledge, which consists of two main meta-learning networks: teacher behavior teaching and teacher experience teaching.
17
Adaptive Divergence-Based Non-Negative Latent Factor Analysis of High-Dimensional and Incomplete Matrices From Industrial Applications
TL;DR: This study proposes an Adaptive Divergence-based Non-Negative Latent Factor Analysis (ADNL) model for high-dimensional and incomplete matrices, generalizing the objective function with α-β-divergence, facilitating non-negative bridging, and making divergence parameters adaptive for high scalability and improved estimation accuracy.
10
Improving Knowledge Distillation via Head and Tail Categories
Liuchi Xu,Jin Ren,Zhenhua Huang,Weishi Zheng +3 more
TL;DR: ReKD effectively transfers knowledge from head and tail categories, improving student performance on image classification tasks.
6
References
Graph Attention Networks
Petar Veličković,Guillem Cucurull,Arantxa Casanova,Adriana Romero,Pietro Liò,Yoshua Bengio +5 more
- 15 Feb 2018
TL;DR: Graph Attention Networks (GATs) as mentioned in this paper leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
Backpropagation applied to handwritten zip code recognition
Yann LeCun,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +6 more
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
12.5K
DeepWalk: online learning of social representations
Bryan Perozzi,Rami Al-Rfou,Steven Skiena +2 more
- 24 Aug 2014
TL;DR: DeepWalk as mentioned in this paper uses local information obtained from truncated random walks to learn latent representations by treating walks as the equivalent of sentences, which encode social relations in a continuous vector space, which is easily exploited by statistical models.
Collective Classification in Network Data
TL;DR: This article introduces four of the most widely used inference algorithms for classifying networked data and empirically compare them on both synthetic and real-world data.
•Posted Content
Variational Graph Auto-Encoders
Thomas Kipf,Max Welling +1 more
TL;DR: The variational graph auto-encoder (VGAE) is introduced, a framework for unsupervised learning on graph-structured data based on the variational auto- Encoder (VAE) that can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.
2.9K