arXiv Analytics

Sign in

arXiv:2105.00490 [cs.CV]AbstractReferencesReviewsResources

Residual Enhanced Multi-Hypergraph Neural Network

Jing Huang, Xiaolin Huang, Jie Yang

Published 2021-05-02Version 1

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains. Meanwhile, HyperGraph Neural Network (HGNN) is currently the de-facto method for hypergraph representation learning. However, HGNN aims at single hypergraph learning and uses a pre-concatenation approach when confronting multi-modal datasets, which leads to sub-optimal exploitation of the inter-correlations of multi-modal hypergraphs. HGNN also suffers the over-smoothing issue, that is, its performance drops significantly when layers are stacked up. To resolve these issues, we propose the Residual enhanced Multi-Hypergraph Neural Network, which can not only fuse multi-modal information from each hypergraph effectively, but also circumvent the over-smoothing issue associated with HGNN. We conduct experiments on two 3D benchmarks, the NTU and the ModelNet40 datasets, and compare against multiple state-of-the-art methods. Experimental results demonstrate that both the residual hypergraph convolutions and the multi-fusion architecture can improve the performance of the base model and the combined model achieves a new state-of-the-art. Code is available at \url{}.

Related articles: Most relevant | Search more
arXiv:2006.07084 [cs.CV] (Published 2020-06-12)
A Face Preprocessing Approach for Improved DeepFake Detection
arXiv:1905.12261 [cs.CV] (Published 2019-05-29)
KG-GAN: Knowledge-Guided Generative Adversarial Networks
arXiv:1908.02671 [cs.CV] (Published 2019-08-07)
Dual-reference Age Synthesis