Channel-Attentive Graph Neural Networks
24th IEEE International Conference on Data Mining, ICDM 2024, Abu Dhabi, Birleşik Arap Emirlikleri, 9 - 12 Aralık 2024, ss.729-734, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/icdm59182.2024.00084
- Basıldığı Şehir: Abu Dhabi
- Basıldığı Ülke: Birleşik Arap Emirlikleri
- Sayfa Sayıları: ss.729-734
- Anahtar Kelimeler: Attention, Deep learning, Graph neural network, Repre-sentation learning
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Boğaziçi Üniversitesi Adresli: Evet
Özet
Graph Neural Networks (GNNs) set the state-of-the-art in representation learning for graph-structured data. They are used in many domains, from online social networks to complex molecules. Most GNNs leverage the message-passing paradigm and achieve strong performances on various tasks. However, the message-passing mechanism used in most models suffers from over-smoothing as a GNN's depth increases. The over-smoothing degrades GNN's performance due to the increased similarity between the representations of unrelated nodes. This study proposes an adaptive channel-wise message-passing approach to alleviate the over-smoothing. The proposed model, Channel-Attentive GNN, learns how to attend to neighboring nodes and their feature channels. Thus, much diverse information can be transferred between nodes during message-passing. Experiments with widely used benchmark datasets show that the proposed model is more resistant to over-smoothing than baselines and achieves state-of-the-art performances for various graphs with strong heterophily. Our code is at https://github.com/ALLab-Boun/CHAT-GNN.