LGAIJun 4, 2023

Towards Deep Attention in Graph Neural Networks: Problems and Remedies

arXiv:2306.02376v144 citationsh-index: 29Has Code
Originality Incremental advance
AI Analysis

This work addresses challenges in graph neural networks for researchers and practitioners, offering an incremental improvement with a novel architecture for deep attention.

The paper tackles problems in deep graph attention networks, such as over-smoothing, and proposes AERO-GNN, which mitigates these issues and achieves higher performance on node classification benchmarks, outperforming baselines on 9 out of 12 datasets.

Graph neural networks (GNNs) learn the representation of graph-structured data, and their expressiveness can be further enhanced by inferring node relations for propagation. Attention-based GNNs infer neighbor importance to manipulate the weight of its propagation. Despite their popularity, the discussion on deep graph attention and its unique challenges has been limited. In this work, we investigate some problematic phenomena related to deep graph attention, including vulnerability to over-smoothed features and smooth cumulative attention. Through theoretical and empirical analyses, we show that various attention-based GNNs suffer from these problems. Motivated by our findings, we propose AEROGNN, a novel GNN architecture designed for deep graph attention. AERO-GNN provably mitigates the proposed problems of deep graph attention, which is further empirically demonstrated with (a) its adaptive and less smooth attention functions and (b) higher performance at deep layers (up to 64). On 9 out of 12 node classification benchmarks, AERO-GNN outperforms the baseline GNNs, highlighting the advantages of deep graph attention. Our code is available at https://github.com/syleeheal/AERO-GNN.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes