Towards Deep Attention in Graph Neural Networks: Problems and Remedies

• URL: http://arxiv.org/abs/2306.02376v1
• Date: Sun, 4 Jun 2023 15:19:44 GMT
• Title: Towards Deep Attention in Graph Neural Networks: Problems and Remedies
• Authors: Soo Yong Lee, Fanchen Bu, Jaemin Yoo, Kijung Shin
• Abstract summary: Graph neural networks (GNNs) learn the representation of graph-structured data, and their expressiveness can be enhanced by inferring node relations for propagation. We investigate some problematic phenomena related to deep graph attention, including vulnerability to over-smoothed features and smooth cumulative attention. Motivated by our findings, we propose AEROGNN, a novel GNN architecture designed for deep graph attention.
• Score: 15.36416000750147
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Neighbor Overlay-Induced Graph Attention Network [5.792501481702088]
  Graph neural networks (GNNs) have garnered significant attention due to their ability to represent graph data. This study proposes a neighbor overlay-induced graph attention network (NO-GAT) with the following two-fold ideas. Empirical studies on graph benchmark datasets indicate that the proposed NO-GAT consistently outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2024-08-16T15:01:28Z)
• Spectral Greedy Coresets for Graph Neural Networks [61.24300262316091]
  The ubiquity of large-scale graphs in node-classification tasks hinders the real-world applications of Graph Neural Networks (GNNs) This paper studies graph coresets for GNNs and avoids the interdependence issue by selecting ego-graphs based on their spectral embeddings. Our spectral greedy graph coreset (SGGC) scales to graphs with millions of nodes, obviates the need for model pre-training, and applies to low-homophily graphs.
  arXiv  Detail & Related papers  (2024-05-27T17:52:12Z)
• Information Flow in Graph Neural Networks: A Clinical Triage Use Case [49.86931948849343]
  Graph Neural Networks (GNNs) have gained popularity in healthcare and other domains due to their ability to process multi-modal and multi-relational graphs. We investigate how the flow of embedding information within GNNs affects the prediction of links in Knowledge Graphs (KGs) Our results demonstrate that incorporating domain knowledge into the GNN connectivity leads to better performance than using the same connectivity as the KG or allowing unconstrained embedding propagation.
  arXiv  Detail & Related papers  (2023-09-12T09:18:12Z)
• DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
  We propose DEGREE to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
  arXiv  Detail & Related papers  (2023-05-22T10:29:52Z)
• Improving Your Graph Neural Networks: A High-Frequency Booster [20.391179274946214]
  We argue that the complement of the original graph incorporates a high-pass filter and propose Complement Laplacian Regularization (CLAR) for an efficient enhancement of high-frequency components. The experimental results demonstrate that CLAR helps GNNs tackle over-smoothing, improving the expressiveness of heterophilic graphs.
  arXiv  Detail & Related papers  (2022-10-15T10:24:28Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective [44.96635754139024]
  Oversmoothing has been identified as one of the key issues which limit the performance of deep GNNs. We propose a new perspective to look at the performance degradation of deep GNNs, i.e., feature overcorrelation. To reduce the feature correlation, we propose a general framework DeCorr which can encourage GNNs to encode less redundant information.
  arXiv  Detail & Related papers  (2022-06-15T18:13:52Z)
• EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks [51.42338058718487]
  Graph Neural Networks (GNNs) have received extensive research attention for their promising performance in graph machine learning. Existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs. We propose EvenNet, a spectral GNN corresponding to an even-polynomial graph filter.
  arXiv  Detail & Related papers  (2022-05-27T10:48:14Z)
• Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions [51.597480162777074]
  Graph neural networks (GNNs) rely on the message passing paradigm to propagate node features and build interactions. Recent works point out that different graph learning tasks require different ranges of interactions between nodes. We study two common graph construction methods in scientific domains, i.e., emphK-nearest neighbor (KNN) graphs and emphfully-connected (FC) graphs.
  arXiv  Detail & Related papers  (2022-05-15T11:38:14Z)
• Addressing Over-Smoothing in Graph Neural Networks via Deep Supervision [13.180922099929765]
  Deep graph neural networks (GNNs) suffer from over-smoothing when the number of layers increases. We propose DSGNNs enhanced with deep supervision where representations learned at all layers are used for training. We show that DSGNNs are resilient to over-smoothing and can outperform competitive benchmarks on node and graph property prediction problems.
  arXiv  Detail & Related papers  (2022-02-25T06:05:55Z)
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives [27.148827305359436]
  Graph neural networks (GNNs) have attracted much attention because of their excellent performance on tasks such as node classification. This paper aims to provide a theoretical framework to understand GNNs, specifically, spectral graph convolutional networks and graph attention networks.
  arXiv  Detail & Related papers  (2020-06-08T07:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.