USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

• URL: http://arxiv.org/abs/2302.05889v1
• Date: Sun, 12 Feb 2023 10:32:12 GMT
• Title: USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Authors: Yifei Wang, Yupan Wang, Zeyu Zhang, Song Yang, Kaiqi Zhao, Jiamou Liu
• Abstract summary: Unsupervised graph neural networks (GNNs) are vulnerable to inherent randomness in the input graph data. We propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy. Experiments conducted on clustering and link prediction tasks under random-noises and meta-attack over three datasets show USER outperforms benchmarks.
• Score: 22.322867182077182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised/self-supervised graph neural networks (GNN) are vulnerable to inherent randomness in the input graph data which greatly affects the performance of the model in downstream tasks. In this paper, we alleviate the interference of graph randomness and learn appropriate representations of nodes without label information. To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy. We analyze the property of intrinsic connectivity and define intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. We then introduce structural entropy in the objective function to capture such a graph. Extensive experiments conducted on clustering and link prediction tasks under random-noises and meta-attack over three datasets show USER outperforms benchmarks and is robust to heavier randomness.

Related papers

• Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structure [7.133681867718039]
  Graph neural networks are becoming increasingly popular in the field of machine learning. They have been applied in safety-critical environments where perturbations inherently occur. This research addresses the non-passing gap by preserving the dependencies of all elements in the underlying computations.
  arXiv  Detail & Related papers  (2024-04-23T14:12:48Z)
• Multitask Active Learning for Graph Anomaly Detection [48.690169078479116]
  We propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. By coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection.
  arXiv  Detail & Related papers  (2024-01-24T03:43:45Z)
• Universally Robust Graph Neural Networks by Preserving Neighbor Similarity [5.660584039688214]
  We introduce a novel robust model termed NSPGNN which incorporates a dual-kNN graphs pipeline to supervise the neighbor similarity-guided propagation. Experiments on both homophilic and heterophilic graphs validate the universal robustness of NSPGNN compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-18T06:57:29Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification [59.06717774425588]
  We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field. It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations. We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
  arXiv  Detail & Related papers  (2021-07-27T19:47:53Z)
• Stability of Graph Convolutional Neural Networks to Stochastic Perturbations [122.12962842842349]
  Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. Current analysis considers deterministic perturbations but fails to provide relevant insights when topological changes are random. This paper investigates the stability of GCNNs to perturbed graph perturbations induced by link losses.
  arXiv  Detail & Related papers  (2021-06-19T16:25:28Z)
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs [54.13919050090926]
  We propose an end-to-end structural temporal Graph Neural Network model for detecting anomalous edges in dynamic graphs. In particular, we first extract the $h$-hop enclosing subgraph centered on the target edge and propose the node labeling function to identify the role of each node in the subgraph. Based on the extracted features, we utilize Gated recurrent units (GRUs) to capture the temporal information for anomaly detection.
  arXiv  Detail & Related papers  (2020-05-15T09:17:08Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

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.