Robust Subgraph Learning by Monitoring Early Training Representations
- URL: http://arxiv.org/abs/2403.09901v2
- Date: Mon, 18 Nov 2024 17:43:31 GMT
- Title: Robust Subgraph Learning by Monitoring Early Training Representations
- Authors: Sepideh Neshatfar, Salimeh Yasaei Sekeh,
- Abstract summary: Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks.
Their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a challenge in decision-making.
We introduce the novel technique SHERD (Subgraph Learning Hale through Early Training Representation Distances) to address both performance and adversarial robustness in graph input.
- Score: 5.524804393257921
- License:
- Abstract: Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks. However, their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a challenge in decision-making. The need for robust graph summarization is evident in adversarial challenges resulting from the propagation of attacks throughout the entire graph. In this paper, we address both performance and adversarial robustness in graph input by introducing the novel technique SHERD (Subgraph Learning Hale through Early Training Representation Distances). SHERD leverages information from layers of a partially trained graph convolutional network (GCN) to detect susceptible nodes during adversarial attacks using standard distance metrics. The method identifies "vulnerable (bad)" nodes and removes such nodes to form a robust subgraph while maintaining node classification performance. Through our experiments, we demonstrate the increased performance of SHERD in enhancing robustness by comparing the network's performance on original and subgraph inputs against various baselines alongside existing adversarial attacks. Our experiments across multiple datasets, including citation datasets such as Cora, Citeseer, and Pubmed, as well as microanatomical tissue structures of cell graphs in the placenta, highlight that SHERD not only achieves substantial improvement in robust performance but also outperforms several baselines in terms of node classification accuracy and computational complexity.
Related papers
- Self-Supervised Conditional Distribution Learning on Graphs [15.730933577970687]
We present an end-to-end graph representation learning model to align the conditional distributions of weakly and strongly augmented features over the original features.
This alignment effectively reduces the risk of disrupting intrinsic semantic information through graph-structured data augmentation.
arXiv Detail & Related papers (2024-11-20T07:26:36Z) - HGAttack: Transferable Heterogeneous Graph Adversarial Attack [63.35560741500611]
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce.
This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs.
arXiv Detail & Related papers (2024-01-18T12:47:13Z) - BOURNE: Bootstrapped Self-supervised Learning Framework for Unified
Graph Anomaly Detection [50.26074811655596]
We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE)
By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies.
BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
arXiv Detail & Related papers (2023-07-28T00:44:57Z) - CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network [33.18119972779757]
Hypergraphs can model higher-order relationships among data objects found in applications such as social networks and bioinformatics.
We propose a contrastive hypergraph neural network, CHGNN, that exploits self-supervised contrastive learning techniques to learn from labeled and unlabeled data.
Experimental results on nine real datasets offer insight into the effectiveness of CHGNN, showing that it outperforms 13 competitors in terms of classification accuracy consistently.
arXiv Detail & Related papers (2023-03-10T21:28:10Z) - Spectral Adversarial Training for Robust Graph Neural Network [36.26575133994436]
Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations.
Adversarial Training (AT) is a successful approach to learning a robust model using adversarially perturbed training samples.
We propose Spectral Adversarial Training (SAT), a simple yet effective adversarial training approach for GNNs.
arXiv Detail & Related papers (2022-11-20T07:56:55Z) - Resisting Graph Adversarial Attack via Cooperative Homophilous
Augmentation [60.50994154879244]
Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations.
In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack.
We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
arXiv Detail & Related papers (2022-11-15T11:44:31Z) - A Systematic Evaluation of Node Embedding Robustness [77.29026280120277]
We assess the empirical robustness of node embedding models to random and adversarial poisoning attacks.
We compare edge addition, deletion and rewiring strategies computed using network properties as well as node labels.
We found that node classification suffers from higher performance degradation as opposed to network reconstruction.
arXiv Detail & Related papers (2022-09-16T17:20:23Z) - Information Obfuscation of Graph Neural Networks [96.8421624921384]
We study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data.
We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance.
arXiv Detail & Related papers (2020-09-28T17:55:04Z) - Subgraph Neural Networks [14.222887950206662]
We introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations.
SubGNN performs exceptionally well on challenging biomedical datasets.
arXiv Detail & Related papers (2020-06-18T13:54:30Z) - 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)
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.