Structural Alignment Improves Graph Test-Time Adaptation

• URL: http://arxiv.org/abs/2502.18334v1
• Date: Tue, 25 Feb 2025 16:26:25 GMT
• Title: Structural Alignment Improves Graph Test-Time Adaptation
• Authors: Hans Hao-Hsun Hsu, Shikun Liu, Han Zhao, Pan Li,
• Abstract summary: Graph-based learning has achieved remarkable success in domains ranging from recommendation to fraud detection and particle physics.<n>It often struggles to generalize when distribution shifts occur, particularly those involving changes in network connectivity or interaction patterns.<n>Existing approaches designed to mitigate such shifts typically require retraining with full access to source data, rendering them infeasible under strict computational or privacy constraints.<n>We propose a test-time structural alignment (TSA) algorithm for Graph Test-Time Adaptation (GTTA), a novel method that aligns graph structures during inference without revisiting the source domain.
• Score: 17.564393890432193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph-based learning has achieved remarkable success in domains ranging from recommendation to fraud detection and particle physics by effectively capturing underlying interaction patterns. However, it often struggles to generalize when distribution shifts occur, particularly those involving changes in network connectivity or interaction patterns. Existing approaches designed to mitigate such shifts typically require retraining with full access to source data, rendering them infeasible under strict computational or privacy constraints. To address this limitation, we propose a test-time structural alignment (TSA) algorithm for Graph Test-Time Adaptation (GTTA), a novel method that aligns graph structures during inference without revisiting the source domain. Built upon a theoretically grounded treatment of graph data distribution shifts, TSA integrates three key strategies: an uncertainty-aware neighborhood weighting that accommodates structure shifts, an adaptive balancing of self-node and neighborhood-aggregated representations driven by node representations' signal-to-noise ratio, and a decision boundary refinement that corrects remaining label and feature shifts. Extensive experiments on synthetic and real-world datasets demonstrate that TSA can consistently outperform both non-graph TTA methods and state-of-the-art GTTA baselines.

Related papers

• Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation [28.214010408550394]
  Unsupervised Graph Domain Adaptation (UGDA) seeks to bridge distribution shifts between domains by transferring knowledge from labeled source graphs to given unlabeled target graphs.<n>We introduce a novel approach for UGDA called Target-Domain Structural Smoothing ( TDSS)<n> TDSS is a simple and effective method designed to perform structural smoothing directly on the target graph.
  arXiv  Detail & Related papers  (2024-12-16T10:56:58Z)
• Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation [66.40525136929398]
  Test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain.<n>We propose Matcha, an innovative framework designed for effective and efficient adaptation to structure shifts in graphs.<n>We validate the effectiveness of Matcha on both synthetic and real-world datasets, demonstrating its robustness across various combinations of structure and attribute shifts.
  arXiv  Detail & Related papers  (2024-10-09T15:15:40Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph [24.44321658238713]
  Graph Neural Networks (GNNs) are widely used for node classification tasks but often fail to generalize when training and test nodes come from different distributions. We introduce the Topology-Aware Dynamic Reweighting (TAR) framework, which dynamically adjusts sample weights through gradient flow in the Wasserstein space during training. Our framework's superiority is demonstrated through standard testing on four graph OOD datasets and three class-imbalanced node classification datasets.
  arXiv  Detail & Related papers  (2024-06-03T07:32:05Z)
• Pairwise Alignment Improves Graph Domain Adaptation [16.626928606474173]
  This work delves into Graph Domain Adaptation (GDA) to address the unique complexities of distribution shifts over graph data. We propose a novel, theoretically principled method, Pairwise Alignment (Pair-Align) to counter graph structure shift. Our method demonstrates superior performance in real-world applications, including node classification with region shift in social networks.
  arXiv  Detail & Related papers  (2024-03-02T04:31:28Z)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• 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)
• Structural Re-weighting Improves Graph Domain Adaptation [13.019371337183202]
  This work examines different impacts of distribution shifts caused by either graph structure or node attributes. A novel approach, called structural reweighting (StruRW), is proposed to address this issue and is tested on synthetic graphs, four benchmark datasets, and a new application in high energy physics.
  arXiv  Detail & Related papers  (2023-06-05T20:11:30Z)
• Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification [69.45543438974963]
  We find graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues. The well-trained input features weaken the learning of graph topology, making it not generalized enough during the inference process. We propose a Counterfactual Intervention Feature Transfer (CIFT) method to tackle these problems.
  arXiv  Detail & Related papers  (2022-08-01T16:15:31Z)
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning [64.98816284854067]
  Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. A novel GCN-based SSL algorithm is presented in this paper to enrich the supervision signals by utilizing both data similarities and graph structure.
  arXiv  Detail & Related papers  (2020-09-15T13:59:28Z)

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.