T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

• URL: http://arxiv.org/abs/2606.30011v1
• Date: Mon, 29 Jun 2026 09:18:11 GMT
• Title: T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
• Abstract summary: Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, leading to degraded performance under distribution shifts.<n>A potential approach is Test-Time Training (TTT), which adapts models' weights using unlabeled test data.<n>We propose T3R, leveraging multiple Rotograd matrices to improve task affinity between the target and auxiliary tasks.
• Score: 41.99844472131922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts. This issue can be mitigated by conventional fine-tuning, but in many real-world cases, collecting labeled data is expensive or infeasible. A potential approach is Test-Time Training (TTT), which adapts models' weights using unlabeled test data, yet it is typically limited to shallow updates that affect only a subset of model parameters. We propose T3R, leveraging multiple Rotograd matrices to improve task affinity between the target and auxiliary tasks, essential for effective test-time training. T3R further introduces a rotation technique that reorients self-supervised signals using these matrices to create surrogate gradients for the target task, allowing deeper adaptation across nearly the entire architecture. Empirically, T3R reduces MAE by 0.172 points over standard inference in regression datasets and achieves at least 9.37% relative improvement on cross-domain OGB classification benchmarks compared to models without adaptation. These results highlight the potential to develop an adaptation pipeline for graph-based systems, particularly in settings where conventional fine-tuning or retraining is infeasible.

Related papers

• Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence [30.38509036690193]
  MOCHI is a multi-view 3D face prediction framework trained without requiring registered training data.<n>Standard point-to-surface distances induce training instabilities and visual artifacts in registration-free settings.<n>We propose pointmap- and normal-based losses instead, which provide smoother gradients and superior reconstruction fidelity.
  arXiv  Detail & Related papers  (2026-05-02T13:59:29Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Challenges in 3D Data Synthesis for Training Neural Networks on Topological Features [0.0]
  Topological Data Analysis involves techniques of analyzing the underlying structure and connectivity of data.<n>Traditional methods like persistent homology can be computationally demanding, motivating the development of neural network-based estimators.<n>Key barrier to advancing these methods is the lack of labeled 3D data with class distributions and diversity tailored specifically for supervised learning.<n>This paper uses a synthetic 3D dataset to train a genus estimator network, created using a 3D convolutional transformer architecture.
  arXiv  Detail & Related papers  (2025-11-07T04:15:32Z)
• 3D Test-time Adaptation via Graph Spectral Driven Point Shift [19.664235213514743]
  Graph Spectral Domain Test-Time Adaptation (GSDTTA) is a novel approach for 3D point cloud classification.<n>It shifts adaptation to the graph spectral domain, enabling more efficient adaptation by capturing global structural properties with fewer parameters.<n> Experimental results and ablation studies on benchmark datasets demonstrate the effectiveness of GSDTTA.
  arXiv  Detail & Related papers  (2025-07-24T09:18:39Z)
• Structural Alignment Improves Graph Test-Time Adaptation [17.564393890432193]
  We introduce Test-Time Structural Alignment (TSA), a novel algorithm for Graph Test-Time Adaptation (GTTA)<n>TSA aligns graph structures during inference without accessing the source data.<n>Experiments on synthetic and real-world datasets demonstrate TSA's consistent outperformance of both non-graph TTA methods and state-of-the-art GTTA baselines.
  arXiv  Detail & Related papers  (2025-02-25T16:26:25Z)
• Just How Flexible are Neural Networks in Practice? [89.80474583606242]
  It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters. In practice, however, we only find solutions via our training procedure, including the gradient and regularizers, limiting flexibility.
  arXiv  Detail & Related papers  (2024-06-17T12:24:45Z)
• TSI-GAN: Unsupervised Time Series Anomaly Detection using Convolutional Cycle-Consistent Generative Adversarial Networks [2.4469484645516837]
  Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. This paper proposes TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically. We evaluate TSI-GAN using 250 well-curated and harder-than-usual datasets and compare with 8 state-of-the-art baseline methods.
  arXiv  Detail & Related papers  (2023-03-22T23:24:47Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns [77.34726150561087]
  We introduce four complicated missing patterns, including missing and three fiber-like missing cases according to the mode-drivenn fibers. Despite nonity of the objective function in our model, we derive the optimal solutions by integrating alternating data-mputation method of multipliers.
  arXiv  Detail & Related papers  (2022-05-19T08:37:56Z)
• Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping [116.26579152942162]
  Graph neural networks (GNNs) are processing architectures that exploit graph structural information to model representations from network data. Despite their success, GNNs suffer from sub-optimal generalization performance given limited training data. This paper proposes Topology Adaptive Edge Dropping to improve generalization performance and learn robust GNN models.
  arXiv  Detail & Related papers  (2021-06-05T13:20:36Z)
• LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification [9.571458051525768]
  This paper proposes a new network architecture, LiteDepthwiseNet, for hyperspectral image (HSI) classification. LiteDepthwiseNet decomposes standard convolution into depthwise convolution and pointwise convolution, which can achieve high classification performance with minimal parameters. Experiment results on three benchmark hyperspectral datasets show that LiteDepthwiseNet achieves state-of-the-art performance with a very small number of parameters and low computational cost.
  arXiv  Detail & Related papers  (2020-10-15T13:12:17Z)

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.