T3R通过梯度旋转实现图神经网络深层测试时自适应，无需标注数据。
T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
- 利用多旋转矩阵增强目标与辅助任务的关联性
- 在回归任务上降低MAE 0.172点，在分类任务上提升超9.37%
- 适合无标签数据场景下的图模型实时优化
部署于真实系统的图神经网络通常采用固定权重，导致分布偏移下性能下降。传统微调需标注数据，成本高且不现实。测试时训练（TTT）可利用无标签测试数据调整权重，但通常仅限浅层更新。本文提出T3R，通过多旋转向量（Rotograd matrices）增强目标任务与辅助任务间的任务亲和性，进而引入旋转技术，利用这些矩阵重构自监督信号生成目标任务的代理梯度，实现几乎全网络范围的深度适配。实验表明，T3R在回归数据集上相比标准推理降低MAE 0.172点，在跨域OGB分类基准上相对未适配模型提升至少9.37%。结果验证了在无法进行传统微调或重训练场景中，构建图系统自适应流水线的可行性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。