谱反转：抵消图提示中的奇异值偏差
Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting
AI总结：
针对预训练图神经网络的谱偏差问题，提出谱反转提示（SRP），通过可学习软阈值掩码和零空间增强模块重新平衡谱贡献，以极少的参数在多个基准上实现最先进的图适配性能。
AI中文摘要：
通过自监督学习预训练图神经网络（GNNs）已成为主导范式，但高效适配冻结编码器仍是一个挑战。图提示提供了一种参数高效的微调替代方案，但现有方法大多将预训练模型视为不透明的特征提取器，忽略其内部谱结构。在本工作中，我们识别了预训练GNNs中的一个系统性现象，称之为谱偏差：预训练期间的优化不成比例地将表示与对应大奇异值的方向对齐，导致低能量方向未被充分探索。我们表明，这些未被充分利用的方向可以编码互补信息，有利于下游适配，尤其是在分布偏移下。为利用这一见解，我们提出谱反转提示（SRP），一种重新平衡冻结GNN编码器谱贡献的提示框架。SRP在谱域应用一个可学习的软阈值掩码，以降低主导方向的权重，同时放大较弱方向。此外，SRP包含一个零空间增强模块，用于捕获冻结编码器下激活最小的方向上的变化。跨多个基准的大量实验表明，SRP以极少的额外参数实现了最先进的性能，凸显了重新加权谱分量是参数高效图适配的一种有原则且有效的策略。
英文摘要：
Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains a challenge. Graph prompting offers a parameter-efficient alternative to fine-tuning, but existing methods largely treat pre-trained models as opaque feature extractors, ignoring their internal spectral structure. In this work, we identify a systematic phenomenon in pre-trained GNNs, which we term spectral bias: optimization during pre-training disproportionately aligns representations with directions associated with large singular values, leaving low-energy directions under-explored. We show that these underutilized directions can encode complementary information that is beneficial for downstream adaptation, especially under distribution shift. To leverage this insight, we propose Spectral Reverse Prompt (SRP), a prompting framework that rebalances the spectral contributions of frozen GNN encoders. SRP applies a learnable soft-thresholding mask in the spectral domain to down-weight dominant directions while amplifying weaker ones. In addition, SRP incorporates a null-space augmentation module that captures variation in directions with minimal activation under the frozen encoder. Extensive experiments across multiple benchmarks demonstrate that SRP achieves state-of-the-art performance with minimal additional parameters, highlighting that reweighting spectral components is a principled and effective strategy for parameter-efficient graph adaptation.
