NodeJEPA：面向节点级图自监督学习的结构条件隐式预测
NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
浏览论文内容
中文总结 AI 辅助
本文提出NodeJEPA，一种节点级图自监督学习的联合嵌入预测架构，通过结构条件隐式预测避免依赖输入重构，经节点分类基准评估有效，为相关研究提供实用方案。
中文摘要 AI 辅助
图自监督学习很大程度上依赖于两类方法：一类是依赖精心设计的数据增强的对比方法，另一类是在输入空间中重构节点属性的生成方法，这两类方法都可能使表示与低层次输入统计数据纠缠，而非与关系结构关联。联合嵌入预测架构（JEPA）则通过预测隐式目标而非重构输入来学习，近期研究已将该思路应用于图级表示学习，但如何为节点级任务设计JEPA风格的目标函数、预测器应依赖哪些结构信号仍不明确。本文提出NodeJEPA，一种面向节点级图自监督学习的联合嵌入预测架构：NodeJEPA对感知结构的k跳自子图进行掩码，训练上下文编码器以预测被掩码节点的隐式表示，这些目标来自采用停止梯度的EMA更新目标编码器；结构条件预测器通过交叉注意力整合谱描述符与中心性描述符；方差、协方差和拉普拉斯谱正则化器有助于稳定嵌入几何，可选的课程学习在训练过程中逐步增加掩码难度。由于预测发生在隐式空间，NodeJEPA不依赖输入重构或手动设计的图增强。我们在标准节点分类基准上，采用线性探测和微调协议评估NodeJEPA，并对掩码、预测和正则化设计选择进行消融实验。本研究为图上的节点级JEPA风格隐式预测提供了实用方案，并明确了结构条件何时有助于表示学习，代码、配置和评估脚本已公开于此https://URL。
英文摘要
Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attributes in the input space. Both paradigms can entangle representations with low-level input statistics rather than with relational structure. Joint-embedding predictive architectures (JEPA) instead learn by predicting latent targets rather than reconstructing inputs. Recent work has explored this idea for graph-level representation learning, but how to design JEPA-style objectives for node-level tasks, and which structural signals the predictor should condition on, remains less clear. We present NodeJEPA, a joint-embedding predictive architecture for node-level graph self-supervised learning. NodeJEPA masks structure-aware k-hop ego-subgraphs and trains a context encoder to predict the latent representations of the masked nodes. These targets come from an EMA-updated target encoder with stop-gradient. A structure-conditioned predictor integrates spectral and centrality descriptors through cross-attention. Variance, covariance, and Laplacian spectral regularizers help stabilize the embedding geometry, and an optional curriculum gradually increases masking difficulty during training. Because prediction occurs in latent space, NodeJEPA does not rely on input reconstruction or hand-crafted graph augmentations. We evaluate NodeJEPA on standard node classification benchmarks under linear probing and fine-tuning protocols, and conduct ablations on masking, prediction, and regularization design choices. Our study offers a practical recipe for node-level JEPA-style latent prediction on graphs, and clarifies when structural conditioning helps representation learning. Code, configurations, and evaluation scripts are publicly available at https://github.com/OliverZ-dot/Node-Jepa.
发表机构
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
