发表机构
Stony Brook University; TikTok; PayPal; New York University（石溪大学; TikTok（抖音海外版）; PayPal（贝宝）; 纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
HP-JEPA是一种多分辨率图联合嵌入预测的层次划分框架，通过在不同分辨率下进行潜在预测并整合表示，在多数图分类与回归基准及不同规模图上，性能优于固定分辨率的Graph-JEPA。
AI 中文摘要
图自监督学习旨在从大规模未标注图数据中学习可迁移的表示。联合嵌入预测架构（JEPAs）通过在潜在空间直接预测掩码目标，避免了显式负对构造和原始输入重建。然而，现有图JEPAs通常依赖单一预定义图划分，使学习到的表示偏向某一结构粒度，限制了其捕获不同图尺度互补模式的能力。为解决此局限，我们提出HP-JEPA，一种用于多分辨率图联合嵌入预测的层次划分框架。HP-JEPA将每个图组织为从粗到细划分分辨率的有序库，使用在线编码器、指数移动平均目标编码器和潜在预测器，在每个分辨率下分别执行上下文-目标潜在预测。随后，通过拼接或特定任务的分辨率加权，整合得到的特定分辨率图表示，使下游模型能结合互补的局部、区域和全局结构信息。在7个图分类基准和1个图回归基准上的实验表明，HP-JEPA在8项任务中的6项上优于固定分辨率的Graph-JEPA基线，在多数评估基准上优于Graph-JEPA。按图规模分层的分析进一步显示，HP-JEPA在3个代表性数据集的多数评估图规模四分位数上，比Graph-JEPA取得更高的准确率。这些结果凸显了层次多分辨率划分在可迁移图表示学习中的有效性。
英文摘要
Graph self-supervised learning aims to learn transferable representations from large-scale unlabeled graph data. Joint-embedding predictive architectures (JEPAs) avoid explicit negative-pair construction and raw-input reconstruction by predicting masked targets directly in latent space. However, existing graph JEPAs typically rely on a single predefined graph partition, biasing the learned representations toward one structural granularity and limiting their ability to capture complementary patterns at different graph scales. To address this limitation, we propose HP-JEPA, a hierarchical partitioning framework for multi-resolution graph joint-embedding prediction. HP-JEPA organizes each graph into an ordered bank of coarse-to-fine partition resolutions and performs context-target latent prediction separately at each resolution using an online encoder, an exponential-moving-average target encoder, and a latent predictor. The resulting resolution-specific graph representations are subsequently integrated through concatenation or task-specific resolution weighting, allowing downstream models to combine complementary local, regional, and global structural information. Experiments on seven graph classification benchmarks and one graph regression benchmark show that HP-JEPA outperforms the fixed-resolution Graph-JEPA baseline on 6 of 8 tasks, improving upon Graph-JEPA on most evaluated benchmarks. Size-stratified analyses further show that HP-JEPA achieves higher accuracy than Graph-JEPA in most evaluated graph-size quartiles on three representative datasets. These results highlight the effectiveness of hierarchical multi-resolution partitioning for transferable graph representation learning.
Comments15 pages, 4 figures, 5 tables
