Predict, Cluster, Refine: A Joint Embedding Predictive Self-Supervised Framework for Graph Representation Learning

TL;DR

This paper introduces a novel self-supervised graph learning framework that avoids contrastive methods, reduces computational costs, and improves node discrimination by combining joint embedding prediction with GMM-based pseudo-labels.

Contribution

It proposes a non-contrastive, joint embedding predictive framework with semantic-aware pseudo-labeling, advancing graph SSL efficiency and effectiveness.

Findings

Outperforms state-of-the-art methods on benchmark tasks.

Eliminates the need for contrastive loss and complex decoders.

Enhances node discriminability through GMM-based pseudo-labels.

Abstract

Graph representation learning has emerged as a cornerstone for tasks like node classification and link prediction, yet prevailing self-supervised learning (SSL) methods face challenges such as computational inefficiency, reliance on contrastive objectives, and representation collapse. Existing approaches often depend on feature reconstruction, negative sampling, or complex decoders, which introduce training overhead and hinder generalization. Further, current techniques which address such limitations fail to account for the contribution of node embeddings to a certain prediction in the absence of labeled nodes. To address these limitations, we propose a novel joint embedding predictive framework for graph SSL that eliminates contrastive objectives and negative sampling while preserving semantic and structural information. Additionally, we introduce a semantic-aware objective term that incorporates pseudo-labels derived from Gaussian Mixture Models (GMMs), enhancing node discriminability by evaluating latent feature contributions. Extensive experiments demonstrate that our framework outperforms state-of-the-art graph SSL methods across benchmarks, achieving superior performance without contrastive loss or complex decoders. Key innovations include (1) a non-contrastive, view-invariant joint embedding predictive architecture, (2) Leveraging single context and multiple targets relationship between subgraphs, and (3) GMM-based pseudo-label scoring to capture semantic contributions. This work advances graph SSL by offering a computationally efficient, collapse-resistant paradigm that bridges spatial and semantic graph features for downstream tasks. The code for our paper can be found at https://github.com/Deceptrax123/JPEB-GSSL