Instance Discrimination for Link Prediction
Summary
This paper adapts instance discrimination self-supervised learning to link prediction in graphs, proposing new models L-GRACE and L-BGRL that operate on link representations and improve performance especially on unattributed graphs.
View Cached Full Text
Cached at: 05/21/26, 06:21 AM
# Instance Discrimination for Link Prediction Source: [https://arxiv.org/abs/2605.20257](https://arxiv.org/abs/2605.20257) Authors:[Valentin Cuzin\-Rambaud](https://arxiv.org/search/cs?searchtype=author&query=Cuzin-Rambaud,+V)\(SyCoSMA, DM2L, LIRIS, UCBL\),[Mathieu Lefort](https://arxiv.org/search/cs?searchtype=author&query=Lefort,+M)\(LIRIS, SyCoSMA, IRISA, MALT, UR\),[Rémy Cazabet](https://arxiv.org/search/cs?searchtype=author&query=Cazabet,+R)\(DM2L, LIRIS, UCBL, IXXI\) [View PDF](https://arxiv.org/pdf/2605.20257) > Abstract:Recently, instance discrimination models have emerged as a major solution for self\-supervised learning\. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification\. However, fewer contributions have tackled the link prediction task\. In this contribution, we propose to adapt existing methods to this context\. We first provide a rigorous evaluation of existing self\-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process \(like in computer vision\)\. We then propose a new structural augmentation based on the community structure that is relevant for link prediction\. Our main contribution introduces two new models, L\-GRACE and L\-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self\-supervised contexts\. ## Submission history From: Valentin Cuzin\-Rambaud \[[view email](https://arxiv.org/show-email/0996fe63/2605.20257)\] \[via CCSD proxy\] **\[v1\]**Mon, 18 May 2026 13:27:41 UTC \(350 KB\)
Similar Articles
A Unified Perspective for Learning Graph Representations Across Multi-Level Abstractions
This paper proposes a unified contrastive framework for learning graph representations across multiple abstraction levels (node, proximity, cluster, graph) with a parameter-free self-weighting mechanism that adaptively assigns weights to similarity scores, outperforming state-of-the-art on downstream tasks like classification, clustering, and link prediction.
Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks
This paper proposes a modular temporal enhancement framework for signed graph neural networks that integrates historical context via a Historical Context Integration Module (HCIM) with LSTM and multi-head temporal attention, achieving consistent improvements on real-world temporal signed networks for dynamic link prediction.
Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
The paper introduces a novel task of fact generation for hyper-relational knowledge graphs (HKGs) and proposes KREPE, a generative representation learning method using masked discrete diffusion that unifies link prediction and fact generation, achieving state-of-the-art performance.
Path-Based Gradient Boosting for Graph-Level Prediction
This paper introduces PathBoost, a gradient tree boosting method for graph-level prediction that uses path-based features to compete with graph neural networks while offering better interpretability.
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
This paper introduces Transductive Sharpening (TS), a loss-level modification for semi-supervised node classification that minimizes prediction entropy on unlabeled nodes while counterbalancing on labeled nodes, achieving consistent performance improvements without architectural changes.