Add Attract-Repel link prediction model

[tommyly201]

Add Attract-Repel Embeddings for Link Prediction

This PR adds an implementation of Attract-Repel embeddings from the paper "Pseudo-Euclidean Attract-Repel Embeddings for Undirected Graphs" by Peysakhovich et al.

Overview

Attract-Repel embeddings address a fundamental limitation in traditional graph embeddings: their inability to effectively represent non-transitive relationships. The method splits node representations into two components:

• Attract component: nodes with similar attract vectors are likely to connect
• Repel component: nodes with similar repel vectors are unlikely to connect

Link prediction scores are calculated as: attract_dot_product - repel_dot_product

Implementation

• Added ARLinkPredictor class that implements the core functionality
• Added thorough tests to validate the implementation
• The implementation is minimal and focused on the core concept

Benefits

• Improves link prediction performance on graphs with non-transitive relationships
• Requires minimal architectural changes to existing models
• Provides useful information about graph structure through R-fraction analysis
• Example PR #10107