# Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations

Source: [Multi-hop Relational Contrastive Learning: Extending Spatial Contrastive Pre-training Beyond Pairwise Relations](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1b3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-20T05:00:05.687Z

Authors: Sheikh Tanvir Ahmed, Md. Tanvir Raihan

Published: 2026-05-15T05:33:18.000Z

## Abstract

Understanding how objects relate to each other in space is fundamental to scene understanding, yet most contrastive pre-training approaches only model pairwise relationships, leaving richer compositional and multi-hop interactions largely unexplored. We introduce Multi-Hop Relational Contrastive Learning (MRCL), a framework that extends spatial contrastive learning to graph-structured scene representations. By tracing k-hop paths through scene graphs built from detected objects, MRCL captures implicit spatial dependencies that go well beyond what direct object pairs can express. We define a multi-level contrastive objective spanning nodes, edges, and multi-hop paths, encouraging embeddings that remain stable across object semantics while staying responsive to spatial layout. On a GQA subset, MRCL produces spatially-aware representations that improve content-based graph retrieval (NDCG@5 = 0.748) and consistently benefit downstream tasks, including spatial relationship recognition and graph-based question answering. Together, these results suggest that multi-hop relational supervision offers substantially richer structural guidance than pairwise-only methods, leading to visual representations that are more robust, compositional, and geometry-aware.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Content-Based Graph Retrieval on GQA subset](<https://www.sota2.com/research/sota/content-based-graph-retrieval-on-gqa-subset.md>): Content-Based Graph Retrieval; GQA subset; NDCG@5: 74.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.16456>)

[PDF](<https://arxiv.org/pdf/2605.16456.pdf>)
