Self-supervised Relational Reasoning For Representation Learning

Abstract

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Training a relation head to discriminate how entities relate to themselves (intra-reasoning) and other entities (inter-reasoning), results in rich and descriptive representations in the underlying neural network backbone, which can be used in downstream tasks such as classification and image retrieval. We evaluate the proposed method following a rigorous experimental procedure, using standard datasets, protocols, and backbones. Self-supervised relational reasoning outperforms the best competitor in all conditions by an average 14% in accuracy, and the most rec

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypatacchiola2020self

Related papers

• Learning To Learn In A Semi-supervised Fashion (2020)2.26
• Reasoning-augmented Representations For Multimodal Retrieval (2026)0.00
• Laser: Internalizing Explicit Reasoning Into Latent Space For Dense Retrieval (2026)0.00
• Relation Extraction As Open-book Examination: Retrieval-enhanced Prompt Tuning (2022)16.08
• Domain Adaptation For Dense Retrieval Through Self-supervision By Pseudo-relevance Labeling (2022)0.00
• Rar-b: Reasoning As Retrieval Benchmark (2024)2.68
• Reasoning Guided Embeddings: Leveraging MLLM Reasoning For Improved Multimodal Retrieval (2025)0.00
• Multimodal Representation Learning Conditioned On Semantic Relations (2025)0.00