Object-Centric Case-Based Reasoning via Argumentation

2025-09-30

AI Summary

This paper addresses the disconnection between neural learning and symbolic reasoning in image classification by proposing Slot Attention Argumentation for Case-Based Reasoning (SAA-CBR), a neuro-symbolic hybrid framework. Methodologically, it introduces Slot Attention for object-level feature disentanglement—the first such application—and integrates abstract argumentation: a counting-based partial order relation models case importance; a representative-sample pruning strategy compresses the case base; and a one-vs-rest multi-classifier coupled with a support-based bidirectional argumentation model enables interpretable inference. Evaluated on CLEVR-Hans, SAA-CBR achieves significant improvements in classification accuracy and robustness. Results empirically validate the synergistic effectiveness of object-aware neural representations and structured symbolic argumentation, establishing a novel paradigm for explainable and generalizable case-based reasoning.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Argumentation
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

We introduce Slot Attention Argumentation for Case-Based Reasoning (SAA-CBR), a novel neuro-symbolic pipeline for image classification that integrates object-centric learning via a neural Slot Attention (SA) component with symbolic reasoning conducted by Abstract Argumentation for Case-Based Reasoning (AA-CBR). We explore novel integrations of AA-CBR with the neural component, including feature combination strategies, casebase reduction via representative samples, novel count-based partial orders, a One-Vs-Rest strategy for extending AA-CBR to multi-class classification, and an application of Supported AA-CBR, a bipolar variant of AA-CBR. We demonstrate that SAA-CBR is an effective classifier on the CLEVR-Hans datasets, showing competitive performance against baseline models.

Problem

• Integrating object-centric learning with symbolic reasoning for image classification
• Developing novel neuro-symbolic pipeline combining Slot Attention and Argumentation
• Extending Case-Based Reasoning to multi-class classification using bipolar variants

Innovation

• Slot Attention Argumentation for Case-Based Reasoning pipeline
• Integrates object-centric learning with symbolic reasoning
• Uses novel AA-CBR integrations for multi-class classification