Pith. sign in

REVIEW 3 cited by

The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.04212 v1 pith:7THDV3KN submitted 2020-07-08 cs.LG cs.AIcs.LOstat.ML

Yuhuai Wu , Honghua Dong , Roger Grosse , Jimmy Ba This is my paper · ORCID
classification cs.LGcs.AIcs.LOstat.ML
keywords compositionalanalogicalattributeslearnerobjectsreasoningrelationshipsscattering
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), and their relationships (e.g., progression, union). We also find that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A single conditional generative model, trained only on RPM-style puzzles, can be repurposed via probability scoring to solve odd-one-out, analogy, and categorization tasks, with modest zero-shot transfer.

  2. Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecture

    cs.AI 2025-01 conditional novelty 5.0 of 10

    Rel-SAR, a vector-symbolic architecture with numeric, circular, and boolean vectors, improves accuracy on Raven's Progressive Matrices, particularly for position-based rules.

  3. Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning

    cs.AI 2024-12 conditional novelty 5.0 of 10

    With oracle text attributes, GPT-4 and Llama-3 solve Raven matrices but their arithmetic-rule accuracy drops below 10% on larger grids and value ranges, while the neuro-symbolic ARLC model stays accurate.

Pith tools