Pith. sign in

REVIEW 2 cited by

Neuro-Symbolic Forward Reasoning

Not yet reviewed by Pith; the record is open.

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 2110.09383 v1 pith:3ZOS4QPI submitted 2021-10-18 cs.AI cs.CVcs.LG

Neuro-Symbolic Forward Reasoning

classification cs.AI cs.CVcs.LG
keywords reasoningdifferentiableforward-chaininglearningobject-centricapproachdeepinference
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Reasoning is an essential part of human intelligence and thus has been a long-standing goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

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

  1. Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach

    cs.LG 2026-05 conditional novelty 6.0

    GRAIL is a gaze-guided neurosymbolic imitation learning method that reweights relational atoms with predicted human gaze and learns interpretable rules outperforming neural behavioral cloning on Asterix and Seaquest.

  2. Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach

    cs.LG 2026-05 unverdicted novelty 5.0

    A neurosymbolic imitation learning approach uses privileged gaze data during training to handle high-dimensional inputs while achieving better generalization than pure neural or symbolic methods.