On Improving Neurosymbolic Learning by Exploiting the Representation Space

• URL: http://arxiv.org/abs/2602.07973v1
• Date: Sun, 08 Feb 2026 13:56:47 GMT
• Title: On Improving Neurosymbolic Learning by Exploiting the Representation Space
• Authors: Aaditya Naik, Efthymia Tsamoura, Shibo Jin, Mayur Naik, Dan Roth,
• Abstract summary: We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula.<n>One challenge is that the space of label combinations can grow exponentially, making learning difficult.<n>We propose a technique that prunes this space by exploiting the intuition that instances with similar latent representations are likely to share the same label.
• Score: 54.16389421332958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the problem of learning neural classifiers in a neurosymbolic setting where the hidden gold labels of input instances must satisfy a logical formula. Learning in this setting proceeds by first computing (a subset of) the possible combinations of labels that satisfy the formula and then computing a loss using those combinations and the classifiers' scores. One challenge is that the space of label combinations can grow exponentially, making learning difficult. We propose a technique that prunes this space by exploiting the intuition that instances with similar latent representations are likely to share the same label. While this intuition has been widely used in weakly supervised learning, its application in our setting is challenging due to label dependencies imposed by logical constraints. We formulate the pruning process as an integer linear program that discards inconsistent label combinations while respecting logical structure. Our approach, CLIPPER, is orthogonal to existing training algorithms and can be seamlessly integrated with them. Across 16 benchmarks over complex neurosymbolic tasks, we demonstrate that CLIPPER boosts the performance of state-of-the-art neurosymbolic engines like Scallop, Dolphin, and ISED by up to 48%, 53%, and 8%, leading to state-of-the-art accuracies.

Related papers

• Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration [46.43084711486819]
  Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning.<n>We introduce Logic of Hypotheses (LoH), a novel language that unifies data-driven rule learning with symbolic priors and expert knowledge.
  arXiv  Detail & Related papers  (2025-09-25T22:31:43Z)
• Enhancing Symbolic Machine Learning by Subsymbolic Representations [2.4280350854512673]
  We propose to enhance symbolic machine learning schemes by giving them access to neural embeddings.<n>In experiments in three real-world domain, we show that this simple, yet effective, approach outperforms all other baseline methods in terms of the F1 score.
  arXiv  Detail & Related papers  (2025-06-17T14:26:21Z)
• Verification Learning: Make Unsupervised Neuro-Symbolic System Feasible [49.084647802326366]
  This paper introduces a novel learning paradigm, Verification Learning (VL), which transforms the label-based reasoning process in Nesy into a label-free verification process.<n>VL achieves excellent learning results solely by relying on unlabeled data and a function that verifies whether the current predictions conform to the rules.<n>Our theoretical analysis points out which tasks in Nesy systems can be completed without labels and explains why rules can replace infinite labels for some tasks, while for others the rules have no effect.
  arXiv  Detail & Related papers  (2025-03-17T08:28:58Z)
• Pseudo-labelling meets Label Smoothing for Noisy Partial Label Learning [8.387189407144403]
  We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive.<n>We focus on Partial Learning (PLL), a weakly-supervised learning paradigm where each training instance is paired with a set of candidate labels.<n>We present a framework that initially assigns pseudo-labels to images by exploiting the noisy partial labels through a weighted nearest neighbour algorithm.
  arXiv  Detail & Related papers  (2024-02-07T13:32:47Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation [85.12429517510311]
  LogicDiag is a neural-logic semi-supervised learning framework for semantic segmentation. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules.
  arXiv  Detail & Related papers  (2023-08-24T06:50:07Z)
• Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
  Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data. We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data. NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
  arXiv  Detail & Related papers  (2022-05-25T12:41:59Z)
• Learning with Holographic Reduced Representations [28.462635977110413]
  Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors. This paper revisits this approach to understand if it is viable for enabling a hybrid neural-symbolic approach to learning.
  arXiv  Detail & Related papers  (2021-09-05T19:37:34Z)
• Neural Active Learning with Performance Guarantees [37.16062387461106]
  We investigate the problem of active learning in the streaming setting in non-parametric regimes, where the labels are generated from a class of functions on which we make no assumptions whatsoever. We rely on recently proposed Neural Tangent Kernel (NTK) approximation tools to construct a suitable neural embedding that determines the feature space the algorithm operates on and the learned model computed atop.
  arXiv  Detail & Related papers  (2021-06-06T20:44:23Z)
• Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning [134.77207192945053]
  Prior methods learn the neural-symbolic models using reinforcement learning approaches. We introduce the textbfgrammar model as a textitsymbolic prior to bridge neural perception and symbolic reasoning. We propose a novel textbfback-search algorithm which mimics the top-down human-like learning procedure to propagate the error.
  arXiv  Detail & Related papers  (2020-06-11T17:42:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.