EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification
Quick Answer
EditSR introduces a two-layer framework that enhances neural symbolic regression by integrating a pre-trained edit-based Rectifier, significantly improving symbolic structure recovery in complex expressions while minimizing error accumulation.
Quick Take
EditSR introduces a two-layer framework that enhances neural symbolic regression by integrating a pre-trained edit-based Rectifier, significantly improving symbolic structure recovery in complex expressions while minimizing error accumulation. Extensive experiments demonstrate substantial performance gains with limited additional costs.
Key Points
- EditSR combines neural symbolic regression with an edit-based Rectifier for improved efficiency.
- The rectification process is formulated as a step-by-step state-transition chain.
- Each edit action is restricted to ensure syntactic validity of expressions.
- Extensive experiments show substantial improvements in complex expression recovery.
- EditSR reduces error accumulation risk by allowing subsequent edits to rectify earlier mistakes.
Article Content
From source RSS / original summaryarXiv:2606. 07915v1 Announce Type: new Abstract: Neural symbolic regression models improve inference efficiency by shifting structural search to pretraining, but their one-pass autoregressive decoding is prone to error accumulation, which may lead to generating structurally incorrect expressions, especially in complex expression generation scenarios.
Existing rectification strategies can alleviate this issue, but they often depend on restarting global search, thereby weakening the efficiency advantage of neural models, and remain susceptible to error accumulation. In this paper, we propose EditSR, a two-layer framework that combines a neural symbolic regression model in the first layer with an edit-based Rectifier in the second layer to achieve efficient prediction and post-hoc rectification.
Instead of restarting the global search, we maintain rectification efficiency by pretraining the Rectifier. Specifically, we formulate the rectification process as a step-by-step state-transition chain starting from an incorrect expression, and develop a state-transition algorithm to construct supervised rectification chains for training the Rectifier.
To ensure syntactic validity throughout rectification, each edit action is restricted to a syntactically valid space so that every edited expression remains parseable. In addition, because each edit decision is conditioned on the current state rather than the history, the Rectifier allows errors made in earlier steps to be rectified by subsequent edits, thereby reducing the risk of error accumulation.
Extensive experiments and ablation studies show that EditSR substantially improves symbolic structure recovery with limited extra cost, with more pronounced gains on complex expressions, where one-pass autoregressive decoding is more susceptible to error accumulation.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective
This paper addresses the sim-to-real gap for foundation model agents by framing it within a Markov Decision Process (MDP) structure. It advocates for established solutions like domain randomization to enhance agent robustness, aiming to create standardized benchmarks for reliable real-world applications.