arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.09056cs.AI
收藏

一种面向序列图推理的上下文增强框架

A Context-Enhanced Framework for Sequential Graph Reasoning

East China Normal University(华东师范大学)

Shuo Shi, Chao Peng, Chenyang Xu, Zhengfeng Yang

AI总结:

针对序列图推理中同时处理序列与图结构信息的难点,提出上下文增强框架,利用多步历史结果聚合增强推理,在CLRS基准多数数据集上达SOTA。

摘要:

本文研究图结构数据上的序列推理任务,该任务是自动数学问题求解、神经图算法学习等多个热门领域的基础任务,受到大量研究关注。在此类任务中同时管理序列信息与图结构信息是一项显著的挑战。近年来,文献中已有多种神经架构被提出以解决这一问题。在本研究中,我们对现有架构进行归纳,提出了一种上下文增强框架。其核心创新点在于,每一步的推理不仅依赖前一步的结果,还会利用更多历史结果的信息聚合。这一思路源于我们的观察:在序列图推理中,与传统的序列到序列(seq-to-seq)任务相比,各步骤的结果之间存在更强的内在联系。我们证明该框架能够有效与现有方法结合,提升其推理能力。我们在具有挑战性的CLRS Reasoning Benchmark(CLRS推理基准)上开展了实证评估,结果表明所提出的框架显著提升了现有架构的性能,在该基准内的绝大多数数据集上取得了当前最优(state-of-the-art)结果。

英文摘要:

The paper studies sequential reasoning over graph-structured data, which stands as a fundamental task in various trending fields like automated math problem solving and neural graph algorithm learning, attracting a lot of research interest. Simultaneously managing both sequential and graph-structured information in such tasks presents a notable challenge. Over recent years, many neural architectures in the literature have emerged to tackle the issue. In this work, we generalize the existing architectures and propose a context-enhanced framework. The crucial innovation is that the reasoning of each step does not only rely on the outcome of the preceding step but also leverages the aggregation of information from more historical outcomes. The idea stems from our observation that in sequential graph reasoning, each step's outcome has a much stronger inner connection with each other compared to traditional seq-to-seq tasks. We show that the framework can effectively integrate with the existing methods, enhancing their reasoning abilities. Empirical evaluations are conducted on the challenging CLRS Reasoning Benchmark, and the results demonstrate that the proposed framework significantly improves the performance of existing architectures, yielding state-of-the-art results across the majority of the datasets within the benchmark.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑