A Context-Enhanced Framework for Sequential Graph Reasoning
This work addresses a fundamental problem in fields like automated math solving and neural graph algorithm learning by enhancing existing methods for sequential graph reasoning, though it is incremental as it builds on prior architectures.
The paper tackles the challenge of sequential reasoning over graph-structured data by proposing a context-enhanced framework that aggregates historical outcomes to improve each reasoning step, achieving state-of-the-art results on the CLRS Reasoning Benchmark across most datasets.
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.