A Context-Enhanced Framework for Sequential Graph Reasoning

Authors: Shuo Shi, Chao Peng, Chenyang Xu, Zhengfeng Yang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia Shuo Shi , Chao Peng , Chenyang Xu and Zhengfeng Yang Shanghai Key Laboratory of Trustworthy Computing, Software Engineering Institute, East China Normal University, Shanghai, China 51255902122@stu.ecnu.edu.cn, {cpeng, cyxu, zfyang}@sei.ecnu.edu.cn
Pseudocode No The paper provides mathematical formulations and model structures but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/Ghost-st/CEF.
Open Datasets Yes We use the CLRS Algorithmic Reasoning Benchmark [Velickovic et al., 2022], a proven benchmark that offers a unified evaluation (micro-F1 score) for assessing the (seq-graph) reasoning capabilities of neural networks.
Dataset Splits No The paper refers to the CLRS Algorithmic Reasoning Benchmark but does not explicitly provide specific details on how the dataset was split into training, validation, and test sets within the paper itself (e.g., percentages or sample counts for each split).
Hardware Specification Yes The experiments are conducted on a machine equipped with an i7-13700K CPU and an RTX 4090 GPU.
Software Dependencies No The paper mentions using the Adam optimizer but does not specify version numbers for any software libraries, frameworks, or programming languages used (e.g., Python, PyTorch versions).
Experiment Setup Yes Specifically, for CEF-GMPNN, we set the batch size to 32 and the network is trained for 10,000 steps by Adam optimizer with a learning rate of 0.001; while for CEF-RT, we set the batch size to 4 and the network is trained for 10,000 steps by Adam optimizer with a learning rate of 0.00025.