Research map / Large language models / Agents, code and math
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
Jiafu Huang, Chao Peng, Chenyang Xu, Zhengfeng Yang, Kecheng Cai, Chenhao Zhang, Yi Wang, Yiwei Gong, Wanqin Zhou, Irene Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add auxiliary reconstruction loss and GNN encoder (ReNAR) | Triplet-GMPNN · CLRS overall average | F1 accuracy (CLRS): 83.63% -> 87.11% | Improved |
| add hint-level masking to reconstruction (M-ReNAR) (ablation) | ReNAR · CLRS overall average | F1 accuracy (CLRS): 87.11% -> 88.41% | Improved |
| add reconstruction framework | Triplet-GMPNN · CLRS Graphs | F1 accuracy (CLRS): 88.80% -> 94.74% | Improved |
| add reconstruction framework | Triplet-GMPNN · CLRS DFS | F1 accuracy (CLRS): around 60% -> nearly 100% | Improved |
| add hint-level masking (ablation) | ReNAR · CLRS Strings | F1 accuracy (CLRS): 62.70% -> 74.72% | Improved |
| add hint-level masking (ablation) | ReNAR · CLRS Sorting | F1 accuracy (CLRS): 92.13% -> 90.51% | Hurt |
| replace GNN+gated encoder with linear encoder (ReNAR-linear) (ablation) | ReNAR · CLRS (Triplet-GMPNN) | F1 accuracy (CLRS) | Hurt |
| vary masking ratio beta in {0.1,0.3,0.5,0.7,0.9} (ablation) | M-ReNAR · CLRS categories | F1 accuracy (CLRS) | Mixed |
| vary reconstruction weight lambda in {0.0,0.05,0.1,0.15,0.20} (ablation) | ReNAR · CLRS categories | F1 accuracy (CLRS) | Mixed |
| add ReNAR to other processors (Triplet-PGN, Triplet-MPNN) | Triplet-PGN / Triplet-MPNN · CLRS overall average | F1 accuracy (CLRS) | Improved |
| add reconstruction framework | Triplet-GMPNN · CLRS Search | F1 accuracy (CLRS): 61.14% -> 58.89% | Hurt |
Closest papers by meaning
- Neural Algorithmic Reasoning Without Intermediate Supervision (NeurIPS 2023 · similarity 0.88)
- Primal-Dual Neural Algorithmic Reasoning (ICML 2025 · similarity 0.87)
- Discrete Neural Algorithmic Reasoning (ICML 2025 · similarity 0.87)
- On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods (ICLR 2024 · similarity 0.86)
- Open-Book Neural Algorithmic Reasoning (NeurIPS 2024 · similarity 0.85)
- Deep Equilibrium Algorithmic Reasoning (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
