Research map / Graph learning / Knowledge and temporal graphs
CFGNN: Cross Flow Graph Neural Networks for Question Answering on Complex Tables
Xuanyu Zhang
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 child-child (sibling RNN) flow (ablation) | CFGNN · Spider dev | exact match accuracy: 42.5% -> 48.7% | Improved |
| add parent-child attention flow (ablation) | CFGNN · Spider dev | exact match accuracy: 44.5% -> 48.7% | Improved |
| add reasoning flow between layers (ablation) | CFGNN · Spider dev | exact match accuracy: 44.8% -> 48.7% | Improved |
| add graph structure (ablation) | CFGNN · Spider dev | exact match accuracy: 42.7% -> 48.7% | Improved |
| use CFGNN instead of plain GNN (ablation) | CFGNN · Spider dev | exact match accuracy: 37.9% -> 48.7% | Improved |
| use CFGNN instead of GAT (ablation) | CFGNN · Spider dev | exact match accuracy: 44.4% -> 48.7% | Improved |
| use CFGNN instead of GGNN (ablation) | CFGNN · Spider dev | exact match accuracy: 40.3% -> 48.7% | Improved |
| use CFGNN instead of GAT (ablation) | CFGNN · Spider dev, GROUP BY | component F1: 73.2% -> 71.5% | Mixed |
| add child-child flow (ablation) | CFGNN · Spider dev, WHERE | component F1: 46.5% -> 52.5% | Improved |
| add reasoning flow (ablation) | CFGNN · Spider dev, ORDER BY | component F1: 65.8% -> 76.6% | Improved |
| use CFGNN instead of Schema GNN | Schema GNN with hierarchical encoding · Spider dev | exact match accuracy: 40.9% -> 48.7% | Improved |
Later papers that compared with this method
3 later accepted papers report CF-GNN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Quantile-Free Uncertainty Quantification in Graph Neural Networks (ICML 2026 · better on 3 of 3 shared results)
- Enhancing Trustworthiness of Graph Neural Networks with Rank-Based Conformal Training (AAAI 2025 · better on 1 of 9 shared results)
- Similarity-Navigated Conformal Prediction for Graph Neural Networks (NeurIPS 2024 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GNN is a Counter? Revisiting GNN for Question Answering (ICLR 2022 · similarity 0.86)
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering (NeurIPS 2024 · similarity 0.85)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.84)
- Charting the Design Space of Neural Graph Representations for Subgraph Matching (ICLR 2025 · similarity 0.84)
- Question Calibration and Multi-Hop Modeling for Temporal Question Answering (AAAI 2024 · similarity 0.83)
- KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering (NeurIPS 2026 · similarity 0.83)
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.
