AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning

Aaron Chan, Jiashu Xu, Boyuan Long, Soumya Sanyal, Tanishq Gupta, Xiang Ren

NeurIPS 2021 · Graph learning › Knowledge and temporal graphs · approach: Temporal knowledge graph reasoning · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
use ensemble-based coarse explanations instead of Grad (ablation)SalKG-Coarse · CSQA dev, BERT+MHGRNaccuracy (%): 56.84 -> 59.49Improved
use ensemble-based coarse explanations instead of Occl (ablation)SalKG-Coarse · CSQA dev, BERT+MHGRNaccuracy (%): 57.60 -> 59.49Improved
soft attention pruning instead of random hard pruning (ablation)SalKG-Fine · CSQA dev, BERT+MHGRNaccuracy (%): 50.61 -> 57.28Improved
soft attention pruning instead of heuristic hard pruning (ablation)SalKG-Fine · CSQA dev, BERT+MHGRNaccuracy (%): 50.72 -> 57.28Improved
train saliency with KL divergence instead of BCE loss (ablation)SalKG-Fine · CSQA dev, BERT+MHGRNaccuracy (%): 50.83 -> 57.28Improved
use Occl instead of Grad for fine explanations (ablation)SalKG-Fine · CSQA dev, BERT+MHGRNaccuracy (%): 56.05 -> 57.28Improved
use Occl instead of Grad for fine explanations (ablation)SalKG-Hybrid · CSQA dev, BERT+MHGRNaccuracy (%): 60.17 -> 59.92Hurt
add SalKG-Coarse to KG modelKG model · CSQA test, BERT+RNaccuracy (%): 56.46 -> 57.50Improved
add SalKG-Hybrid to KG modelKG model · CSQA test, RoBERTa+RNaccuracy (%): 71.37 -> 74.13Improved
add SalKG-Coarse to KG modelKG model · OBQA test, RoBERTa+RNaccuracy (%): 66.80 -> 71.29Improved
add SalKG-Fine to KG modelKG model · OBQA test, RoBERTa+PathGenaccuracy (%): 68.40 -> 51.51Hurt
add SalKG-Hybrid to KG modelKG model · CODAH test, RoBERTa+MHGRNaccuracy (%): 84.02 -> 85.17Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy