AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

GaussianPath:A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning

Guojia Wan, Bo Du

AAAI 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 49 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
Add Bayesian representation and Q-function modeling (ablation)Q-path · FB15K237MRR: 0.247 -> 0.423Improved
Add Bayesian representation and Q-function modeling (ablation)Q-path · WN18RRMRR: 0.336 -> 0.458Improved
Add Bayesian representation and Q-function modeling (ablation)Q-path · NELL995MRR: 0.645 -> 0.748Improved
Add Thompson sampling for action execution (ablation)GaussianPath without Thompson Sampling · FB15K237MRR: 0.338 -> 0.423Improved
Add Thompson sampling for action execution (ablation)GaussianPath without Thompson Sampling · WN18RRMRR: 0.435 -> 0.458Improved
Add Thompson sampling for action execution (ablation)GaussianPath without Thompson Sampling · NELL995MRR: 0.693 -> 0.748Improved
Initialize entity/relation Gaussian priors with pre-trained KG2E embeddingsGaussianPath · NELL995MRR: 0.748 -> 0.756No clear effect
Use Bayesian uncertainty and Thompson sampling instead of one-point RL representationsRL-based multi-hop reasoning · NELL995MRR: 0.725 -> 0.748Improved
Use GaussianPath rather than Multihop-KGKnowledge graph reasoning · KinshipMRR: 0.865 -> 0.874Improved
Use GaussianPath rather than Multihop-KGKnowledge graph reasoning · UMLSMRR: 0.940 -> 0.884Hurt
Use GaussianPath rather than MINERVARelation link prediction · NELL995MAP: 88.4 -> 91.3Improved
Use GaussianPath rather than MINERVARelation link prediction · FB15K-237MAP: 42.3 -> 55.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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