SOTAVerified

Relational Reasoning

The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.

Source: Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 221–230 of 483 papers

TitleStatusHype
Distributed Associative Memory Network with Association Reinforcing Loss—0
Interpretable Reinforcement Learning With Neural Symbolic Logic—0
Graph Networks with Spectral Message Passing—0
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive LearningCode1
Logic Tensor NetworksCode1
T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion—0
Factor Graph Molecule Network for Structure Elucidation—0
Fusing Context Into Knowledge Graph for Commonsense Question AnsweringCode1
Relational Learning for Skill Preconditions—0
Multi-choice Relational Reasoning for Machine Reading Comprehension—0
Show:102550
← PrevPage 23 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified