natural-language-processing-9
Relational Reasoning
3260 papers • 126 benchmarks • 313 datasets
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
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in relational-reasoning-9
Trend
Dataset
Best Model
Actions
CLUTRR (k=3)
CLUTRR (k=3)
Libraries
iUse these libraries to find relational-reasoning-9 models and implementations
3 papers 2,078
Datasets
Subtasks
No subtasks available.
Most implemented papers
Relational inductive biases, deep learning, and graph networks
P. Battaglia, O. Vinyals, Alvaro Sanchez-Gonzalez, Yujia Li, Pushmeet Kohli, Jessica B. Hamrick, V. Bapst, V. Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Çaglar Gülçehre, H. F. Song, A. J. Ballard, J. Gilmer, George E. Dahl, Ashish Vaswani, Kelsey R. Allen, C. Nash, Victoria Langston, Chris Dyer, N. Heess, Daan Wierstra, M. Botvinick, Razvan Pascanu•Sun Jun 03 2018
It is argued that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective.
