Cognitive Graph for Understanding, Reasoning, and Decision
|
|
Jie Tang
Department of Computer Science
Tsinghua University
|
Abstract
We propose a novel CognitiveGraph framework for learning with knowledge graphs.
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently.
The proposed CognitiveGraph framework is founded on the dual process theory in cognitive science.
The framework gradually builds a cognitive graph in an iterative process by coordinating an implicit extraction module (System 1) and an explicit reasoning module (System 2).
While giving accurate answers, our framework further provides explainable reasoning paths.
Specifically, our implementation based on BERT and graph neural network (GNN) efficiently handles graph with tens of millions of nodes.
The framework has many applications.
For example, for multi-hop reasoning-based QA (e.g., HotpotQA), it achieves a winning joint F1 score of 34.9 on the leaderboard,
compared to 23.6 of the best competitor.
Biography
Jie Tang is a Professor and the Associate Chair of the Department of Computer Science at Tsinghua University.
His interests include artificial intelligence, data mining, social networks, and machine learning.
He served as PC Co-Chair of WWW'21, CIKM'16, WSDM'15, Associate General Chair of KDD'18, EiC of IEEE Transactions on Big Data and AI Open Journal.
He leads the project AMiner.org, an AI-enabled research network analysis system, which has attracted more than 20 million users from 220 countries/regions in the world.
He was honored with the SIGKDD Test-of-Time Award, the UK Royal Society-Newton Advanced Fellowship Award, NSFC for Distinguished Young Scholar, and KDD'18 Service Award.
|
|
|
