SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.10128 · ICML · 2022

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

Jian Tang, Zhaocheng Zhu, Zuobai Zhang, Mikhail Galkin

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
DeepGraphLearning/GNN-QE canonical 1 of 4
FunctionStatusWhere it lives
computation_graph_layout Ran DeepGraphLearning/GNN-QE/script/visualize.py
code served (permissive licence) · get_code("6b999fe6d54461d0")
detect_variables Not yet run DeepGraphLearning/GNN-QE/gnnqe/util.py
code served (permissive licence) · get_code("eab8b6a6ced6d93e")
get_root_logger Not yet run DeepGraphLearning/GNN-QE/gnnqe/util.py
code served (permissive licence) · get_code("70a68fd646c6e4a7")
get_topk_prediction Not yet run DeepGraphLearning/GNN-QE/script/visualize.py
code served (permissive licence) · get_code("0fdf31f60a2c67ea")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning. Traditional symbolic methods traverse a complete knowledge graph to extract the answers, which provides good interpretation for each step. Recent neural methods learn geometric embeddings for complex queries. These methods can generalize to incomplete knowledge graphs, but their reasoning process is hard to interpret. In this paper, we propose Graph Neural Network Query Executor (GNN-QE), a neural-symbolic model that enjoys the advantages of both worlds. GNN-QE decomposes a complex FOL query into relation projections and logical operations over fuzzy sets, which provides interpretability for intermediate variables. To reason about the missing links, GNN-QE adapts a graph neural network from knowledge graph completion to execute the relation projections, and models the logical operations with product fuzzy logic. Experiments on 3 datasets show that GNN-QE significantly improves over previous state-ofthe-art models in answering FOL queries. Meanwhile, GNN-QE can predict the number of answers without explicit supervision, and provide visualizations for intermediate variables. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.10128")
get_code_for_paper("2205.10128")
have("2205.10128")

Connect an agent — have() is free.