Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport

by   Zihao Wang, et al.
Tsinghua University
The Hong Kong University of Science and Technology

Answering complex queries on knowledge graphs is important but particularly challenging because of the data incompleteness. Query embedding methods address this issue by learning-based models and simulating logical reasoning with set operators. Previous works focus on specific forms of embeddings, but scoring functions between embeddings are underexplored. In contrast to existing scoring functions motivated by local comparison or global transport, this work investigates the local and global trade-off with unbalanced optimal transport theory. Specifically, we embed sets as bounded measures in endowed with a scoring function motivated by the Wasserstein-Fisher-Rao metric. Such a design also facilitates closed-form set operators in the embedding space. Moreover, we introduce a convolution-based algorithm for linear time computation and a block-diagonal kernel to enforce the trade-off. Results show that WFRE can outperform existing query embedding methods on standard datasets, evaluation sets with combinatorially complex queries, and hierarchical knowledge graphs. Ablation study shows that finding a better local and global trade-off is essential for performance improvement.


page 1

page 2

page 3

page 4


Neural-Symbolic Entangled Framework for Complex Query Answering

Answering complex queries over knowledge graphs (KG) is an important yet...

Neural Methods for Logical Reasoning Over Knowledge Graphs

Reasoning is a fundamental problem for computers and deeply studied in A...

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

One of the fundamental problems in Artificial Intelligence is to perform...

Logical Message Passing Networks with One-hop Inference on Atomic Formulas

Complex Query Answering (CQA) over Knowledge Graphs (KGs) has attracted ...

Sequential Query Encoding For Complex Query Answering on Knowledge Graphs

Complex Query Answering (CQA) is an important and fundamental task for k...

Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs

Complex Query Answering (CQA) is an important reasoning task on knowledg...

Please sign up or login with your details

Forgot password? Click here to reset