Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities

2019/02/27 by Geewook Kim, Akifumi Okuno, Kim, Geewook +5
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1902.10409

openalex publication_date 2019/02/27 · openalex created_date 2019/04/11 · openalex updated_date 2026/07/28

Abstract

We propose weighted inner product similarity (WIPS) for neural network-based graph embedding. In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values. Despite its simplicity, WIPS can approximate arbitrary general similarities including positive definite, conditionally positive definite, and indefinite kernels. WIPS is free from similarity model selection, since it can learn any similarity models such as cosine similarity, negative Poincaré distance and negative Wasserstein distance. Our experiments show that the proposed method can learn high-quality distributed representations of nodes from real datasets, leading to an accurate approximation of similarities as well as high performance in inductive tasks.

Related

• On representation power of neural network-based graph embedding and beyond
• Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability
• Graph-Based Similarity of Neural Network Representations
• Neural Similarity Learning
• Similarity of Neural Networks with Gradients