Discovering Latent Representations of Relations for Interacting Systems
This addresses a bottleneck in graph analysis for domains like social networks or biological systems where relations are unobserved or complex, though it appears incremental as it builds on graph neural network approaches.
The paper tackles the problem of discovering latent relations between entities in interacting systems when the number or complexity of relations is unknown, proposing the DSLR model which uses a latent space representation and a flexible decoder, and shows it is suitable for analyzing dynamic graphs with unknown complex relations in experiments on synthetic and real-world data.
Systems whose entities interact with each other are common. In many interacting systems, it is difficult to observe the relations between entities which is the key information for analyzing the system. In recent years, there has been increasing interest in discovering the relationships between entities using graph neural networks. However, existing approaches are difficult to apply if the number of relations is unknown or if the relations are complex. We propose the DiScovering Latent Relation (DSLR) model, which is flexibly applicable even if the number of relations is unknown or many types of relations exist. The flexibility of our DSLR model comes from the design concept of our encoder that represents the relation between entities in a latent space rather than a discrete variable and a decoder that can handle many types of relations. We performed the experiments on synthetic and real-world graph data with various relationships between entities, and compared the qualitative and quantitative results with other approaches. The experiments show that the proposed method is suitable for analyzing dynamic graphs with an unknown number of complex relations.