Discovering Latent Representations of Relations for Interacting Systems
arXiv:2111.05514 · doi:10.1109/ACCESS.2021.3125335
Abstract
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.
arXiv commentAccepted by IEEE Access on Oct. 25, 2021
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Interaction Networks for Learning about Objects, Relations and Physics
- Learning to Simulate Complex Physics with Graph Networks
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Neural Relational Inference for Interacting Systems
- Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
- Bayesian latent structure discovery from multi-neuron recordings
- Visual Grounding of Learned Physical Models
- Factorised Neural Relational Inference for Multi-Interaction Systems
- Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video