Equivariant Entity-Relationship Networks
arXiv:1903.09033
Abstract
The relational model is a ubiquitous representation of big-data, in part due to its extensive use in databases. In this paper, we propose the Equivariant Entity-Relationship Network (EERN), which is a Multilayer Perceptron equivariant to the symmetry transformations of the Entity-Relationship model. To this end, we identify the most expressive family of linear maps that are exactly equivariant to entity relationship symmetries, and further show that they subsume recently introduced equivariant maps for sets, exchangeable tensors, and graphs. The proposed feed-forward layer has linear complexity in the data and can be used for both inductive and transductive reasoning about relational databases, including database embedding, and the prediction of missing records. This provides a principled theoretical foundation for the application of deep learning to one of the most abundant forms of data. Empirically, EERN outperforms different variants of coupled matrix tensor factorization in both synthetic and real-data experiments.
References in corpus (23)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Empirical Evaluation of Rectified Activations in Convolutional Network
- Molecular Graph Convolutions: Moving Beyond Fingerprints
- A Review of Relational Machine Learning for Knowledge Graphs
- Quantum-Chemical Insights from Deep Tensor Neural Networks
- Interaction Networks for Learning about Objects, Relations and Physics
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Gated Graph Sequence Neural Networks
- On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
- 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
- Adaptive Sampling Towards Fast Graph Representation Learning
- Gauge Equivariant Convolutional Networks and the Icosahedral CNN
- Equivariance Through Parameter-Sharing
- Covariant Compositional Networks For Learning Graphs
- Deep Models of Interactions Across Sets
- Probabilistic symmetries and invariant neural networks
- Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
- Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
- Learning Steerable Filters for Rotation Equivariant CNNs