Neural Networks for Relational Data
This addresses the challenge of handling structured domains like social network analysis for researchers and practitioners in machine learning, representing an incremental improvement by combining existing ideas in a novel way.
The paper tackles the problem of applying neural networks to relational data, which is unsuitable for traditional flat-feature vector approaches, by learning relational random-walk-based features and using parameter tying, resulting in effectiveness demonstrated over neural net baselines and state-of-the-art statistical relational models.
While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis. Such domains rely on relational representations to capture complex relationships between entities and their attributes. Thus, we consider the problem of learning neural networks for relational data. We distinguish ourselves from current approaches that rely on expert hand-coded rules by learning relational random-walk-based features to capture local structural interactions and the resulting network architecture. We further exploit parameter tying of the network weights of the resulting relational neural network, where instances of the same type share parameters. Our experimental results across several standard relational data sets demonstrate the effectiveness of the proposed approach over multiple neural net baselines as well as state-of-the-art statistical relational models.