AdaGNN: A multi-modal latent representation meta-learner for GNNs based on AdaBoosting
This work addresses a bottleneck in GNNs for tasks like social network recommendations by enabling better capture of diverse graph signals, though it appears incremental as it builds on existing inductive GNN methods.
The authors tackled the problem of single embedding spaces in Graph Neural Networks (GNNs) failing to capture all aspects of graph signals by proposing AdaGNN, a boosting-based meta-learner that automatically learns multiple projections and embedding spaces, resulting in improved performance for applications with rich node neighborhood information.
As a special field in deep learning, Graph Neural Networks (GNNs) focus on extracting intrinsic network features and have drawn unprecedented popularity in both academia and industry. Most of the state-of-the-art GNN models offer expressive, robust, scalable and inductive solutions empowering social network recommender systems with rich network features that are computationally difficult to leverage with graph traversal based methods. Most recent GNNs follow an encoder-decoder paradigm to encode high dimensional heterogeneous information from a subgraph onto one low dimensional embedding space. However, one single embedding space usually fails to capture all aspects of graph signals. In this work, we propose boosting-based meta learner for GNNs, which automatically learns multiple projections and the corresponding embedding spaces that captures different aspects of the graph signals. As a result, similarities between sub-graphs are quantified by embedding proximity on multiple embedding spaces. AdaGNN performs exceptionally well for applications with rich and diverse node neighborhood information. Moreover, AdaGNN is compatible with any inductive GNNs for both node-level and edge-level tasks.