Based on the recent success of deep generative models on continuous data, various new methods are being developed to generate discrete data such as graphs. However, these approaches focus on unconditioned generation, which limits their control over the generating procedure to produce graphs in context, thus limiting the applicability to real-world settings. To address this gap, we introduce an attention-based graph evolution model (AGE). AGE is a conditional graph generator based on the neural attention mechanism that can not only model graph evolution in both space and time, but can also model the transformation between graphs from one state to another. We evaluate AGE on multiple conditional graph-generation tasks, and our results show that it can generate realistic graphs conditioned on source graphs, outperforming existing methods in terms of quality and generality.

No abstract

No abstract

No abstract

We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet, existing methods for training ICA models rely on the assumption that relational features reflect the true labels of the nodes. This unrealistic assumption introduces a bias that is inconsistent with the actual prediction algorithm. In this paper, we introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA.