Spectral Neural Graph Sparsification

Graphs are central to modeling complex systems in domains such as social networks, molecular chemistry, and neuroscience. While Graph Neural Networks, particularly Graph Convolutional Networks, have become standard tools for graph learning, they remain constrained by reliance on fixed structures and susceptibility to over-smoothing. We propose the Spectral Preservation Network, a new framework for graph representation learning that generates reduced graphs serving as faithful proxies of the original, enabling downstream tasks such as community detection, influence propagation, and information diffusion at a reduced computational cost. The Spectral Preservation Network introduces two key components: the Joint Graph Evolution layer and the Spectral Concordance loss. The former jointly transforms both the graph topology and the node feature matrix, allowing the structure and attributes to evolve adaptively across layers and overcoming the rigidity of static neighborhood aggregation. The latter regularizes these transformations by enforcing consistency in both the spectral properties of the graph and the feature vectors of the nodes. We evaluate the effectiveness of Spectral Preservation Network on node-level sparsification by analyzing well-established metrics and benchmarking against state-of-the-art methods. The experimental results demonstrate the superior performance and clear advantages of our approach.

Discussion: Effective and Interpretable Outcome Prediction by Training Sparse Mixtures of Linear Experts

Process Outcome Prediction entails predicting a discrete property of an unfinished process instance from its partial trace. High-capacity outcome predictors discovered with ensemble and deep learning methods have been shown to achieve top accuracy performances, but they suffer from a lack of transparency. Aligning with recent efforts to learn inherently interpretable outcome predictors, we propose to train a sparse Mixture-of-Experts where both the ``gate'' and ``expert'' sub-nets are Logistic Regressors. This ensemble-like model is trained end-to-end while automatically selecting a subset of input features in each sub-net, as an alternative to the common approach of performing a global feature selection step prior to model training. Test results on benchmark logs confirmed the validity and efficacy of this approach.