Kyriakos Axiotis
Kyriakos is a research scientist working on the Algorithms & Optimization team in New York. He is interested in efficient ML, including efficient optimization, model/data/systems efficiency, as well as ML interpretability. He received his PhD from MIT in the theory of graph algorithms and optimization and his BSc from the National Technical University of Athens. Examples of recent research interests include sparse optimization, model compression, neural architecture search, data selection and attribution.
Authored Publications
Sort By
SubMix: Learning to Mix Graph Sampling Heuristics
Josh Dillon
Johannes Gasteiger
Preview abstract
Sampling subgraphs for training Graph Neural Networks (GNNs) is receiving much attention from the GNN community. While a variety of methods have been proposed, each method samples the graph according to its own heuristic. However, there has been little work in mixing these heuristics in an end-to-end trainable manner. In this work, we design a generative framework for graph sampling. Our method, SubMix, parameterizes subgraph sampling as a convex combination of heuristics. We show that a continuous relaxation of the discrete sampling process allows us to efficiently obtain analytical gradients for training the sampling parameters. Our experimental results illustrate the usefulness of learning graph sampling in three scenarios: (1) robust training of GNNs by automatically learning to discard noisy edge sources; (2) improving model performance by trainable and online edge subset selection; and (3) by integrating our framework into decoupled GNN models improves their performance on standard benchmarks.
View details
