Published multiple papers including 'Graph Clustering with Graph Neural Networks' (JMLR 2023), 'InstantEmbedding: Efficient Local Node Representations', 'FREDE: Anytime Graph Embeddings' (VLDB 2021), 'The Shape of Data: Intrinsic Distance for Data Distributions' (ICLR 2020), 'Just SLaQ When You Approximate: Accurate Spectral Distances for Web-Scale Graphs' (WWW 2020) & 'NetLSD: hearing the shape of a graph' (KDD 2018, Audience appreciation award runner up).
Research Experience
Currently working at Google Research in NYC, focusing on the intersection of graph algorithms and machine learning.
Education
Ph.D. from the University of Bonn, advised by Prof. Emmanuel Müller; M.Sc. from Skoltech, B.Sc. from Higher School of Economics, both in Moscow, Russia, with M.Sc. advisor Panagiotis Karras.
Background
Senior Research Scientist, mainly working on scalable & principled graph machine learning methods, methods & tools for understanding unsupervised learning, and data for Gemini and Gemma model families.