Paper Accepted to Nature Physics: Topological limits to parallel processing capability of network architectures - Paper Link
For more recent updates and information, please check my Curriculum Vitae.
I'm a senior member of the research staff at Intel Labs.
I received my Ph.D. from the Computer Science Department at Purdue University,
and my M.S. in statistics and computer science from Purdue University. Before joining Intel Labs, I had the opportunity to work at a number of industrial research labs including
Facebook data science, Adobe research Labs, Technicolor research and innovation Labs, Intel data analytics, and the data mining and computer modeling center of excellence in Egypt.
My research lies in the field of large-scale machine learning and spans the theory and algorithms of graphs, statistical machine learning methods,
and their applications in social and information networks. I have authored numerous papers and tutorials in top-tier conferences and journals.
My research was selected among the best papers of ICDM in 2015, BigMine in 2012, and covered by popular press such as the MIT Technology Review.
I'm very honored to be a recipient of the class of 2014 Rising Stars in Computer Science (selected by top faculty at UC Berkeley, Stanford University, MIT, etc). In 2018-19, I received the Intel Labs recognition award for my significant contribution and impact to Intel's DARPA HIVE proposal and project. In 2013, I co-founded the open source network repository project,
the first data repository with interactive visual graph analytics to promote reproducibility and help researchers find and explore graph data in real-time over the web.
Erdos Number 3
Paper Accepted to Nature Physics: Topological limits to parallel processing capability of network architectures - Paper Link
Paper Accepted to AAAI 2021: Graph Neural Networks with Heterophily - Paper Link
Paper Accepted to MLSys: A Distributed Graph-Theoretic Framework for Automatic Parallelization in Multi-core Systems.
Serving as an Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems (TNNLS) - Submit your best work here!
Paper accepted to NeurIPS 2020 workshop: Neural Algorithms for Graph Navigation - Paper link
Paper accepted to NeurIPS 2020: Adaptive Shrinkage Estimation for Streaming Graphs - Paper link
Serving as the PC chair of the 2021 IPDPS Workshop on Graphs, Architectures, Programming, and Learning (GrAPL) - Submit your work here!
Paper accepted to IEEE TKDE: Role-based Graph Embeddings - Paper link
Paper accepted to ACM TKDD: Heterogenous Graphlets - Paper link
Organizing the 7th BigGraphs workshop at IEEE Big Data 2020 with Mohammed Hasan, Kamesh Madduri, and Shaikh Arifuzzaman
Journal paper accepted to DAMI: Deep Graph Similarity Learning: A Survey
Paper on Network Science Infrastructure accepted to Gateways 2020
Paper accepted to ACM TKDD: On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
Paper accepted to SDM 2020: Deep Parametric Model for Discovering Group-cohesive Functional Brain Regions
Invited Panelist at the Workshop on Irregular Applications: Architectures and Algorithms at SuperComputing 2019
Paper accepted to NeurIPS workshop on ML for systems: Learning to Vectorize Using Deep Reinforcement Learning - link
Paper accepted to WSDM 2020: A Structural Graph Representation Learning Framework
New preprint: Temporal Network Sampling - arXiv link
Paper accepted to CGO 2020: NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning - arXiv link
New preprint: Deep Reinforcement Learning in System Optimization - arXiv link
Paper accepted to CIKM 2019: Deep Graph Similarity Learning for Brain Data Analysis - link
Invited Keynote at the SIGKDD Workshop on Offline and Online Evaluation of Interactive Systems - [Slides]