Fragkiskos D. Malliaros
Associate Professor (HDR)
CentraleSupélec,
Paris-Saclay University
OPIS team,
Inria Saclay
About me
I am an Associate Professor (HDR) at CentraleSupélec, Paris-Saclay University, working in the Center for Visual Computing, and the OPIS team of Inria Saclay. My research interests span the broad area of data science, with focus on graph mining, social network analysis, applied machine learning and natural language processing.
Right before that, I spent a wonderful year as a data science postdoctoral fellow in the Department of Computer Science and Engineering at UC San Diego, where I was a member of the Artificial Intelligence group. I was also affiliated with the Information Theory and Applications Center (ITA) and the Qualcomm Institute. Between Oct. 2015 - Sept. 2016, I was a postdoctoral researcher in the Data Science and Mining (DaSciM) group of the Computer Science Laboratory (LIX) at École Polytechnique in Paris, France, from where I also received my Ph.D. degree (Sept. 2015), working under the supervision of Prof. Michalis Vazirgiannis. I obtained both my Diploma and my M.Sc. degree from the Computer Engineering and Informatics Department of the University of Patras, Greece in 2009 and 2011 respectively. There, I was fortunate to work with Prof. Vasileios Megalooikonomou.
During the summer of 2014, I was a research intern at the Palo Alto Research Center (PARC) in Palo Alto, CA. I was also the recipient of the 2012 Google Europe Doctoral Fellowship in Graph Mining and the 2015 Thesis Prize by Ecole Polytechnique.
Publications
Preprints
-
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
2024
-
Continuous Product Graph Neural NetworksConference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024.
-
Higher-Order GNNs Meet Efficiency: Sparse Sobolev Graph Neural Networks
-
Learning Graph Representations for Influence MaximizationSocial Network Analysis and Mining (SNAM), Springer, 2024.
-
Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?ACM International Conference on Information and Knowledge Management (CIKM), Boise, Idaho, 2024.
(Short paper).
-
Measuring Factual Correctness of Large Language Models in the Legal DomainACM International Conference on Information and Knowledge Management (CIKM), Boise, Idaho, 2024.
(Short paper).
-
Improving Molecular Modeling with Geometric GNNs: an Empirical Study
-
Uplift Modeling Under Limited Supervision
-
Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
-
Estimation of a Causal Directed Acyclic Graph Process using Non-Gaussianity
-
A Machine Learning Tour in Network Science
-
Maximizing Influence with Graph Neural NetworksIEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Morocco, 2023.
[arXiv: PDF]
-
On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks
-
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
-
Time-varying Signals Recovery via Graph Neural NetworksIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, 2023.
[Paper: PDF]
-
Higher-order Sparse Convolutions in Graph Neural NetworksIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Rhodes Island, Greece, 2023.
[Paper: PDF]
-
BraneMF: Integration of Biological Networks for Functional Analysis of Proteins
-
BRANEnet: Embedding Multilayer Networks for Omics Data Integration
-
NodeSig: Binary Node Embeddings via Random Walk Diffusion
-
Higher-order Clustering and Pooling for Graph Neural Networks
-
Multiple Similarity Drug-Target Interaction Prediction with Random Walks and Matrix Factorization
-
Multiple Kernel Representation Learning on Networks
-
Multivariate Lipschitz Analysis of the Stability of Neural NetworksFrontiers in Signal Processing (Front. Sig. Proc.), 2022.
[Journal Version: LINK] -
BRANET: Graph-based Integration of Multi-omics Data with Biological a priori for Regulatory Network Inference
-
Influence Learning and Maximization (Tutorial)IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Online, 2021.
[Tutorial Website: LINK] -
GraphSVX: Shapley Value Explanations for Graph Neural Networks
-
Multiomics Data Integration for Gene Regulatory Network Inference with Exponential Family Embeddings
-
An Adversarial Attacker for Neural Networks in Regression ProblemsIJCAI AI Safety Workshop (AISafety), Online, 2021. [Paper: PDF] Shortlisted for the Best Paper Award.
-
Topic-Aware Latent Models for Representation Learning on Networks
-
Influence Learning and Maximization (Tutorial)
-
Multi-task Learning for Influence Estimation and Maximization
-
Boosting Tricks for Word Mover’s DistanceInternational Conference on Artificial Neural Networks (ICANN), Bratislava, Slovakia, 2020.
[Paper: PDF] -
Exponential Family Graph Embeddings
-
Influence Maximization using Influence and Susceptibility Embeddings
-
The Core Decomposition of Networks: Theory, Algorithms and Applications
-
Dynamic Monitoring of Software Use with Recurrent Neural NetworksData & Knowledge Engineering (DKE), Elsevier, 2019.
[Journal Version: LINK] -
Learning Node Embeddings with Exponential Family DistributionsNeurIPS Graph Representation Learning Workshop (NeurIPS-GRL), Vancouver, Canada, 2019.
[Paper: PDF] -
Kernel Node Embeddings
-
Perturb and Combine to Identify Influential Spreaders in Real-World NetworksIEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Vancouver, Canada, August 2019.
[arXiv: PDF] -
Semi-Supervised Learning and Graph Neural Networks for Fake News Detection
-
TNE: A Latent Model for Representation Learning on Networks
-
BiasedWalk: Biased Sampling for Representation Learning on Graphs
-
MATI: An Efficient Algorithm for Influence Maximization in Social NetworksPLOS One, 2018.
[Journal version: LINK] -
DiffuGreedy: An Influence Maximization Algorithm based on Diffusion Cascades
-
k-Degree Anonymity on Directed Networks
-
GraphRep: Boosting Text Mining, NLP and Information Retrieval with Graphs (Tutorial)
-
Fusing Document, Collection and Label Graph-based Representations with Word Embeddings for Text Classification
-
Reconstructing Uncertain Graphs Based on Low-Rank FactorizationsFrom Physics to Information Sciences and Geometry (Entropy) , Barcelona, May 2018.
-
Graph-based Text Representations: Boosting Text Mining, NLP and Information Retrieval with Graphs (Tutorial)The Web Conference (WWW), Lyon, France, 2018.
[Tutorial Website: LINK] -
MATI: An Efficient Algorithm for Influence Maximization in Social NetworksInternational Conference on Complex Networks and Their Applications (Complex Networks), Lyon, France, December 2017.
[Paper: PDF] -
NetGloVe: Learning Node Representations for Community DetectionInternational Conference on Complex Networks and Their Applications (Complex Networks), Lyon, France, December 2017.
[Paper: PDF] -
Core Decomposition of Uncertain Graphs Using Representative InstancesInternational Conference on Complex Networks and Their Applications (Complex Networks), Lyon, France, December 2017.
[Paper: PDF] -
Core Decomposition of Networks: Concepts, Algorithms and Applications (Tutorial)European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), Skopje, September 2017.
[Tutorial Website: LINK] -
Graph-based Text Representations: Boosting Text Mining, NLP and Information Retrieval with Graphs (Tutorial)Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, September 2017.
[Tutorial Website: LINK] -
Sensitivity of Community Structure to Network Uncertainty
-
SpreadViz: Analytics and Visualization of Spreading Processes in Social NetworksIEEE International Conference on Data Mining (ICDM), Barcelona, Spain, December 2016.
(Demo paper) -
Core Decomposition of Networks: Concepts, Algorithms and Applications (Tutorial)IEEE International Conference on Data Mining (ICDM), Barcelona, Spain, December 2016.
(Acceptance Rate: 4/17)
[Tutorial Website: LINK] -
A Graph Degeneracy-based Approach to Keyword ExtractionConference on Empirical Methods in Natural Language Processing (EMNLP), Austin, Texas, November 2016.
[Paper: PDF] -
A k-core Decomposition Framework for Graph ClusteringPreprint, 2016.
[arXiv: PDF] -
Locating Influential Nodes in Complex NetworksScientific Reports, Nature Publishing Group, 2016.
(Impact Factor: 5.228)
[Journal Version: LINK]
Editor's choice: complex networks.
-
Core Decomposition in Graphs: Concepts, Algorithms and Applications (Tutorial)
-
Vulnerability Assessment in Social Networks under Cascade-based Node DeparturesEPL (Europhysics Letters), 110(6): 68006, IOP Science, 2015.
(Impact Factor: 1.963)
[Journal Version: LINK] -
Graph-Based Term Weighting for Text Categorization
-
Core Decomposition: Algorithms and Applications (Tutorial)IEEE/ACM Intern. Conf. on Advances in Social Networks Analysis and Mining (ASONAM), Paris, France, August 2015.
[Tutorial Website: LINK] -
Disengagement Social Contagion: Assessing Network Vulnerability under Node DeparturesInternational Conference on Computational Social Science (ICCSS), Helsinki, Finland, June 2015.
[Paper: PDF] -
Spread it Good, Spread it Fast: Identification of Influential Nodes in Social Networks
-
Estimating Robustness in Large Social Graphs
-
CoreCluster: A Degeneracy Based Graph Clustering Framework
-
To Stay or Not to Stay: Modeling Engagement Dynamics in Social Graphs
-
Clustering and Community Detection in Directed Networks: A Survey
-
Multiresolution Similarity Search in Time Series Data: An Application to EEG SignalsACM International Conf. on Pervasive Technologies Related to Assistive Environments (PETRA), Rhodes, Greece, May 2013.
[Paper: PDF] -
Graph Mining Tools for Community Detection and Evaluation in Social Networks and the Web (Tutorial)International World Wide Web Conference (WWW), Rio de Janeiro, Brazil, May 2013.
[Tutorial Slides: PDF] -
Advanced Graph Mining for Community Evaluation in Social Networks and the Web (Tutorial)
-
Fast Robustness Estimation in Large Social Graphs: Communities and Anomaly Detection
-
Expansion Properties of Large Social Graphs
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2011 - 2012
Collaborators
I have been very privileged to collaborate with the following great people, listed in chronological order of collaboration.
Vasileios Megalooikonomou (U of Patras), Christos Faloutsos (CMU), Michalis Vazirgiannis (École Polytechnique), Christos Giatsidis (École Polytechnique), Amalia Charisi (U of Patras), Evangelia I. Zacharaki (U of Patras), Dimitrios M. Thilikos (U of Montpellie, CNRS and U of Athens), Maria-Evgenia Rossi (École Polytechnique), Konstantinos Skianis (École Polytechnique), Jordi Casas-Roma (U Oberta de Catalunya and U Autònoma de Barcelona), Apostolos N. Papadopoulos (Aristotle U of Thessaloniki), Charanpal Dhanjal (Télécom ParisTech and Forebyte Ltd. London), Nikolaos Tziortziotis (École Polytechnique), Emmanouil Kiagias (Oracle, UK), Antoine J.-P. Tixier (École Polytechnique)
