Information and Network Dynamics group

Our research group is part of the School of Computer and Communication Sciences at EPFL in Lausanne, Switzerland. The group is lead by Matthias Grossglauser and Patrick Thiran. Our research focuses broadly on the statistical modeling of large dynamical systems involving both human and technical agents. Examples include social and information networks, epidemic processes, human mobility and transportation, and recommender systems. Our work lies at the intersection of machine learning, probabilistic modeling, large-scale data analytics, and performance analysis. Here are the research areas we work on:

Graph Mining

Network alignment, network assembly, and network inference

Mobility Mining

Prediction and transfer learning in populations

Epidemics

Monitoring, prediction, and source inference

Distributed Processes on Graphs

Gossiping, voting, and optimization

Discrete-Choice Models

Large-scale inference and ranking

Active Learning

Multi-armed bandits, online optimization, active learning

Wireless and Hybrid Networking

Wireless networking, power-line communication, hybrid networking

Applications

In computational biology, data privacy, medical data analytics, etc.

Recent publications

Generalization Comparison of Deep Neural Networks via Output Sensitivity
M. Forouzesh, F. Salehi and P. Thiran
25th International Conference on Pattern Recognition, Milan, Italy, January 10-15, 2021.
[view at publisher]

Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the loss function to the output's sensitivity to its input. We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data. We find that sensitivity is decreased by applying popular methods which improve the generalization performance of the model, such as (1) using a deep network rather than a wide one, (2) adding convolutional layers to baseline classifiers instead of adding fully-connected layers, (3) using batch normalization, dropout and max-pooling, and (4) applying parameter initialization techniques.

War of Words II: Enriched Models of Law-Making Processes
V. Kristof, A. Suresh, M. Grossglauser and P. Thiran
The Web Conference 2021 (WWW '21), Ljubljana, Slovenia, April 19-23, 2021.
[view at publisher]

The European Union law-making process is an instance of a peer- production system. We mine a rich dataset of law edits and intro- duce models predicting their adoption by parliamentary committees. Edits are proposed by parliamentarians, and they can be in conflict with edits of other parliamentarians and with the original proposition in the law. Our models combine three different categories of features: (a) Explicit features extracted from data related to the edits, the parliamentarians, and the laws, (b) latent features that capture bi-linear interactions between parliamentarians and laws, and (c) text features of the edits. We show experimentally that this combination enables us to accurately predict the success of the edits. Furthermore, it leads to model parameters that are interpretable, hence provides valuable insight into the law-making process.

A Variational Inference Approach to Learning Multivariate Wold Processes
J. Etesami, W. Trouleau, N. Kiyavash, M. Grossglauser and P. Thiran
24th International Conference on Artificial Intelligence and Statistics (AISTATS), San Diego, California, USA, April 13-15, 2021.
[full text]

Temporal point-processes are often used for mathematical modeling of sequences of discrete events with asynchronous timestamps. We focus on a class of temporal point-process models called multivariate Wold processes (MWP). These processes are well suited to model real-world communication dynamics. Statistical inference on such processes often requires learning their corresponding parameters using a set of observed timestamps. In this work, we relax some of the restrictive modeling assumptions made in the state-of-the-art and introduce a Bayesian approach for inferring the parameters of MWP. We develop a computationally efficient variational inference algorithm that allows scaling up the approach to high-dimensional processes and long sequences of observations. Our experimental results on both synthetic and real-world datasets show that our proposed algorithm outperforms existing methods.

Metric dimension of critical Galton–Watson trees and linear preferential attachment trees
J. Komjáthy and G. Ódor
European Journal of Combinatorics, 2021.
[view at publisher]

The metric dimension of a graph G is the minimal size of a subset R of vertices of G that, upon reporting their graph distance from a distinguished (source) vertex v⋆, enable unique identification of the source vertex v⋆ among all possible vertices of G. In this paper we show a Law of Large Numbers (LLN) for the metric dimension of some classes of trees: critical Galton–Watson trees conditioned to have size n, and growing general linear preferential attachment trees. The former class includes uniform random trees, the latter class includes Yule-trees (also called random recursive trees), m-ary increasing trees, binary search trees, and positive linear preferential attachment trees. In all these cases, we are able to identify the limiting constant in the LLN explicitly. Our result relies on the insight that the metric dimension can be related to subtree properties, and hence we can make use of the powerful fringe-tree literature developed by Aldous and Janson et al.

A meta-learning approach for genomic survival analysis
Y. L. Qiu, H. Zheng, A. Devos, H. Selby and O. Gevaert
Nature Communications, 2020.
[full text] [view at publisher]

RNA sequencing has emerged as a promising approach in cancer prognosis as sequencing data becomes more easily and affordably accessible. However, it remains challenging to build good predictive models especially when the sample size is limited and the number of features is high, which is a common situation in biomedical settings. To address these limitations, we propose a meta-learning framework based on neural networks for survival analysis and evaluate it in a genomic cancer research setting. We demonstrate that, compared to regular transfer-learning, meta-learning is a significantly more effective paradigm to leverage high-dimensional data that is relevant but not directly related to the problem of interest. Specifically, meta-learning explicitly constructs a model, from abundant data of relevant tasks, to learn a new task with few samples effectively. For the application of predicting cancer survival outcome, we also show that the meta-learning framework with a few samples is able to achieve competitive performance with learning from scratch with a significantly larger number of samples. Finally, we demonstrate that the meta-learning model implicitly prioritizes genes based on their contribution to survival prediction and allows us to identify important pathways in cancer. RNA-sequencing data from tumours can be used to predict the prognosis of patients. Here, the authors show that a neural network meta-learning approach can be useful for predicting prognosis from a small number of samples.

We have open positions!

We are hiring postdocs and PhD students in all our research areas.