Ali H. Sayed | EPFL Graph Search

Ali H. Sayed est doyen de la Faculté des sciences et techniques de l’ingénieur (STI) de l'EPFL, en Suisse, où il dirige également le laboratoire de systèmes adaptatifs. Il a également été professeur émérite et président du département d'ingénierie électrique de l'UCLA. Il est reconnu comme un chercheur hautement cité et est membre de la US National Academy of Engineering. Il est également membre de l'Académie mondiale des sciences et a été président de l'IEEE Signal Processing Society en 2018 et 2019.

Le professeur Sayed est auteur et co-auteur de plus de 570 publications et de six monographies. Ses recherches portent sur plusieurs domaines, dont les théories d'adaptation et d'apprentissage, les sciences des données et des réseaux, l'inférence statistique et les systèmes multi-agents, entre autres.

Ses travaux ont été récompensés par plusieurs prix importants, notamment le prix Fourier de l'IEEE (2022), le prix de la société Norbert Wiener (2020) et le prix de l'éducation (2015) de la société de traitement des signaux de l'IEEE, le prix Papoulis (2014) de l'Association européenne de traitement des signaux, le Meritorious Service Award (2013) et le prix de la réalisation technique (2012) de la société de traitement des signaux de l'IEEE, le prix Terman (2005) de la société américaine de formation des ingénieurs, le prix de conférencier émérite (2005) de la société de traitement des signaux de l'IEEE, le prix Koweït (2003) et le prix Donald G. Fink (1996) de l'IEEE. Ses publications ont été récompensées par plusieurs prix du meilleur article de l'IEEE (2002, 2005, 2012, 2014) et de l'EURASIP (2015). Pour finir, Ali H. Sayed est aussi membre de l'IEEE, d'EURASIP et de l'American Association for the Advancement of Science (AAAS), l'éditeur de la revue Science.

Discovering Influencers in Opinion Formation Over Social Graphs

Mert Kayaalp, Ali H. Sayed, Valentina Shumovskaia

The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private observations and exchange the beliefs with their neighbors. In this work, it is shown how the sequence of publicly exchanged beliefs over time allows users to discover rich information about the underlying network topology and about the flow of information over the graph. In particular, it is shown that it is possible (i) to identify the influence of each individual agent to the objective of truth learning, (ii) to discover how well-informed each agent is, (iii) to quantify the pairwise influences between agents, and (iv) to learn the underlying network topology. The algorithm derived herein is also able to work under non-stationary environments where either the true state of nature or the graph topology are allowed to drift over time. We apply the proposed algorithm to different subnetworks of Twitter users, and identify the most influential and central agents by using their public tweets (posts).

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Estimating the Topology of Preferential Attachment Graphs Under Partial Observability

Ali H. Sayed

This work addresses the problem of learning the topology of a network from the signals emitted by the network nodes. These signals are generated over time through a linear diffusion process, where neighboring nodes exchange messages according to the underlying network topology, and aggregate them according to a certain combination matrix. We consider the demanding setting of graph learning under partial observability, where signals are available only from a limited fraction of nodes, and we want to establish whether the topology of these nodes can be estimated faithfully, despite the presence of possibly many latent nodes. Recent results examined this problem when the network topology is generated according to an Erdos-Renyi random model. However, Erdos-Renyi graphs feature homogeneity across nodes and independence across edges, while, over several real-world networks, significant heterogeneity is observed between very connected "hubs" and scarcely connected peripheral nodes, and the edge construction process entails significant dependencies across edges. Preferential attachment random graphs were conceived primarily to fill these gaps. We tackle the problem of graph learning over preferential attachment graphs by focusing on the following setting: first-order vector autoregressive models equipped with a stable Laplacian combination matrix, and a network topology drawn according to the popular Bollobas-Riordan preferential attachment model. The main result established in this work is that a combination-matrix estimator known as Granger estimator achieves graph learning under partial observability.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Learning From Heterogeneous Data Based on Social Interactions Over Graphs

Virginia Bordignon, Ali H. Sayed, Stefan Vlaski

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of social learning, several useful strategies have been developed, which solve decision making problems through local cooperation across distributed agents and allow them to learn from streaming data. However, traditional social learning strategies rely on the fundamental assumption that each agent has significant prior knowledge of the underlying distribution of the observations. In this work we overcome this issue by introducing a machine learning framework that exploits social interactions over a graph, leading to a fully data-driven solution to the distributed classification problem. In the proposed social machine learning (SML) strategy, two phases are present: in the training phase, classifiers are independently trained to generate a belief over a set of hypotheses using a finite number of training samples; in the prediction phase, classifiers evaluate streaming unlabeled observations and share their instantaneous beliefs with neighboring classifiers. We show that the SML strategy enables the agents to learn consistently under this highly-heterogeneous setting and allows the network to continue learning even during the prediction phase when it is deciding on unlabeled samples. The prediction decisions are used to continually improve performance thereafter in a manner that is markedly different from most existing static classification schemes where, following training, the decisions on unlabeled data are not re-used to improve future performance.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023