Hello, since Nov. 2018, I am on an “advanced research position” at Inria, in the WIDE team.

“Maybe, not content to be alienated by observation, maybe does the object deceive us? Maybe it invented original answers, and not only the ones we ask for? May not be does it not want to be analyzed and observed at all and taking this for a challenge (which is true), does it respond with another challenge? […] the object analyzed today triumphs everywhere, by its object position, over the subject of analysis.” (Jean Baudrillard, Fatal Strategies.)

My main current research activity is trying to disprove that nice Baudrillard quote, by studying black-box algorithms in the context of recommender systems, or neural-network models. I am also interested in algorithms for the distribution of machine learning (deep networks, GANs).

I was a senior research scientist at Technicolor R&I (2009-2018), where I worked on scalable storage, processing and machine learning for data analytics and monitoring of home devices. I own a PhD on distributed systems from University of Rennes 1, and a background on peer-to-peer systems, and graph mining/algorithms. My Ph.D. thesis was financed by Orange Labs (where I stayed btw 2004-2007). I obtained my habilitation (HDR) on November 2016 from University of Rennes 1. I am the president and sysadmin of the gozdata association, that provides the gozmail service, built from free software.

News

• Launched the whosban.org website, to check the shadow banning practice on Twitter !
• Semestre Supervision de systèmes dynamiques.
• Article sur les enjeux de l’explicabilité, mentionant nos travaux, sur internetactu.net.
• Talk au THCON20 @ Toulouse avec G. Trédan.
• Joined the board of the Société Informatique de France.
• Article from Algorithm Watch (Berlin) on our “bouncer problem” “Explainable AI” doesn’t work for online services – now there’s proof
• Atelier “algorithmes en boite-noire”, le 10 octobre 2019 à Lyon.
• Article Emergences/Inria “Plus de transparence pour les algorithmes de recommandation” par J-M Prima.
• Talk video about “Decision boundaries & security related questions” @ the Deep Learning : from theory to applications workshop in Sept. 2018 in Rennes: VIDEO HERE.
• Second order centrality code now part of the Networkx library v2.2.

Recent publications

• The Bouncer Problem: Challenges to Remote Explainability, Erwan Le Merrer, Gilles Trédan. [ArXiv preprint 2019].

• Adversarial Frontier Stitching for Remote Neural Network Watermarking, Erwan Le Merrer, Patrick Perez, Gilles Trédan. In the journal of Neural Computing and Applications, 2019. [editor] [preprint]

• TamperNN: Efficient Tampering Detection of Deployed Neural Nets, Erwan Le Merrer, Gilles Trédan. In ISSRE, 2019. [preprint]

• Unified and Scalable Incremental Recommenders with Consumed Item Packs, Rachid Guerraoui, Erwan Le Merrer, Rhicheek Patra, Jean-Ronan Vigouroux. In Euro-par 2019. [preprint].

• Application-aware adaptive partitioning for graph processing systems, Erwan Le Merrer, Gilles Trédan. (6p short) In MASCOTS 2019. [preprint]

• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets, Corentin Hardy, Erwan Le Merrer, Bruno Sericola. In IPDPS, 2019. [preprint].

• Gossiping GANs, Corentin Hardy, Erwan Le Merrer, Bruno Sericola. In Middleware’s Workshop on Distributed Infrastructures for Deep Learning, 2018. [preprint] [ACM ref]

• zoNNscan : a boundary-entropy index for zone inspection of neural models, Adel Jaouen, Erwan Le Merrer. [ArXiv preprint 2018].

• Distributed deep learning on edge-devices: feasibility via adaptive compression, Corentin Hardy, Erwan Le Merrer, Bruno Sericola. In IEEE NCA, 2017. Best paper award [preprint].

• The topological face of recommendation, Erwan Le Merrer, Gilles Trédan. In Complex Networks 2017. [preprint].

• Uncovering Influence Cookbooks : Reverse Engineering the Topological Impact in Peer Ranking Services, Erwan Le Merrer, Gilles Trédan. In ACM CSCW, 2017. [preprint].

Selected publications

• Adversarial Frontier Stitching for Remote Neural Network Watermarking, Erwan Le Merrer, Patrick Perez, Gilles Trédan. Neural Computing and Applications, 2019.

• Frugal topology construction for stream aggregation in the cloud, Rachid Guerraoui, Erwan Le Merrer, Rhicheek Patra, Bao-Duy Tran. Infocom, 2016.

• Archiving cold data in warehouses with clustered network coding, Fabien André, Anne-Marie Kermarrec, Erwan Le Merrer, Nicolas Le Scouarnec, Gilles Straub, Alexandre van Kempen. Eurosys, 2014.

• Second order centrality: Distributed assessment of nodes criticity in complex networks, Anne-Marie Kermarrec, Erwan Le Merrer, Bruno Sericola, Gilles Trédan. Computer Communications, 2011.

• Peer counting and sampling in overlay networks based on random walks, Ayalvadi J. Ganesh, Anne-Marie Kermarrec, Erwan Le Merrer, Laurent Massoulié. Distributed computing, 2007.

Code

• Pushed non-randomness computation for graphs, by Ying & Wu, in NetworkX 2.4.
• zoNNscan code, for analysis of decision boundaries, available here.
• Second order centrality code now part of the Networkx library, from ComCom paper.
• Corentin’s code for distributed deep learning (NCA best paper) here and for random neural layers here.

Awards

• IEEE NCA 2017 best paper award, for paper “Distributed deep learning on edge-devices: feasibility via adaptive compression”, with Corentin Hardy and Bruno Sericola.
• Paper co-authors are awarded prize “La recherche 2015”, for work on cold storage, from Eurosys 2014.
• Prix “Bretagne jeune chercheur” 2011, mention spéciale.

Service

As my main participation to scientific events, I was co-chair of Middleware 2018 industry track, in Rennes, and AlgoTel 2019 program co-chair. Co-organizing WOS with INRIA and Interdigital (ex Technicolor), a workshop on storage, cloud processing and data analytics, in every year Rennes: WOS archive.

I have co-authored 8 granted patents, and around 39 pending demands.

.