Béni Egressy

Distributed Computing Group
Computer Engineering and Networks Laboratory (TIK)
Department Electrical Engineering (D-ITET)
Office ETZ G 94
ETH Zurich

Gloriastrasse 35
8092 Zurich
Switzerland

phone	+41 44 63 27051
fax	+41 44 63 21036
email

Publications

GRAPHTESTER: Exploring Theoretical Boundaries of GNNs on Graph Datasets
Eren Akbiyik, Florian Grötschla and Béni Egressy and Roger Wattenhofer.
Data-centric Machine Learning Research (DMLR) Workshop at ICML 2023, Honolulu, Hawaii, July 2023.
BibTeX
A Plug-and-Play Method for Controlled Text Generation
Damian Pascual, Béni Egressy, Clara Meister, Ryan Cotterell and Roger Wattenhofer.
Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021, Punta Cana, Dominican Republic, November 2021.
BibTeX
Two-Agent Tree Evacuation
Béni Egressy, Henri Devillez, Robin Fritsch and Roger Wattenhofer.
28th International Colloquium on Structural Information and Communication Complexity (SIROCCO), Wrocław, Poland, June 2021.
External BibTeX
Brain2Word: Improving Brain Decoding Methods and Evaluation (Oral presentation)
Nicolas Affolter, Béni Egressy, Damian Pascual and Roger Wattenhofer.
Medical Imaging Meets Neurips Workshop, Online, December 2020.
BibTeX

Theses & Labs

	Title	Type	Contact/Supervisor	Assigned
Available Theses & Labs
	Contrastive Learning and Predictability Minimization Continued	S	Béni Egressy	available
	Graph Neural Networks for Financial Crime Analysis (2)	M	Béni Egressy	available
Past Theses & Labs
	Title	Type	Contact/Supervisor	Assigned	Student(s)
	Cascaded BeamSearch: Plug-and-Play Terminology-Forcing For Neural Machine Translation [confidential]	S	Béni Egressy	HS 22
	Graph Neural Networks for Financial Fraud Detection [confidential]	M	Béni Egressy	HS 22
	A Practical Study on Anomaly Detection for a Hydro-Power Plant [confidential]	M	Béni Egressy	FS 22
	Inconvenient Data Sets for Graph Neural Networks [confidential]	B	Béni Egressy, Florian Grötschla	FS 22
	Unreasonable Effectiveness of Edge Features: Formalization and Applications of Edge Pre-coloring in Color Refinement [confidential]	S	Béni Egressy, Florian Grötschla	FS 22
	Benchmarking Graph Neural Network Models [confidential]	S	Béni Egressy, Florian Grötschla	FS 22
	What Can Neural Networks Learn? Set Functions [confidential]	B	Béni Egressy	FS 22
	What can Neural Networks learn? - Set Functions [confidential]	G	Béni Egressy	FS 22	,
	Benchmarking Graph Neural Networks [confidential]	M	Béni Egressy, Ard Kastrati	HS 21
	Applying Predictability Minimization onto Unsupervised Contrastive Representation Learning [confidential]	B	Béni Egressy	HS 21
	Understanding Reinforcement Learning with 6nimmt!	G	Béni Egressy	HS 21	,
	Improving Brain Decoding Methods and Evaluation	M	Béni Egressy, Damian Pascual	FS 21
	Region Based File Sharing	B	Robin Fritsch, Béni Egressy	FS 21
	Multi Agent Reinforcement Learning for Game Theory: Financial Graphs [confidential]	M	Béni Egressy, Pál András Papp	FS 21
	Conditional Language Generation [confidential]	S	Damian Pascual, Béni Egressy	HS 20
	Graph Neural Networks in Finance	S	Lukas Faber, Béni Egressy	HS 20
	Infection Spreading in Graphs	S	Pál András Papp, Béni Egressy	HS 20
	Smart Vote [confidential]	B	Béni Egressy, Robin Fritsch	HS 20
	Brain2Word: Decoding Brain Activity for Language Generation	M	Damian Pascual, Béni Egressy	FS 20
	An Algorithm For Tree Evacuation [confidential]	B	Béni Egressy, Henri Devillez	FS 20
	Graph Evacuation [confidential]	S	Béni Egressy	FS 20

Béni Egressy

Publications

Theses & Labs

Available Theses & Labs

Past Theses & Labs