Unit
Data Science Laboratory
LaboratoryRelated publications (103)
Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning
The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...
EPFL2024Robust machine learning for neuroscientific inference
Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...
EPFL2024Content Moderation in Online Platforms
A critical role of online platforms like Facebook, Wikipedia, YouTube, Amazon, Doordash, and Tinder is to moderate content. Interventions like banning users or deleting comments are carried out thousands of times daily and can potentially improve our onlin ...
EPFL2024Measuring and shaping the nutritional environment via food sales logs: case studies of campus-wide food choice and a call to action
Robert West, Robin Adrien Zbinden, Kristina Gligoric
Although diets influence health and the environment, measuring and changing nutrition is challenging. Traditional measurement methods face challenges, and designing and conducting behavior-changing interventions is conceptually and logistically complicated ...
Frontiers Media Sa2024Transformer Models for Vision
Jean-Baptiste Francis Marie Juliette Cordonnier
The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins.All these successful methods depend on a gradient-based learning algorithm to train a model on massive a ...
EPFL2023Language Model Decoding as Likelihood–Utility Alignment
Boi Faltings, Robert West, Maxime Jean Julien Peyrard, Martin Josifoski, Valentin Hartmann, Debjit Paul, Jiheng Wei, Frano Rajic
A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re- main unclear. Previous works only compare decoding algorithms in narrow sc ...
2023Equivariant Neural Architectures for Representing and Generating Graphs
Graph machine learning offers a powerful framework with natural applications in scientific fields such as chemistry, biology and material sciences. By representing data as a graph, we encode the prior knowledge that the data is composed of a set of entitie ...
EPFL2023Text Representation Learning for Low Cost Natural Language Understanding
Jan Frederik Jonas Florian Mai
Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...
EPFL2023Distribution Inference Risks: Identifying and Mitigating Sources of Leakage
Robert West, Maxime Jean Julien Peyrard, Valentin Hartmann, Léo Nicolas René Meynent
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the ...
IEEE COMPUTER SOC2023Monotonicity Reasoning in the Age of Neural Foundation Models
The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...
Dordrecht2023