1

Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as …
Dingling Yao, Danru Xu, Sebastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius Von K\:uglen, Francesco Locatello
Cite
A Sparsity Principle for Partially Observable Causal Representation Learning
Causal representation learning (CRL) aims at identifying high-level causal variables from low-level data, e.g. images. Current methods …
Danru Xu, Dingling Yao, Sebastien Lachapelle, Perouz Taslakian, Julius Von K\:uglen, Francesco Locatello, Sara Magliacane
Cite
Capture the Flag: Uncovering Data Insights with Large Language Models
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. …
Issam Laradji, Perouz Taslakian, Sai Rajeswar, Valentina Zantedeschi, Alexandre Lacoste, Nicolas Chapados, David Vazquez, Christopher Pal, Alexandre Drouin
Cite
Explaining Graph Neural Networks Using Interpretable Local Surrogates
We propose an interpretable local surrogate (ILS) method for understanding the predictions of black-box graph models. Explainability …
Farzaneh Heidari, Perouz Taslakian, Guillaume Rabusseau
Cite
OC-NMN : Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
A key aspect of human intelligence is the ability to imagine — composing learned concepts in novel ways — to make sense of new …
Pau Rodriguez, Perouz Taslakian, David Vazquez, Yoshua Bengio Rim Assouel
Cite
Typing assumptions improve identification in causal discovery
Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. Under …
Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sebastien Lachapelle, Drouin Alexandre
Cite URL
Knowledge Hypergraphs: Prediction Beyond Binary Relations
Knowledge graphs store facts using relations between two entities. In this work, we address the question of link prediction in …
Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole
Cite URL
Context-aware visual compatibility prediction
How do we determine whether two or more clothing items are compatible or visually appealing? Part of the answer lies in understanding …
Guillem Cucurull, Perouz Taslakian, David Vazquez
Cite URL
Efficient multi-robot coverage of a known environment
This paper addresses the complete area coverage problem of a known environment by multiple-robots. Complete area coverage is the …
Nare Karapetyan, Kelly Benson, Chris McKinney, Perouz Taslakian, Ioannis Rekleitis
Cite URL
Continuous Yao Graphs
In this paper, we introduce a variation of the well-studied Yao graphs. Given a set of points $S⊂ ℝ^2$ and an angle $0 < Θ łeq 2π$, …
Luis Barba, Prosenjit Bose, Jean-Lou De Carufel, Mirel Damian, Rolf Fagerberg, André van Renssen, Perouz Taslakian, Sander Verdonschot
Cite URL