Publications

A portrait of the different configurations between digitally-enabled innovations and climate governance
Pierre J. C. Chuard
Jennifer Garard
Karsten A. Schulz
Nilushi Kumarasinghe
David Rolnick
Damon Matthews
2022-08-01
Earth System Governance (publié)
doi.org
The generalizability of pre-processing techniques on the accuracy and fairness of data-driven building models: a case study
Ying Sun
Benjamin Fung
Fariborz Haghighat
2022-08-01
Energy and Buildings (publié)
doi.org
Single‐pass stratified importance resampling
Ege Ciklabakkal
Adrien Gruson
Iliyan Georgiev
Derek Nowrouzezahrai
Toshiya Hachisuka
Resampling is the process of selecting from a set of candidate samples to achieve a distribution (approximately) proportional to a desired t… (voir plus)arget. Recent work has revisited its application to Monte Carlo integration, yielding powerful and practical importance sampling methods. One drawback of existing resampling methods is that they cannot generate stratified samples. We propose two complementary techniques to achieve efficient stratified resampling. We first introduce bidirectional CDF sampling which yields the same result as conventional inverse CDF sampling but in a single pass over the candidates, without needing to store them, similarly to reservoir sampling. We then order the candidates along a space‐filling curve to ensure that stratified CDF sampling of candidate indices yields stratified samples in the integration domain. We showcase our method on various resampling‐based rendering problems.
2022-07-30
Computer Graphics Forum (publié)
doi.org
Automated prediction of extubation success in extremely preterm infants: the APEX multicenter study
Lara Kanbar
Wissam Shalish
Charles Onu
Samantha Latremouille
Lajos Kovacs
Martin Keszler
Sanjay Chawla
Karen A. Brown
Doina Precup
R. Kearney
Guilherme M. Sant’Anna
2022-07-29
Pediatric Research (publié)
doi.org
BioCaster in 2021: automatic disease outbreaks detection from global news media
Zaiqiao Meng
Anya Okhmatovskaia
Maxime Polleri
Yannan Shen
Guido Powell
Zihao Fu
Iris Ganser
Meiru Zhang
Nicholas B King
David Buckeridge
Nigel Collier
2022-07-28
Bioinformatics (publié)
doi.org
A parsimonious description of global functional brain organization in three spatiotemporal patterns
Taylor Bolt
Jason S. Nomi
Danilo Bzdok
Jorge A. Salas
Catie Chang
B.T. Thomas Yeo
Lucina Q. Uddin
Shella Keilholz
2022-07-28
Nature Neuroscience (publié)
doi.org
Explanatory latent representation of heterogeneous spatial maps of task-fMRI in large-scale datasets
Mariam Zabihi
Seyed Mostafa Kia
Thomas Wolfers
Stijn de Boer
C. Fraza
Sourena Soheili‐nezhad
Richard Dinga
Alberto Llera
Danilo Bzdok
Christian Beckmann
Andre Marquand
2022-07-27
bioRxiv (prépublication)
doi.org
Global fMRI signal topography differs systematically across the lifespan
Jason S. Nomi
Danilo Bzdok
Jingwei Li
Taylor Bolt
Catie Chang
Salome Kornfeld
Zachary T. Goodman
B.T. Thomas Yeo
R. Nathan Spreng
Lucina Q. Uddin
2022-07-27
bioRxiv (prépublication)
doi.org
H4rm0ny: A Competitive Zero-Sum Two-Player Markov Game for Multi-Agent Learning on Evasive Malware Generation and Detection
Christopher Molloy
Steven H. H. Ding
Benjamin Fung
Philippe Charland
To combat the increasingly versatile and mutable modern malware, Machine Learning (ML) is now a popular and effective complement to the exis… (voir plus)ting signature-based techniques for malware triage and identification. However, ML is also a readily available tool for adversaries. Recent studies have shown that malware can be modified by deep Reinforcement Learning (RL) techniques to bypass AI-based and signature-based anti-virus systems without altering their original malicious functionalities. These studies only focus on generating evasive samples and assume a static detection system as the enemy.Malware detection and evasion essentially form a two-party cat-and-mouse game. Simulating the real-life scenarios, in this paper we present the first two-player competitive game for evasive malware detection and generation, following the zero-sum Multi-Agent Reinforcement Learning (MARL) paradigm. Our experiments on recent malware show that the produced malware detection agent is more robust against adversarial attacks. Also, the produced malware modification agent is able to generate more evasive samples fooling both AI-based and other anti-malware techniques.
2022-07-27
Computer Science Symposium in Russia (publié)
doi.org
Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs
Stephen Bonner
Ufuk Kirik
Ola Engkvist
Jian Tang
Ian P Barrett
Adoption of recently developed methods from machine learning has given rise to creation of drug-discovery knowledge graphs (KGs) that utiliz… (voir plus)e the interconnected nature of the domain. Graph-based modelling of the data, combined with KG embedding (KGE) methods, are promising as they provide a more intuitive representation and are suitable for inference tasks such as predicting missing links. One common application is to produce ranked lists of genes for a given disease, where the rank is based on the perceived likelihood of association between the gene and the disease. It is thus critical that these predictions are not only pertinent but also biologically meaningful. However, KGs can be biased either directly due to the underlying data sources that are integrated or due to modelling choices in the construction of the graph, one consequence of which is that certain entities can get topologically overrepresented. We demonstrate the effect of these inherent structural imbalances, resulting in densely connected entities being highly ranked no matter the context. We provide support for this observation across different datasets, models as well as predictive tasks. Further, we present various graph perturbation experiments which yield more support to the observation that KGE models can be more influenced by the frequency of entities rather than any biological information encoded within the relations. Our results highlight the importance of data modelling choices, and emphasizes the need for practitioners to be mindful of these issues when interpreting model outputs and during KG composition.
2022-07-26
Briefings in Bioinformatics (publié)
doi.org
arxiv.org
On the Expressivity of Markov Reward (Extended Abstract)
David Abel
Will Dabney
Anna Harutyunyan
Mark K. Ho
Michael L. Littman
Doina Precup
Satinder Singh
2022-07-23
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence (publié)
doi.org
Flaky Performances when Pre-Training on Relational Databases with a Plan for Future Characterization Efforts
Shengchao Liu
David Vazquez
Jian Tang
Pierre-Andre Noel
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extra… (voir plus)cted from relational databases (RDBs). Intu-itively, this joint use of SSL and GNNs allows us to leverage more of the available data, which could translate to better results. However, while we observe positive transfer in some cases, others showed systematic performance degradation, including some spectacular ones. We hypothesize a mechanism that could explain this behaviour and draft the plan for future work testing it by characterizing how much relevant information different strategies can (theoretically and/or empirically) extract from (synthetic and/or real) RDBs.
2022-07-22
ICML.cc/2022/Workshop/Pre-Training (accepté)
openreview.net
openreview.net