Portrait of Siamak Ravanbakhsh

Siamak Ravanbakhsh

Core Academic Member
siamak.ravanbakhsh@mila.quebec
Canada CIFAR AI Chair
Assistant Professor, McGill University, School of Computer Science
Website
Google Scholar

Biography

Siamak Ravanbakhsh is an assistant professor at McGill University’s School of Computer Science and a core academic member of Mila – Quebec Artificial Intelligence Institute.

Before joining McGill and Mila, he held a similar position at the University of British Columbia. Prior to that, he was a postdoctoral fellow at the Machine Learning Department and Robotics Institute of Carnegie Mellon University. He completed his PhD at the University of Alberta.

Ravanbakhsh’s research is centred around problems of representation learning, in particular the principled use of geometry, probabilistic inference and symmetry.

Current Students

Arnab Kumar-Mondal
PhD - McGill University
Co-supervisor :
Kaleem Siddiqi
arnab.mondal@mila.quebec
Website
Github
Google Scholar
Daniel Levy
PhD - McGill University
daniel.levy@mila.quebec
Github
Google Scholar
Han Du Han
Professional Master's - McGill University
du.han@mila.quebec
Website
Github
Fabricio Dos Santos
Research Intern - McGill University
fabricio.dos-santos@mila.quebec
Jikael Gagnon
Research Intern - McGill University
jikael.gagnon@mila.quebec
Github
Julie Hlavacek-Larrondo
Independent visiting researcher
julie.larrondo@mila.quebec
Alan Yang
Professional Master's - McGill University
kai-yam.yang@mila.quebec
Website
Kusha Sareen
Collaborating researcher - see above
kusha.sareen@mila.quebec
Website
Github
Mahsa Massoud
Master's Research - McGill University
mahsa.massoud@mila.quebec
Mary Letey
Collaborating researcher
mary.letey@mila.quebec
Website
Github
Google Scholar
Mehran Shakerinava
PhD - McGill University
mehran.shakerinava@mila.quebec
Google Scholar
Mohammad Pedramfar
Postdoctorate - McGill University
mohammad.pedramfar@mila.quebec
Oumar Kaba
PhD - McGill University
kabaseko@mila.quebec
Website
Github
Google Scholar
Siba Smarak Panigrahi
Master's Research - McGill University
siba-smarak.panigrahi@mila.quebec
Website
Github
Google Scholar
Tara Akhound-Sadegh
PhD - McGill University
Co-supervisor :
Laurence Perreault-Levasseur
tara.akhoundsadegh@mila.quebec
Victor Livernoche
Master's Research - McGill University
victor.livernoche@mila.quebec
Github
Vineet Jain
PhD - McGill University
jain.vineet@mila.quebec
Xiusi Li
Master's Research - McGill University
xiusi.li@mila.quebec

Publications

Lie Point Symmetry and Physics-Informed Networks
Tara Akhound-Sadegh
Laurence Perreault-Levasseur
Johannes Brandstetter
Max Welling
Siamak Ravanbakhsh
Symmetries have been leveraged to improve the generalization of neural networks through different mechanisms from data augmentation to equiv… (see more)ariant architectures. However, despite their potential, their integration into neural solvers for partial differential equations (PDEs) remains largely unexplored. We explore the integration of PDE symmetries, known as Lie point symmetries, in a major family of neural solvers known as physics-informed neural networks (PINNs). We propose a loss function that informs the network about Lie point symmetries in the same way that PINN models try to enforce the underlying PDE through a loss function. Intuitively, our symmetry loss ensures that the infinitesimal generators of the Lie group conserve the PDE solutions.. Effectively, this means that once the network learns a solution, it also learns the neighbouring solutions generated by Lie point symmetries. Empirical evaluations indicate that the inductive bias introduced by the Lie point symmetries of the PDEs greatly boosts the sample efficiency of PINNs.
openreview.net
Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks
Daniel Levy
Sékou-Oumar Kaba
Carmelo Gonzales
Santiago Miret
Siamak Ravanbakhsh
2023-09-06
ArXiv (preprint)
doi.org
arxiv.org
Equivariance with Learned Canonicalization Functions
Sékou-Oumar Kaba
Arnab Kumar Mondal
Yan Zhang
Yoshua Bengio
Siamak Ravanbakhsh
2023-07-03
Proceedings of the 40th International Conference on Machine Learning (published)
doi.org
openreview.net
Equivariance With Learned Canonicalization Functions
Sékou-Oumar Kaba
Arnab Kumar Mondal
Yan Zhang
Yoshua Bengio
Siamak Ravanbakhsh
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations… (see more). In this paper, we propose an alternative that avoids this architectural constraint by learning to produce a canonical representation of the data. These canonicalization functions can readily be plugged into non-equivariant backbone architectures. We offer explicit ways to implement them for many groups of interest. We show that this approach enjoys universality while providing interpretable insights. Our main hypothesis is that learning a neural network to perform canonicalization is better than doing it using predefined heuristics. Our results show that learning the canonicalization function indeed leads to better results and that the approach achieves great performance in practice.
2023-04-24
ICML.cc/2023/Conference (poster)
doi.org
openreview.net
Characterization Of Inpaint Residuals In Interferometric Measurements of the Epoch Of Reionization
Michael Pagano
Jing Liu
Adrian Liu
Nicholas S Kern
Aaron Ewall-Wice
Philip Bull
Robert Pascua
Siamak Ravanbakhsh
Zara Abdurashidova
Tyrone Adams
James E Aguirre
Paul Alexander
Zaki S Ali
Rushelle Baartman
Yanga Balfour
Adam P Beardsley
Gianni Bernardi
Tashalee S Billings
Judd D Bowman
Richard F Bradley … (see 58 more)
Jacob Burba
Steven Carey
Chris L Carilli
Carina Cheng
David R DeBoer
Eloy de Lera Acedo
Matt Dexter
Joshua S Dillon
Nico Eksteen
John Ely
Nicolas Fagnoni
Randall Fritz
Steven R Furlanetto
Kingsley Gale-Sides
Brian Glendenning
Deepthi Gorthi
Bradley Greig
Jasper Grobbelaar
Ziyaad Halday
Bryna J Hazelton
Jacqueline N Hewitt
Jack Hickish
Daniel C Jacobs
Austin Julius
MacCalvin Kariseb
Joshua Kerrigan
Piyanat Kittiwisit
Saul A Kohn
Matthew Kolopanis
Adam Lanman
Paul La Plante
Anita Loots
David Harold Edward MacMahon
Lourence Malan
Cresshim Malgas
Keith Malgas
Bradley Marero
Zachary E Martinot
Andrei Mesinger
Mathakane Molewa
Miguel F Morales
Tshegofalang Mosiane
Abraham R Neben
Bojan Nikolic
Hans Nuwegeld
Aaron R Parsons
Nipanjana Patra
Samantha Pieterse
Nima Razavi-Ghods
James Robnett
Kathryn Rosie
Peter Sims
Craig Smith
Hilton Swarts
Nithyanandan Thyagarajan
Pieter van Wyngaarden
Peter K G Williams
Haoxuan Zheng
To mitigate the effects of Radio Frequency Interference (RFI) on the data analysis pipelines of 21cm interferometric instruments, numerous i… (see more)npaint techniques have been developed. In this paper we examine the qualitative and quantitative errors introduced into the visibilities and power spectrum due to inpainting. We perform our analysis on simulated data as well as real data from the Hydrogen Epoch of Reionization Array (HERA) Phase 1 upper limits. We also introduce a convolutional neural network that is capable of inpainting RFI corrupted data. We train our network on simulated data and show that our network is capable at inpainting real data without requiring to be retrained. We find that techniques that incorporate high wavenumbers in delay space in their modeling are best suited for inpainting over narrowband RFI. We show that with our fiducial parameters Discrete Prolate Spheroidal Sequences (DPSS) and CLEAN provide the best performance for intermittent RFI while Gaussian Progress Regression (GPR) and Least Squares Spectral Analysis (LSSA) provide the best performance for larger RFI gaps. However we caution that these qualitative conclusions are sensitive to the chosen hyperparameters of each inpainting technique. We show that all inpainting techniques reliably reproduce foreground dominated modes in the power spectrum. Since the inpainting techniques should not be capable of reproducing noise realizations, we find that the largest errors occur in the noise dominated delay modes. We show that as the noise level of the data comes down, CLEAN and DPSS are most capable of reproducing the fine frequency structure in the visibilities.
2023-02-10
Monthly Notices of the Royal Astronomical Society (published)
doi.org
arxiv.org
Physics-Informed Transformer Networks
F. Dos
Santos
Tara Akhound-Sadegh
Siamak Ravanbakhsh
Physics-informed neural networks (PINNs) have been recognized as a viable alternative to conventional numerical solvers for Partial Differen… (see more)tial Equations (PDEs). The main appeal of PINNs is that since they directly enforce the PDE equation, one does not require access to costly ground truth solutions for training the model. However, a key challenge is their limited generalization across varied initial conditions. Addressing this, our study presents a novel Physics-Informed Transformer (PIT) model for learning the solution operator for PDEs. Using the attention mechanism, PIT learns to leverage the relationships between its initial condition and query points, resulting in a significant improvement in generalization. Moreover, in contrast to existing physics-informed networks, our model is invariant to the discretization of the input domain, providing great flexibility in problem specification and training. We validated our proposed method on the 1D Burgers’ and the 2D Heat equations, demonstrating notable improvement over standard PINN models for operator learning with negligible computational overhead.
2000-01-01
(published)
www.semanticscholar.org