Portrait of Leo Feng is unavailable

Leo Feng

leo.feng@mila.quebec
PhD - Université de Montréal
Supervisor
Yoshua Bengio
Research Topics
Deep Learning
Website
Google Scholar

Publications

Memory Efficient Neural Processes via Constant Memory Attention Block
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
proceedings.mlr.press
openreview.net
Attention as an RNN
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Mohamed Osama Ahmed
Yoshua Bengio
Greg Mori
The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of le… (see more)veraging GPU parallelism. However, Transformers are computationally expensive at inference time, limiting their applications, particularly in low-resource settings (e.g., mobile and embedded devices). Addressing this, we (1) begin by showing that attention can be viewed as a special Recurrent Neural Network (RNN) with the ability to compute its \textit{many-to-one} RNN output efficiently. We then (2) show that popular attention-based models such as Transformers can be viewed as RNN variants. However, unlike traditional RNNs (e.g., LSTMs), these models cannot be updated efficiently with new tokens, an important property in sequence modelling. Tackling this, we (3) introduce a new efficient method of computing attention's \textit{many-to-many} RNN output based on the parallel prefix scan algorithm. Building on the new attention formulation, we (4) introduce \textbf{Aaren}, an attention-based module that can not only (i) be trained in parallel (like Transformers) but also (ii) be updated efficiently with new tokens, requiring only constant memory for inferences (like traditional RNNs). Empirically, we show Aarens achieve comparable performance to Transformers on
2024-05-22
ArXiv (preprint)
doi.org
arxiv.org
Attention as an RNN
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Mohamed Osama Ahmed
Yoshua Bengio
Greg Mori
2024-05-22
ArXiv (preprint)
doi.org
arxiv.org
Attention as an RNN
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Mohamed Osama Ahmed
Yoshua Bengio
Greg Mori
The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of le… (see more)veraging GPU parallelism. However, Transformers are computationally expensive at inference time, limiting their applications, particularly in low-resource settings (e.g., mobile and embedded devices). Addressing this, we (1) begin by showing that attention can be viewed as a special Recurrent Neural Network (RNN) with the ability to compute its \textit{many-to-one} RNN output efficiently. We then (2) show that popular attention-based models such as Transformers can be viewed as RNN variants. However, unlike traditional RNNs (e.g., LSTMs), these models cannot be updated efficiently with new tokens, an important property in sequence modelling. Tackling this, we (3) introduce a new efficient method of computing attention's \textit{many-to-many} RNN output based on the parallel prefix scan algorithm. Building on the new attention formulation, we (4) introduce \textbf{Aaren}, an attention-based module that can not only (i) be trained in parallel (like Transformers) but also (ii) be updated efficiently with new tokens, requiring only constant memory for inferences (like traditional RNNs). Empirically, we show Aarens achieve comparable performance to Transformers on
2024-05-22
ArXiv (preprint)
doi.org
arxiv.org
Attention as an RNN
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Mohamed Osama Ahmed
Yoshua Bengio
Greg Mori
2024-05-22
ArXiv (preprint)
doi.org
arxiv.org
Generative Active Learning for the Search of Small-molecule Protein Binders
Maksym Korablyov
Cheng-Hao Liu
Moksh J. Jain
Almer M. van der Sloot
Eric Jolicoeur
Edward Ruediger
Andrei Cristian Nica
Emmanuel Bengio
Kostiantyn Lapchevskyi
Daniel St-Cyr
Doris Alexandra Schuetz
Victor I Butoi
Jarrid Rector-Brooks
Simon R. Blackburn
Leo Feng
Hadi Nekoei
Sai Krishna Gottipati
Priyesh Vijayan
Prateek Gupta
Ladislav Rampášek … (see 14 more)
Sasikanth Avancha
Pierre-Luc Bacon
William L. Hamilton
Brooks Paige
Sanchit Misra
Stanisław Jastrzębski
Bharat Kaul
Doina Precup
José Miguel Hernández-Lobato
Marwin Segler
Michael M. Bronstein
Anne Marinier
Mike Tyers
Yoshua Bengio
Despite substantial progress in machine learning for scientific discovery in recent years, truly de novo design of small molecules which exh… (see more)ibit a property of interest remains a significant challenge. We introduce LambdaZero, a generative active learning approach to search for synthesizable molecules. Powered by deep reinforcement learning, LambdaZero learns to search over the vast space of molecules to discover candidates with a desired property. We apply LambdaZero with molecular docking to design novel small molecules that inhibit the enzyme soluble Epoxide Hydrolase 2 (sEH), while enforcing constraints on synthesizability and drug-likeliness. LambdaZero provides an exponential speedup in terms of the number of calls to the expensive molecular docking oracle, and LambdaZero de novo designed molecules reach docking scores that would otherwise require the virtual screening of a hundred billion molecules. Importantly, LambdaZero discovers novel scaffolds of synthesizable, drug-like inhibitors for sEH. In in vitro experimental validation, a series of ligands from a generated quinazoline-based scaffold were synthesized, and the lead inhibitor N-(4,6-di(pyrrolidin-1-yl)quinazolin-2-yl)-N-methylbenzamide (UM0152893) displayed sub-micromolar enzyme inhibition of sEH.
2024-05-02
ArXiv (preprint)
doi.org
arxiv.org
Memory Efficient Neural Processes via Constant Memory Attention Block
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, … (see more)however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource settings. In this work, we propose Constant Memory Attention Block (CMAB), a novel general-purpose attention block that (1) is permutation invariant, (2) computes its output in constant memory, and (3) performs updates in constant computation. Building on CMAB, we propose Constant Memory Attentive Neural Processes (CMANPs), an NP variant which only requires \textbf{constant} memory. Empirically, we show CMANPs achieve state-of-the-art results on popular NP benchmarks (meta-regression and image completion) while being significantly more memory efficient than prior methods.
2024-05-01
ICML.cc/2024/Conference (poster)
openreview.net
openreview.net
Tree Cross Attention
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for e… (see more)ach prediction, Cross Attention scans the full set of
2024-01-16
ICLR.cc/2024/Conference (poster)
openreview.net
openreview.net
Tree Cross Attention
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
2023-09-29
ArXiv (preprint)
doi.org
arxiv.org
Tree Cross Attention
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
2023-09-29
ArXiv (preprint)
doi.org
arxiv.org
Constant Memory Attention Block
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
2023-06-20
ICML.cc/2023/Workshop/ES-FoMO (poster)
doi.org
openreview.net
Latent Bottlenecked Attentive Neural Processes
Leo Feng
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on… (see more) a context dataset. Previous state-of-the-art method Transformer Neural Processes (TNPs) achieve strong performance but require quadratic computation with respect to the number of context datapoints, significantly limiting its scalability. Conversely, existing sub-quadratic NP variants perform significantly worse than that of TNPs. Tackling this issue, we propose Latent Bottlenecked Attentive Neural Processes (LBANPs), a new computationally efficient sub-quadratic NP variant, that has a querying computational complexity independent of the number of context datapoints. The model encodes the context dataset into a constant number of latent vectors on which self-attention is performed. When making predictions, the model retrieves higher-order information from the context dataset via multiple cross-attention mechanisms on the latent vectors. We empirically show that LBANPs achieve results competitive with the state-of-the-art on meta-regression, image completion, and contextual multi-armed bandits. We demonstrate that LBANPs can trade-off the computational cost and performance according to the number of latent vectors. Finally, we show LBANPs can scale beyond existing attention-based NP variants to larger dataset settings.
2023-02-01
ICLR.cc/2023/Conference (poster)
doi.org
openreview.net