no code implementations • 12 Mar 2024 • Michael Rizvi, Maude Lizaire, Clara Lacroce, Guillaume Rabusseau
Recent work has shown that these models can compactly simulate the sequential reasoning abilities of deterministic finite automata (DFAs).
no code implementations • 31 Oct 2023 • Alex Meiburg, Jing Chen, Jacob Miller, Raphaëlle Tihon, Guillaume Rabusseau, Alejandro Perdomo-Ortiz
Beyond their origin in modeling many-body quantum systems, tensor networks have emerged as a promising class of models for solving machine learning problems, notably in unsupervised generative learning.
1 code implementation • 6 Oct 2023 • Dominique Beaini, Shenyang Huang, Joao Alex Cunha, Zhiyi Li, Gabriela Moisescu-Pareja, Oleksandr Dymov, Samuel Maddrell-Mander, Callum McLean, Frederik Wenkel, Luis Müller, Jama Hussein Mohamud, Ali Parviz, Michael Craig, Michał Koziarski, Jiarui Lu, Zhaocheng Zhu, Cristian Gabellini, Kerstin Klaser, Josef Dean, Cas Wognum, Maciej Sypetkowski, Guillaume Rabusseau, Reihaneh Rabbany, Jian Tang, Christopher Morris, Ioannis Koutis, Mirco Ravanelli, Guy Wolf, Prudencio Tossou, Hadrien Mary, Therence Bois, Andrew Fitzgibbon, Błażej Banaszewski, Chad Martin, Dominic Masters
Recently, pre-trained foundation models have enabled significant advancements in multiple fields.
2 code implementations • NeurIPS 2023 • Shenyang Huang, Farimah Poursafaei, Jacob Danovitch, Matthias Fey, Weihua Hu, Emanuele Rossi, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, Reihaneh Rabbany
We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs.
2 code implementations • 15 May 2023 • Shenyang Huang, Jacob Danovitch, Guillaume Rabusseau, Reihaneh Rabbany
Current solutions do not scale well to large real-world graphs, lack robustness to large amounts of node additions/deletions, and overlook changes in node attributes.
2 code implementations • 2 Feb 2023 • Shenyang Huang, Samy Coulombe, Yasmeen Hitti, Reihaneh Rabbany, Guillaume Rabusseau
how to capture temporal dependencies, and iii).
1 code implementation • 4 Nov 2022 • Kaiwen Hou, Guillaume Rabusseau
Various forms of regularization in learning tasks strive for different notions of simplicity.
no code implementations • 8 Jun 2022 • Tianyu Li, Bogdan Mazoure, Guillaume Rabusseau
Although WFAs have been extended to deal with continuous input data, namely continuous WFAs (CWFAs), it is still unclear how to approximate density functions over sequences of continuous random variables using WFA-based models, due to the limitation on the expressiveness of the model as well as the tractability of approximating density functions via CWFAs.
no code implementations • 24 May 2022 • Chenqing Hua, Guillaume Rabusseau, Jian Tang
Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data.
no code implementations • NeurIPS 2021 • Behnoush Khavari, Guillaume Rabusseau
These results are used to derive a generalization bound which can be applied to classification with low rank matrices as well as linear classifiers based on any of the commonly used tensor decomposition models.
no code implementations • 26 Oct 2021 • Beheshteh T. Rakhshan, Guillaume Rabusseau
Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimension of very high-dimensional tensors.
no code implementations • 22 Jun 2021 • Behnoush Khavari, Guillaume Rabusseau
These results are used to derive a generalization bound which can be applied to classification with low rank matrices as well as linear classifiers based on any of the commonly used tensor decomposition models.
no code implementations • 5 Jun 2021 • Clara Lacroce, Prakash Panangaden, Guillaume Rabusseau
The objective is to obtain a weighted finite automaton (WFA) that fits within a given size constraint and which mimics the behaviour of the original model while minimizing some notion of distance between the black box and the extracted WFA.
no code implementations • 13 Jan 2021 • Greta Laage, Emma Frejinger, Andrea Lodi, Guillaume Rabusseau
This is a challenging problem as it corresponds to the difference between the generated value and the value that would have been generated keeping the system as before.
no code implementations • 20 Oct 2020 • Siddarth Srinivasan, Sandesh Adhikary, Jacob Miller, Guillaume Rabusseau, Byron Boots
We address this gap by showing how stationary or uniform versions of popular quantum tensor network models have equivalent representations in the stochastic processes and weighted automata literature, in the limit of infinitely long sequences.
no code implementations • 19 Oct 2020 • Tianyu Li, Doina Precup, Guillaume Rabusseau
In this paper, we present connections between three models used in different research fields: weighted finite automata~(WFA) from formal languages and linguistics, recurrent neural networks used in machine learning, and tensor networks which encompasses a set of optimization techniques for high-order tensors used in quantum physics and numerical analysis.
2 code implementations • 7 Oct 2020 • Thang Doan, Mehdi Bennani, Bogdan Mazoure, Guillaume Rabusseau, Pierre Alquier
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime.
no code implementations • 12 Aug 2020 • Meraj Hashemizadeh, Michelle Liu, Jacob Miller, Guillaume Rabusseau
However, identifying the best tensor network structure from data for a given task is challenging.
1 code implementation • 2 Jul 2020 • Shenyang Huang, Yasmeen Hitti, Guillaume Rabusseau, Reihaneh Rabbany
To solve the above challenges, we propose Laplacian Anomaly Detection (LAD) which uses the spectrum of the Laplacian matrix of the graph structure at each snapshot to obtain low dimensional embeddings.
no code implementations • 11 Mar 2020 • Beheshteh T. Rakhshan, Guillaume Rabusseau
We introduce a novel random projection technique for efficiently reducing the dimension of very high-dimensional tensors.
no code implementations • 2 Mar 2020 • Stefano Alletto, Shenyang Huang, Vincent Francois-Lavet, Yohei Nakata, Guillaume Rabusseau
Almost all neural architecture search methods are evaluated in terms of performance (i. e. test accuracy) of the model structures that it finds.
1 code implementation • 2 Mar 2020 • Jacob Miller, Guillaume Rabusseau, John Terilla
Tensor networks are a powerful modeling framework developed for computational many-body physics, which have only recently been applied within machine learning.
no code implementations • 7 Feb 2020 • Bogdan Mazoure, Thang Doan, Tianyu Li, Vladimir Makarenkov, Joelle Pineau, Doina Precup, Guillaume Rabusseau
We propose a general framework for policy representation for reinforcement learning tasks.
no code implementations • 12 Nov 2019 • Tianyu Li, Bogdan Mazoure, Doina Precup, Guillaume Rabusseau
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning.
no code implementations • 14 Sep 2019 • Shenyang Huang, Vincent François-Lavet, Guillaume Rabusseau
To understand how to expand a continual learner, we focus on the neural architecture design problem in the context of class-incremental learning: at each time step, the learner must optimize its performance on all classes observed so far by selecting the most competitive neural architecture.
1 code implementation • 18 Dec 2018 • Kian Kenyon-Dean, Andre Cianflone, Lucas Page-Caccia, Guillaume Rabusseau, Jackie Chi Kit Cheung, Doina Precup
The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective.
1 code implementation • NeurIPS 2017 • Matteo Ruffini, Guillaume Rabusseau, Borja Balle
Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models.
no code implementations • ICLR 2018 • Eric Crawford, Guillaume Rabusseau, Joelle Pineau
Achieving machine intelligence requires a smooth integration of perception and reasoning, yet models developed to date tend to specialize in one or the other; sophisticated manipulation of symbols acquired from rich perceptual spaces has so far proved elusive.
no code implementations • 4 Jul 2018 • Guillaume Rabusseau, Tianyu Li, Doina Precup
In this paper, we unravel a fundamental connection between weighted finite automata~(WFAs) and second-order recurrent neural networks~(2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent.
no code implementations • 21 Jun 2018 • Philip Amortila, Guillaume Rabusseau
Graph Weighted Models (GWMs) have recently been proposed as a natural generalization of weighted automata over strings and trees to arbitrary families of labeled graphs (and hypergraphs).
2 code implementations • 27 Dec 2017 • Xingwei Cao, Guillaume Rabusseau
We evaluate the compressive and regularization performances of the proposed model with both deep and shallow convolutional neural networks.
no code implementations • NeurIPS 2017 • Guillaume Rabusseau, Borja Balle, Joelle Pineau
We first present a natural notion of relatedness between WFAs by considering to which extent several WFAs can share a common underlying representation.
no code implementations • 22 Sep 2017 • Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability.
no code implementations • 13 Sep 2017 • Tianyu Li, Guillaume Rabusseau, Doina Precup
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models.
no code implementations • NeurIPS 2016 • Guillaume Rabusseau, Hachem Kadri
This paper proposes an efficient algorithm (HOLRR) to handle regression tasks where the outputs have a tensor structure.
no code implementations • 22 Feb 2016 • Guillaume Rabusseau, Hachem Kadri
This paper proposes an efficient algorithm (HOLRR) to handle regression tasks where the outputs have a tensor structure.
no code implementations • 4 Nov 2015 • Guillaume Rabusseau, Borja Balle, Shay B. Cohen
We describe a technique to minimize weighted tree automata (WTA), a powerful formalisms that subsumes probabilistic context-free grammars (PCFGs) and latent-variable PCFGs.
no code implementations • 17 Mar 2014 • Guillaume Rabusseau, François Denis
Building upon a recent paper on tensor decompositions for learning latent variable models, we extend this work to the broader setting of tensors having a symmetric decomposition with positive and negative weights.