Eugene Belilovsky

Adversarial Attacks on the Interpretation of Neuron Activation Maximization

G'eraldin Nanfack

Alexander Fulleringer

Jonathan Marty

Michael Eickenberg

Feature visualization is one of the most popular techniques used to interpret the internal behavior of individual units of trained deep neur… (see more)al networks. Based on activation maximization, they consist of finding synthetic or natural inputs that maximize neuron activations. This paper introduces an optimization framework that aims to deceive feature visualization through adversarial model manipulation. It consists of finetuning a pre-trained model with a specifically introduced loss that aims to maintain model performance, while also significantly changing feature visualization. We provide evidence of the success of this manipulation on several pre-trained models for the classification task with ImageNet.

2024-03-24

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim

Benjamin Thérien

Kshitij Gupta

Mats Leon Richter

Quentin Gregory Anthony

Timothee LESORT

Eugene Belilovsky

Irina Rish

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (see more)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English

2024-03-13

ArXiv (preprint)

doi.org

arxiv.org

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim

Benjamin Thérien

Kshitij Gupta

Mats Leon Richter

Quentin Anthony

Timothee LESORT

Eugene Belilovsky

Irina Rish

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (see more)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English

2024-03-13

ArXiv (preprint)

doi.org

arxiv.org

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim

Benjamin Thérien

Kshitij Gupta

Mats Leon Richter

Quentin Gregory Anthony

Timothee LESORT

Eugene Belilovsky

Irina Rish

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (see more)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English

2024-03-13

ArXiv (preprint)

doi.org

arxiv.org

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim

Benjamin Thérien

Kshitij Gupta

Mats Leon Richter

Quentin Gregory Anthony

Timothee LESORT

Eugene Belilovsky

Irina Rish

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (see more)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English

2024-03-13

ArXiv (preprint)

doi.org

arxiv.org

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim

Benjamin Thérien

Kshitij Gupta

Mats Leon Richter

Quentin Gregory Anthony

Timothee LESORT

Eugene Belilovsky

Irina Rish

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes ava… (see more)ilable. A much more efficient solution is to continually pre-train these models, saving significant compute compared to re-training. However, the distribution shift induced by new data typically results in degraded performance on previous data or poor adaptation to the new data. In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks. Specifically, we show this for a weak but realistic distribution shift between two commonly used LLM pre-training datasets (English

2024-03-13

ArXiv (preprint)

doi.org

arxiv.org

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Stefan Horoi

Albert Manuel Orozco Camacho

Eugene Belilovsky

Guy Wolf

Ensembling multiple models enhances predictive performance by utilizing the varied learned features of the different models but incurs signi… (see more)ficant computational and storage costs. Model fusion, which combines parameters from multiple models into one, aims to mitigate these costs but faces practical challenges due to the complex, non-convex nature of neural network loss landscapes, where learned minima are often separated by high loss barriers. Recent works have explored using permutations to align network features, reducing the loss barrier in parameter space. However, permutations are restrictive since they assume a one-to-one mapping between the different models' neurons exists. We propose a new model merging algorithm, CCA Merge, which is based on Canonical Correlation Analysis and aims to maximize the correlations between linear combinations of the model features. We show that our method of aligning models leads to better performances than past methods when averaging models trained on the same, or differing data splits. We also extend this analysis into the harder many models setting where more than 2 models are merged, and we find that CCA Merge works significantly better in this setting than past methods.

2024-03-02

ICLR.cc/2024/Workshop/Re-Align (poster)

openreview.net

Generalization of deep learning models for hepatic steatosis grading using B-mode ultrasound images

Pedro Vianna

Yue Qi

Michael Chassé

Guy Wolf

Eugene Belilovsky

An Tang

Guy Cloutier

2024-03-01

The Journal of the Acoustical Society of America (published)

doi.org

Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation

Pedro Vianna

Muawiz Chaudhary

Paria Mehrbod

An Tang

Guy Cloutier

Guy Wolf

Michael Eickenberg

Eugene Belilovsky

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the … (see more)data distribution. For example, in the biomedical field, their performance can be affected by changes in the data (different machines, populations) between training and test datasets. To ensure robustness and generalization to real-world scenarios, test-time adaptation has been recently studied as an approach to adjust models to a new data distribution during inference. Test-time batch normalization is a simple and popular method that achieved compelling performance on domain shift benchmarks. It is implemented by recalculating batch normalization statistics on test batches. Prior work has focused on analysis with test data that has the same label distribution as the training data. However, in many practical applications this technique is vulnerable to label distribution shifts, sometimes producing catastrophic failure. This presents a risk in applying test time adaptation methods in deployment. We propose to tackle this challenge by only selectively adapting channels in a deep network, minimizing drastic adaptation that is sensitive to label shifts. Our selection scheme is based on two principles that we empirically motivate: (1) later layers of networks are more sensitive to label shift (2) individual features can be sensitive to specific classes. We apply the proposed technique to three classification tasks, including CIFAR10-C, Imagenet-C, and diagnosis of fatty liver, where we explore both covariate and label distribution shifts. We find that our method allows to bring the benefits of TTA while significantly reducing the risk of failure common in other methods, while being robust to choice in hyperparameters.

2024-02-07

ArXiv (preprint)

doi.org

arxiv.org

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

MohammadReza Davari

Eugene Belilovsky

The rapid development of AI systems has been greatly influenced by the emergence of foundation models. A common approach for targeted proble… (see more)ms involves fine-tuning these pre-trained foundation models for specific target tasks, resulting in a rapid spread of models fine-tuned across a diverse array of tasks. This work focuses on the problem of merging multiple fine-tunings of the same foundation model derived from a spectrum of auxiliary tasks. We introduce a new simple method, Model Breadcrumbs, which consists of a sparsely defined weight set that guides model adaptation within the weight space of a pre-trained model. These breadcrumbs are constructed by subtracting the weights from a pre-trained model before and after fine-tuning, followed by a sparsification process that eliminates weight outliers and negligible perturbations. Our experiments demonstrate the effectiveness of Model Breadcrumbs to simultaneously improve performance across multiple tasks. This contribution aligns with the evolving paradigm of updatable machine learning, reminiscent of the collaborative principles underlying open-source software development, fostering a community-driven effort to reliably update machine learning models. Our method is shown to be more efficient and unlike previous proposals does not require hyperparameter tuning for each new task added. Through extensive experimentation involving various models, tasks, and modalities we establish that integrating Model Breadcrumbs offers a simple, efficient, and highly effective approach for constructing multi-task models and facilitating updates to foundation models.

2023-12-11

ArXiv (preprint)

doi.org

arxiv.org

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

MohammadReza Davari

Eugene Belilovsky

2023-12-11

ArXiv (preprint)

doi.org

arxiv.org

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

MohammadReza Davari

Eugene Belilovsky

The rapid development of AI systems has been greatly influenced by the emergence of foundation models. A common approach for targeted proble… (see more)ms involves fine-tuning these pre-trained foundation models for specific target tasks, resulting in a rapid spread of models fine-tuned across a diverse array of tasks. This work focuses on the problem of merging multiple fine-tunings of the same foundation model derived from a spectrum of auxiliary tasks. We introduce a new simple method, Model Breadcrumbs, which consists of a sparsely defined weight set that guides model adaptation within the weight space of a pre-trained model. These breadcrumbs are constructed by subtracting the weights from a pre-trained model before and after fine-tuning, followed by a sparsification process that eliminates weight outliers and negligible perturbations. Our experiments demonstrate the effectiveness of Model Breadcrumbs to simultaneously improve performance across multiple tasks. This contribution aligns with the evolving paradigm of updatable machine learning, reminiscent of the collaborative principles underlying open-source software development, fostering a community-driven effort to reliably update machine learning models. Our method is shown to be more efficient and unlike previous proposals does not require hyperparameter tuning for each new task added. Through extensive experimentation involving various models, tasks, and modalities we establish that integrating Model Breadcrumbs offers a simple, efficient, and highly effective approach for constructing multi-task models and facilitating updates to foundation models.

2023-12-11

ArXiv (preprint)

doi.org

arxiv.org

Rising to the Occasion

AI Insights for Policymakers

Mila Techaide 2025

The Development of the UN Scientific Panel on AI

Transition in Mila's Scientific Direction

Rising to the Occasion

AI Insights for Policymakers

Eugene Belilovsky

Biography

Current Students

Publications

Rising to the Occasion

AI Insights for Policymakers

Mila Techaide 2025

The Development of the UN Scientific Panel on AI

Transition in Mila's Scientific Direction

Rising to the Occasion

AI Insights for Policymakers

Popular keywords:

Eugene Belilovsky

Biography

Current Students

Publications