Goncalo Mordido

Should We Attend More or Less? Modulating Attention for Fairness

Samira Shabanian

A. Chandar

2024-07-09

colmweb.org/COLM/2024/Conference (accepted)

openreview.net

Lookbehind-SAM: k Steps Back, 1 Step Forward

Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and lo… (see more)ss sharpness as a minimax objective. In this work, we increase the efficiency of the maximization and minimization parts of SAM's objective to achieve a better loss-sharpness trade-off. By taking inspiration from the Lookahead optimizer, which uses multiple descent steps ahead, we propose Lookbehind, which performs multiple ascent steps behind to enhance the maximization step of SAM and find a worst-case perturbation with higher loss. Then, to mitigate the variance in the descent step arising from the gathered gradients across the multiple ascent steps, we employ linear interpolation to refine the minimization step. Lookbehind leads to a myriad of benefits across a variety of tasks. Particularly, we show increased generalization performance, greater robustness against noisy weights, as well as improved learning and less catastrophic forgetting in lifelong learning settings. Our code is available at https://github.com/chandar-lab/Lookbehind-SAM.

2024-07-07

Proceedings of the 41st International Conference on Machine Learning (published)

proceedings.mlr.press

Promoting Exploration in Memory-Augmented Adam using Critical Momenta

Pranshu Malviya

Reza Babanezhad Harikandeh

Aristide Baratin

Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergen… (see more)ce and robustness to hyperparameter settings. However, they often struggle with generalization, attributed to their tendency to converge to sharp minima in the loss landscape. To address this, we propose a new memory-augmented version of Adam that encourages exploration towards flatter minima by incorporating a buffer of critical momentum terms during training. This buffer prompts the optimizer to overshoot beyond narrow minima, promoting exploration. Through comprehensive analysis in simple settings, we illustrate the efficacy of our approach in increasing exploration and bias towards flatter minima. We empirically demonstrate that it can improve model performance for image classification on ImageNet and CIFAR10/100, language modelling on Penn Treebank, and online learning tasks on TinyImageNet and 5-dataset. Our code is available at https://github.com/chandar-lab/CMOptimizer.

2024-06-08

TMLR (accepted)

openreview.net

Why Don't Prompt-Based Fairness Metrics Correlate?

Ioana Baldini

A. Chandar

The widespread use of large language models has brought up essential questions about the potential biases these models might learn. This led… (see more) to the development of several metrics aimed at evaluating and mitigating these biases. In this paper, we first demonstrate that prompt-based fairness metrics exhibit poor agreement, as measured by correlation, raising important questions about the reliability of fairness assessment using prompts. Then, we outline six relevant reasons why such a low correlation is observed across existing metrics. Based on these insights, we propose a method called Correlated Fairness Output (CAIRO) to enhance the correlation between fairness metrics. CAIRO augments the original prompts of a given fairness metric by using several pre-trained language models and then selects the combination of the augmented prompts that achieves the highest correlation across metrics. We show a significant improvement in Pearson correlation from 0.3 and 0.18 to 0.90 and 0.98 across metrics for gender and religion biases, respectively. Our code is available at https://github.com/chandar-lab/CAIRO.

2024-06-08

ArXiv (preprint)

Exploring Quantization for Efficient Pre-Training of Transformer Language Models

Kamran Chitsaz

Quentin Fournier

A. Chandar

The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has p… (see more)roven to be effective after pre-training and during fine-tuning, applying quantization in Transformers during pre-training has remained largely unexplored at scale for language modeling. This study aims to explore the impact of quantization for efficient pre-training of Transformers, with a focus on linear layer components. By systematically applying straightforward linear quantization to weights, activations, gradients, and optimizer states, we assess its effects on model efficiency, stability, and performance during training. By offering a comprehensive recipe of effective quantization strategies to be applied during the pre-training of Transformers, we promote high training efficiency from scratch while retaining language modeling ability. Code is available at https://github.com/chandar-lab/EfficientLLMs.

2023-12-31

EMNLP (Findings) (published)

Sharpness-Aware Minimization Scaled by Outlier Normalization for Robust DNNs on In-Memory Computing Accelerators

Sébastien Henwood

Yvon Savaria

A. Chandar

François Leduc-Primeau

Many deep neural network (DNN) models consume a significant amount of energy at inference time, in large part due to energy consumed by memo… (see more)ry access. In-memory computing addresses this problem by eliminating many memory accesses, but exposes model weights to noise and circuit variations. While several methods have been proposed to train DNNs robust to weight noise they typically require knowledge of the noise distribution, or degrade the DNN performance in noiseless setting. In this work, we first show that applying sharpness-aware training, by optimizing for both the loss value and loss sharpness, significantly improves robustness to noisy weights at inference time. Then, we propose a new adaptive sharpness-aware method that conditions the worst-case perturbation of a given weight not only on its magnitude but also on the range of the weight distribution. This is achieved by performing sharpness-aware minimization scaled by outlier normalization (SAMSON). Results on computer-vision benchmarks show that SAMSON increases model robustness to noisy weights without compromising generalization performance in noiseless regimes.

2023-12-31

IEEECONF (published)

Fairness-Aware Structured Pruning in Transformers

Samira Shabanian

Ioana Baldini

A. Chandar

2023-12-23

ArXiv (preprint)

Improving Meta-Learning Generalization with Activation-Based Early-Stopping

Simon Guiroy

Christopher Pal

A. Chandar

2022-11-27

Proceedings of The 1st Conference on Lifelong Learning Agents (published)

proceedings.mlr.press

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

Prasanna Parthasarathi

Hamid Palangi

Samira Shabanian

Sarath Chandar

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity conc… (see more)erns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show that some of the examples in the augmented dataset can be not important or even harmful for fairness. We hence propose a general method for pruning both the factual and counterfactual examples to maximize the model's fairness as measured by the demographic parity, equality of opportunity, and equality of odds. The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset. Our experiments are conducted using models of varying sizes and pre-training settings.

2022-11-19

ArXiv (preprint)

SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness

Sébastien Henwood

A. Chandar

Franccois Leduc-Primeau

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitig… (see more)ate such degradation, existing methods typically add perturbations to the DNN weights during training to simulate inference on noisy hardware. However, this often requires knowledge about the target hardware and leads to a trade-off between DNN performance and robustness, decreasing the former to increase the latter. In this work, we show that applying sharpness-aware training, by optimizing for both the loss value and loss sharpness, significantly improves robustness to noisy hardware at inference time without relying on any assumptions about the target hardware. In particular, we propose a new adaptive sharpness-aware method that conditions the worst-case perturbation of a given weight not only on its magnitude but also on the range of the weight distribution. This is achieved by performing sharpness-aware minimization scaled by outlier minimization (SAMSON). Our approach outperforms existing sharpness-aware training methods both in terms of model generalization performance in noiseless regimes and robustness in noisy settings, as measured on several architectures and datasets.

2022-11-17

ArXiv (preprint)

Sharpness-Aware Training for Accurate Inference on Noisy DNN Accelerators

A. Chandar

Franccois Leduc-Primeau

Energy-efﬁcient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To miti… (see more)gate such degradation, existing methods typically add perturbations to the DNN weights during training to simulate inference on noisy hardware. However, this often requires knowledge about the target hardware and leads to a trade-off between DNN performance and robustness, decreasing the former to increase the latter. In this work, we show that applying sharpness-aware training by optimizing for both the loss value and the loss sharpness signiﬁcantly improves robustness to noisy hardware at inference time while also increasing DNN performance. We further motivate our results by showing a high correlation between loss sharpness and model robustness. We show superior performance compared to injecting noise during training and aggressive weight clipping on multiple architectures, optimizers, datasets, and training regimes without relying on any assumptions about the target hardware. This is observed on a generic noise model as well as on accurate noise simulations from real hardware.

2021-12-31

arXiv.org (preprint)