Publications

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers

Jonas Ngnaw'e

Sabyasachi Sahoo

Yann Batiste Pequignot

Fr'ed'eric Precioso

Christian Gagné

Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning mod… (see more)els can still be quite sensitive to imperceptible perturbations, creating serious risks when deploying them for high-stakes real-world applications. While detecting such cases may be critical, evaluating a model's vulnerability at a per-instance level using adversarial attacks is computationally too intensive and unsuitable for real-time deployment scenarios. The input space margin is the exact score to detect non-robust samples and is intractable for deep neural networks. This paper introduces the concept of margin consistency -- a property that links the input space margins and the logit margins in robust models -- for efficient detection of vulnerable samples. First, we establish that margin consistency is a necessary and sufficient condition to use a model's logit margin as a score for identifying non-robust samples. Next, through comprehensive empirical analysis of various robustly trained models on CIFAR10 and CIFAR100 datasets, we show that they indicate strong margin consistency with a strong correlation between their input space margins and the logit margins. Then, we show that we can effectively use the logit margin to confidently detect brittle decisions with such models and accurately estimate robust accuracy on an arbitrarily large test set by estimating the input margins only on a small subset. Finally, we address cases where the model is not sufficiently margin-consistent by learning a pseudo-margin from the feature representation. Our findings highlight the potential of leveraging deep representations to efficiently assess adversarial vulnerability in deployment scenarios.

2024-06-26

ArXiv (preprint)

Learning to Design Data-structures: A Case Study of Nearest Neighbor Search

Omar Salemohamed

Vatsal Sharan

Shivam Garg

Laurent Charlin

Gregory Valiant

We propose a general framework for automating data-structure design and apply it to the problem of nearest neighbor search. Our model adapts… (see more) to the underlying data distribution and provides fine-grained control over query and space complexity, enabling the discovery of solutions tailored to problem-specific constraints. We are able to reverse-engineer learned algorithms in several settings. In 1D, the model discovers optimal distribution (in)dependent algorithms such as binary search and variants of interpolation search. In higher dimensions, the model learns solutions that resemble K-d trees in some regimes, while in others, have elements of locality-sensitive hashing.

2024-06-26

ICML.cc/2024/Workshop/Differentiable_Almost_Everything (published)

Gintare Karolina Dziugaite

Mixture of Experts in a Mixture of RL settings

Timon Willi

Johan Samir Obando Ceron

Jakob Nicolaus Foerster

Pablo Samuel Castro

Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to … (see more)distributed training, and modularity. Previous research has illustrated that MoEs can significantly boost Deep Reinforcement Learning (DRL) performance by expanding the network's parameter count while reducing dormant neurons, thereby enhancing the model's learning capacity and ability to deal with non-stationarity. In this work, we shed more light on MoEs' ability to deal with non-stationarity and investigate MoEs in DRL settings with"amplified"non-stationarity via multi-task training, providing further evidence that MoEs improve learning capacity. In contrast to previous work, our multi-task results allow us to better understand the underlying causes for the beneficial effect of MoE in DRL training, the impact of the various MoE components, and insights into how best to incorporate them in actor-critic-based DRL networks. Finally, we also confirm results from previous work.

2024-06-26

ArXiv (preprint)

BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging

Zeinab Sherkatghanad

Moloud Abdar

Mohammadreza Bakhtyari

Vladimir Makarenkov

Test-time augmentation (TTA) is a well-known technique employed during the testing phase of computer vision tasks. It involves aggregating m… (see more)ultiple augmented versions of input data. Combining predictions using a simple average formulation is a common and straightforward approach after performing TTA. This paper introduces a novel framework for optimizing TTA, called BayTTA (Bayesian-based TTA), which is based on Bayesian Model Averaging (BMA). First, we generate a model list associated with different variations of the input data created through TTA. Then, we use BMA to combine model predictions weighted by their respective posterior probabilities. Such an approach allows one to take into account model uncertainty, and thus to enhance the predictive performance of the related machine learning or deep learning model. We evaluate the performance of BayTTA on various public data, including three medical image datasets comprising skin cancer, breast cancer, and chest X-ray images and two well-known gene editing datasets, CRISPOR and GUIDE-seq. Our experimental results indicate that BayTTA can be effectively integrated into state-of-the-art deep learning models used in medical image analysis as well as into some popular pre-trained CNN models such as VGG-16, MobileNetV2, DenseNet201, ResNet152V2, and InceptionRes-NetV2, leading to the enhancement in their accuracy and robustness performance.

2024-06-25

ArXiv (preprint)

Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers

Xiuying Wei

Skander Moalla

Razvan Pascanu

Caglar Gulcehre

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a re… (see more)search agenda to reduce these models' parameter counts and computational costs without significantly impacting their performance. Our study focuses on transformer-based LLMs, specifically targeting the computationally intensive feedforward networks (FFNs), which are less studied than attention blocks. We consider three structured linear parameterizations of the FFN using efficient low-rank and block-diagonal matrices. In contrast to many previous works that examined these approximations, our study i) explores these structures from a training-from-scratch perspective, ii) scales up to 1.3B parameters, and iii) is conducted within recent Transformer-based LLMs rather than convolutional architectures. We demonstrate that these structures can lead to actual computational gains in various scenarios, including online decoding when using a pre-merge technique. Additionally, we propose a novel training regime, called \textit{self-guided training}, aimed at improving the poor training dynamics that these approximations exhibit when used from initialization. Interestingly, the scaling performance of structured matrices is explored, revealing steeper curves in scaling training FLOPs, along with a favorable scaling trend in the overtraining regime. Specifically, we show that wide and structured networks can utilize training FLOPs more efficiently, with fewer parameters and lower loss than dense models at their optimal trade-off. Our code is available at https://github.com/CLAIRE-Labo/StructuredFFN/tree/main.

2024-06-24

ArXiv (preprint)

Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent

Karolis Jucys

George Adamopoulos

Mehrab Hamidi

Stephanie Milani

Mohammad Reza Samsami

Özgür Şimşek

Understanding the mechanisms behind decisions taken by large foundation models in sequential tasks is critical to ensuring that such systems… (see more) operate transparently and safely. However, interpretability methods have not yet been applied extensively to large-scale agents based on reinforcement learning. In this work, we perform exploratory analysis on the Video PreTraining (VPT) Minecraft playing agent, one of the largest open-source vision-based agents. We try to illuminate its reasoning mechanisms by applying various interpretability techniques. First, we analyze the attention mechanism while the agent solves its training task --- crafting a diamond pickaxe. The agent seems to pay attention to the 4 last frames and several key-frames further back. This provides clues as to how it maintains coherence in the task that takes 3-10 minutes, despite the agent's short memory span of only six seconds. Second, we perform various interventions, which help us uncover a worrying case of goal misgeneralization: VPT mistakenly identifies a villager wearing brown clothes as a tree trunk and punches it to death, when positioned stationary under green tree leaves. We demonstrate similar misbehavior in a related agent (STEVE-1), which motivates the use of VPT as a model organism for large-scale vision-based agent interpretability.

2024-06-24

ICML.cc/2024/Workshop/MI (poster)

Gintare Karolina Dziugaite

Robust Unlearning via Mechanistic Localizations

Phillip Huang Guo

Aaquib Syed

Abhay Sheshadri

Aidan Ewart

Methods for machine unlearning in large language models seek to remove undesirable knowledge or capabilities without compromising general la… (see more)nguage modeling performance. This work investigates the use of mechanistic interpretability to improve the precision and effectiveness of unlearning. We demonstrate that localizing unlearning to components with particular mechanisms in factual recall leads to more robust unlearning across different input/output formats, relearning, and latent knowledge, and reduces unintended side effects compared to nonlocalized unlearning. Additionally, we analyze the strengths and weaknesses of different automated (rather than manual) interpretability methods for guiding unlearning, finding that their corresponding unlearned models require smaller edit sizes to achieve unlearning but are much less robust.

2024-06-24

ICML.cc/2024/Workshop/MI (spotlight)

Gintare Karolina Dziugaite

Robust Unlearning via Mechanistic Localizations

Phillip Huang Guo

Aaquib Syed

Abhay Sheshadri

Aidan Ewart

Methods for machine unlearning in large language models seek to remove undesirable knowledge or capabilities without compromising general la… (see more)nguage modeling performance. This work investigates the use of mechanistic interpretability to improve the precision and effectiveness of unlearning. We demonstrate that localizing unlearning to components with particular mechanisms in factual recall leads to more robust unlearning across different input/output formats, relearning, and latent knowledge, and reduces unintended side effects compared to nonlocalized unlearning. Additionally, we analyze the strengths and weaknesses of different automated (rather than manual) interpretability methods for guiding unlearning, finding that their corresponding unlearned models require smaller edit sizes to achieve unlearning but are much less robust.

2024-06-24

ICML.cc/2024/Workshop/MI (spotlight)

The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources

Shayne Longpre

Stella Biderman

Alon Albalak

Hailey Schoelkopf

Daniel McDuff

Sayash Kapoor

Kevin Klyman

Kyle Lo

Gabriel Ilharco

Nay San

Maribeth Rauh

Aviya Skowron

Bertie Vidgen

Laura Weidinger

Arvind Narayanan

Victor Sanh

David Ifeoluwa Adelani

Percy Liang

Rishi Bommasani

Peter Henderson … (see 3 more)

Sasha Luccioni

Yacine Jernite

Luca Soldaini

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible deve… (see more)lopment practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.

2024-06-24

ArXiv (preprint)

Towards a standardized framework for AI-assisted, image-based monitoring of nocturnal insects

D. B. Roy

David Roy

J. Alison

Tom August

M. Bélisle

K. Bjerge

J. J. Bowden

M. J. Bunsen

F. Cunha

Q. Geissmann

K. Goldmann

Alba Gomez-Segura

A. Jain

C. Huijbers

M. Larrivée

J. L. Lawson

H. M. Mann

M. J. Mazerolle

K. P. McFarland

L. Pasi … (see 8 more)

S. Peters

N. Pinoy

David Rolnick

G. L. Skinner

O. T. Strickson

A. Svenning

S. Teagle

Toke Thomas Høye

Automated sensors have potential to standardize and expand the monitoring of insects across the globe. As one of the most scalable and faste… (see more)st developing sensor technologies, we describe a framework for automated, image-based monitoring of nocturnal insects—from sensor development and field deployment to workflows for data processing and publishing. Sensors comprise a light to attract insects, a camera for collecting images and a computer for scheduling, data storage and processing. Metadata is important to describe sampling schedules that balance the capture of relevant ecological information against power and data storage limitations. Large data volumes of images from automated systems necessitate scalable and effective data processing. We describe computer vision approaches for the detection, tracking and classification of insects, including models built from existing aggregations of labelled insect images. Data from automated camera systems necessitate approaches that account for inherent biases. We advocate models that explicitly correct for bias in species occurrence or abundance estimates resulting from the imperfect detection of species or individuals present during sampling occasions. We propose ten priorities towards a step-change in automated monitoring of nocturnal insects, a vital task in the face of rapid biodiversity loss from global threats. This article is part of the theme issue ‘Towards a toolkit for global insect biodiversity monitoring’.

2024-06-24

Philosophical Transactions of the Royal Society B: Biological Sciences (published)

Efficient Evolutionary Search Over Chemical Space with Large Language Models

Haorui Wang

Marta Skreta

Cher Tian Ser

Wenhao Gao

Lingkai Kong

Felix Streith-Kalthoff

Chenru Duan

Yuchen Zhuang

Yue Yu

Yanqiao Zhu 0001

Yuanqi Du

Alán Aspuru-Guzik

Kirill Neklyudov

Chao Zhang

Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectiv… (see more)es can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in molecular discovery, traverse chemical space by performing random mutations and crossovers, leading to a large number of expensive objective evaluations. In this work, we ameliorate this shortcoming by incorporating chemistry-aware Large Language Models (LLMs) into EAs. Namely, we redesign crossover and mutation operations in EAs using LLMs trained on large corpora of chemical information. We perform extensive empirical studies on both commercial and open-source models on multiple tasks involving property optimization, molecular rediscovery, and structure-based drug design, demonstrating that the joint usage of LLMs with EAs yields superior performance over all baseline models across single- and multi-objective settings. We demonstrate that our algorithm improves both the quality of the final solution and convergence speed, thereby reducing the number of required objective evaluations. Our code is available at http://github.com/zoom-wang112358/MOLLEO

2024-06-23

ArXiv (preprint)