Publications

Exploring the Manifold of Neural Networks Using Diffusion Geometry

Elliott Abel

Peyton Crevasse

Yvan Grinspan

Selma Mazioud

Folu Ogundipe

Kristof Reimann

Ellie Schueler

Andrew J. Steindl

Ellen Zhang

Dhananjay Bhaskar

Siddharth Viswanath

Yanlei Zhang

Tim G. J. Rudner

Ian Adelstein

Smita Krishnaswamy

Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we … (voir plus)apply manifold learning to the space of neural networks. We learn manifolds where datapoints are neural networks by introducing a distance between the hidden layer representations of the neural networks. These distances are then fed to the non-linear dimensionality reduction algorithm PHATE to create a manifold of neural networks. We characterize this manifold using features of the representation, including class separation, hierarchical cluster structure, spectral entropy, and topological structure. Our analysis reveals that high-performing networks cluster together in the manifold, displaying consistent embedding patterns across all these features. Finally, we demonstrate the utility of this approach for guiding hyperparameter optimization and neural architecture search by sampling from the manifold.

2024-11-19

ArXiv (prépublication)

doi.org

arxiv.org

Exploring the Manifold of Neural Networks Using Diffusion Geometry

Elliott Abel

Peyton Crevasse

Yvan Grinspan

Selma Mazioud

Folu Ogundipe

Kristof Reimann

Ellie Schueler

Andrew J. Steindl

Ellen Zhang

Dhananjay Bhaskar

Siddharth Viswanath

Yanlei Zhang

Tim G. J. Rudner

Ian Adelstein

Smita Krishnaswamy

Drawing motivation from the manifold hypothesis, which posits that most high-dimensional data lies on or near low-dimensional manifolds, we … (voir plus)apply manifold learning to the space of neural networks. We learn manifolds where datapoints are neural networks by introducing a distance between the hidden layer representations of the neural networks. These distances are then fed to the non-linear dimensionality reduction algorithm PHATE to create a manifold of neural networks. We characterize this manifold using features of the representation, including class separation, hierarchical cluster structure, spectral entropy, and topological structure. Our analysis reveals that high-performing networks cluster together in the manifold, displaying consistent embedding patterns across all these features. Finally, we demonstrate the utility of this approach for guiding hyperparameter optimization and neural architecture search by sampling from the manifold.

2024-11-19

ArXiv (prépublication)

doi.org

arxiv.org

Sketch-guided Cage-based 3D Gaussian Splatting Deformation

Tianhao Xie

Noam Aigerman

Eugene Belilovsky

Tiberiu Popa

3D Gaussian Splatting (GS) is one of the most promising novel 3D representations that has received great interest in computer graphics and c… (voir plus)omputer vision. While various systems have introduced editing capabilities for 3D GS, such as those guided by text prompts, fine-grained control over deformation remains an open challenge. In this work, we present a novel sketch-guided 3D GS deformation system that allows users to intuitively modify the geometry of a 3D GS model by drawing a silhouette sketch from a single viewpoint. Our approach introduces a new deformation method that combines cage-based deformations with a variant of Neural Jacobian Fields, enabling precise, fine-grained control. Additionally, it leverages large-scale 2D diffusion priors and ControlNet to ensure the generated deformations are semantically plausible. Through a series of experiments, we demonstrate the effectiveness of our method and showcase its ability to animate static 3D GS models as one of its key applications.

2024-11-19

ArXiv (prépublication)

doi.org

arxiv.org

Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineering

Mehil B. Shah

Mohammad Masudur Rahman

Foutse Khomh

Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). Ho… (voir plus)wever, DL systems are prone to bugs from many sources, including training data. Existing literature suggests that bugs in training data are highly prevalent, but little research has focused on understanding their impacts on the models used in software engineering tasks. In this paper, we address this research gap through a comprehensive empirical investigation focused on three types of data prevalent in software engineering tasks: code-based, text-based, and metric-based. Using state-of-the-art baselines, we compare the models trained on clean datasets with those trained on datasets with quality issues and without proper preprocessing. By analysing the gradients, weights, and biases from neural networks under training, we identify the symptoms of data quality and preprocessing issues. Our analysis reveals that quality issues in code data cause biased learning and gradient instability, whereas problems in text data lead to overfitting and poor generalisation of models. On the other hand, quality issues in metric data result in exploding gradients and model overfitting, and inadequate preprocessing exacerbates these effects across all three data types. Finally, we demonstrate the validity and generalizability of our findings using six new datasets. Our research provides a better understanding of the impact and symptoms of data bugs in software engineering datasets. Practitioners and researchers can leverage these findings to develop better monitoring systems and data-cleaning methods to help detect and resolve data bugs in deep learning systems.

2024-11-19

ArXiv (prépublication)

doi.org

arxiv.org

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

Prakhar Ganeesh

Usman Gohar

Lu Cheng

Golnoosh Farnadi

With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often … (voir plus)compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.

2024-11-17

ArXiv (prépublication)

doi.org

arxiv.org

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

Prakhar Ganeesh

Usman Gohar

Lu Cheng

Golnoosh Farnadi

With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often … (voir plus)compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.

2024-11-17

ArXiv (prépublication)

arxiv.org

Evaluating Generative AI Systems is a Social Science Measurement Challenge

Hanna Wallach

Meera Desai

Nicholas Pangakis

A. F. Cooper

Angelina Wang

Solon Barocas

Alexandra Chouldechova

Chad Atalla

Su Lin Blodgett

Emily Corvi

P. A. Dow

Jean Garcia-Gathright

Alexandra Olteanu

Stefanie Reed

Emily Sheng

Dan Vann

Jennifer Wortman Vaughan

Matthew Vogel

Hannah Washington

Abigail Z. Jacobs … (voir 1 de plus)

Microsoft Research

Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI … (voir plus)(GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of measurement tasks found throughout the social sciences. With this in mind, we present a framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, impacts, opportunities, and risks of GenAI systems. The framework distinguishes between four levels: the background concept, the systematized concept, the measurement instrument(s), and the instance-level measurements themselves. This four-level approach differs from the way measurement is typically done in ML, where researchers and practitioners appear to jump straight from background concepts to measurement instruments, with little to no explicit systematization in between. As well as surfacing assumptions, thereby making it easier to understand exactly what the resulting measurements do and do not mean, this framework has two important implications for evaluating evaluations: First, it can enable stakeholders from different worlds to participate in conceptual debates, broadening the expertise involved in evaluating GenAI systems. Second, it brings rigor to operational debates by offering a set of lenses for interrogating the validity of measurement instruments and their resulting measurements.

2024-11-17

ArXiv (prépublication)

doi.org

arxiv.org

Towards AI-designed genomes using a variational autoencoder

N.K. Dudek

Doina Precup

Genomes encode elaborate networks of genes whose products must seamlessly interact to support living organisms. Humans’ capacity to unders… (voir plus)tand these biological systems is limited by their sheer size and complexity. In this work, we develop a proof of concept framework for training a machine learning algorithm to model bacterial genome composition. To achieve this, we create simplified representations of genomes in the form of binary vectors that indicate the encoded genes, henceforth referred to as genome vectors. A denoising variational autoencoder was trained to accept corrupted genome vectors, in which most genes had been masked, and reconstruct the original. The resulting model, DeepGenomeVector, effectively captures complex dependencies in genomic networks, as evaluated by both qualitative and quantitative metrics. An in-depth functional analysis of a generated genome vector shows that its encoded pathways are interconnected, near complete, and ecologically cohesive. On the test set, where the model’s ability to reconstruct uncorrupted genome vectors was evaluated, AUC and F1 scores of 0.98 and 0.83, respectively, support the model’s strong performance. This work showcases the power of machine learning approaches for synthetic biology and highlights the possibility that AI agents may one day be able to design genomes that animate carbon-based cells.

2024-11-17

bioRxiv (prépublication)

doi.org

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Chris Pal

Marco Pedersoli

Issam Hadj Laradji

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual ass… (voir plus)istants. In these dialogues, it is important to identify user's goals automatically to resolve their needs promptly. This has necessitated the integration of models that perform Intent Detection. However, users' intents are diverse and dynamic, making it challenging to maintain a fixed set of predefined intents. As a result, a more practical approach is to develop a model capable of identifying new intents as they emerge. We address the challenge of Intent Discovery, an area that has drawn significant attention in recent research efforts. Existing methods need to train on a substantial amount of data for correctly identifying new intents, demanding significant human effort. To overcome this, we introduce IntentGPT, a novel training-free method that effectively prompts Large Language Models (LLMs) such as GPT-4 to discover new intents with minimal labeled data. IntentGPT comprises an \textit{In-Context Prompt Generator}, which generates informative prompts for In-Context Learning, an \textit{Intent Predictor} for classifying and discovering user intents from utterances, and a \textit{Semantic Few-Shot Sampler} that selects relevant few-shot examples and a set of known intents to be injected into the prompt. Our experiments show that IntentGPT outperforms previous methods that require extensive domain-specific data and fine-tuning, in popular benchmarks, including CLINC and BANKING, among others.

2024-11-16

ArXiv (prépublication)

doi.org

arxiv.org

IntentGPT: Few-shot Intent Discovery with Large Language Models

Juan A. Rodriguez

Nicholas Botzer

David Vazquez

Chris Pal

Marco Pedersoli

Issam Hadj Laradji

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual ass… (voir plus)istants. In these dialogues, it is important to identify user's goals automatically to resolve their needs promptly. This has necessitated the integration of models that perform Intent Detection. However, users' intents are diverse and dynamic, making it challenging to maintain a fixed set of predefined intents. As a result, a more practical approach is to develop a model capable of identifying new intents as they emerge. We address the challenge of Intent Discovery, an area that has drawn significant attention in recent research efforts. Existing methods need to train on a substantial amount of data for correctly identifying new intents, demanding significant human effort. To overcome this, we introduce IntentGPT, a novel training-free method that effectively prompts Large Language Models (LLMs) such as GPT-4 to discover new intents with minimal labeled data. IntentGPT comprises an \textit{In-Context Prompt Generator}, which generates informative prompts for In-Context Learning, an \textit{Intent Predictor} for classifying and discovering user intents from utterances, and a \textit{Semantic Few-Shot Sampler} that selects relevant few-shot examples and a set of known intents to be injected into the prompt. Our experiments show that IntentGPT outperforms previous methods that require extensive domain-specific data and fine-tuning, in popular benchmarks, including CLINC and BANKING, among others.

2024-11-16

ArXiv (prépublication)

arxiv.org