Hugo Larochelle

Survey of Scientific Rigor Studied in Machine Learning

D. Sculley

Gary R. Holt

Daniel R. Golovin

Eugene V. Davydov

Todd Phillips

Dietmar Ebner

Michael Young

Jean-francois Crespo

Dan Dennison

Emily Fox

The concern that Artificial Intelligence (AI) and Machine Learning (ML) are entering a “reproducibility crisis” has spurred significant … (see more)research in the past few years. Yet with each paper, it is often unclear what someone means by “reproducibility” and where it fits in the larger scope of what we will call the “scientific rigor” literature. Ultimately, the lack of clear rigor standards can affect the manner in which businesses seeking to adopt AI/ML implement such capabilities. In this survey, we will use 66 papers published since 2017 to construct a proposed set of 8 high-level categories of scientific rigor, what they are, and the history of work conducted in each. Our proposal is that these eight rigor types are not mutually exclusive and present a model for how they influence each other. To encourage more to study these questions, we map these rigors to the adoption process in real-world business use cases. In doing so, we can quantify gaps in the literature that suggest an under focus on the issues necessary for scientific rigor research to transition to practice

2023-01-01

(published)

www.semanticscholar.org

Teaching Algorithmic Reasoning via In-context Learning

Hattie Zhou

Azade Nova

Aaron Courville

Behnam Neyshabur

Hanie Sedghi

2022-11-15

ArXiv (preprint)

Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning

Utku Evci

Vincent Dumoulin

Michael Curtis Mozer

2022-06-28

Proceedings of the 39th International Conference on Machine Learning (published)

proceedings.mlr.press

Uniform Priors for Data-Efficient Learning

Samarth Sinha

Karsten Roth

Anirudh Goyal

Marzyeh Ghassemi

Zeynep Akata

Animesh Garg

Few or zero-shot adaptation to novel tasks is important for the scalability and deployment of machine learning models. It is therefore cruci… (see more)al to find properties that encourage more transferable features in deep networks for generalization. In this paper, we show that models that learn uniformly distributed features from the training data, are able to perform better transfer learning at test-time. Motivated by this, we evaluate our method: uniformity regularization (UR) on its ability to facilitate adaptation to unseen tasks and data on six distinct domains: Few-Learning with Images, Few-shot Learning with Language, Deep Metric Learning, 0-Shot Domain Adaptation, Out-of-Distribution classification, and Neural Radiance Fields. Across all experiments, we show that using UR, we are able to learn robust vision systems which consistently offer benefits over baselines trained without uniformity regularization and are able to achieve state-of-the-art performance in Deep Metric Learning, Few-shot learning with images and language.

2022-06-19

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (published)

Matching Feature Sets for Few-Shot Image Classification

Arman Afrasiyabi

Jean‐François Lalonde

Christian Gagné

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classific… (see more)ation methods also mostly follow this trend. In this work, we depart from this established direction and instead propose to extract sets of feature vectors for each image. We argue that a set-based representation intrinsically builds a richer representation of images from the base classes, which can subsequently better transfer to the few-shot classes. To do so, we propose to adapt existing feature extractors to instead produce sets of feature vectors from images. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures. The attention modules are lightweight, and as such our method results in encoders that have approximately the same number of parameters as their original versions. During training and inference, a set-to-set matching metric is used to perform image classification. The effectiveness of our proposed architecture and metrics is demonstrated via thorough experiments on standard few-shot datasets-namely miniImageNet, tieredImageNet, and CUB-in both the 1- and 5-shot scenarios. In all cases but one, our method outperforms the state-of-the-art.

2022-06-18

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)

Matching Feature Sets for Few-Shot Image Classification

Arman Afrasiyabi

Jean‐François Lalonde

Christian Gagné

In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classific… (see more)ation methods also mostly follow this trend. In this work, we depart from this established direction and instead propose to extract sets of feature vectors for each image. We argue that a set-based representation intrinsically builds a richer representation of images from the base classes, which can subsequently better transfer to the few-shot classes. To do so, we propose to adapt existing feature extractors to instead produce sets of feature vectors from images. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures. The attention modules are lightweight, and as such our method results in encoders that have approximately the same number of parameters as their original versions. During training and inference, a set-to-set matching metric is used to perform image classification. The effectiveness of our proposed architecture and metrics is demonstrated via thorough experiments on standard few-shot datasets-namely miniImageNet, tieredImageNet, and CUB-in both the 1- and 5-shot scenarios. In all cases but one, our method outperforms the state-of-the-art.

2022-04-02

ArXiv (preprint)

Fortuitous Forgetting in Connectionist Networks

Hattie Zhou

Ankit Vani

Aaron Courville

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact b… (see more)e favorable to learning. We introduce"forget-and-relearn"as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.

2022-01-28

ICLR.cc/2022/Conference (poster)

Learning to Combine Per-Example Solutions for Neural Program Synthesis

Disha Shrivastava

Danny Tarlow

The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most… (see more) learning-based approaches try to find a program that satisfies all examples at once. Our work, by contrast, considers an approach that breaks the problem into two stages: (a) find programs that satisfy only one example, and (b) leverage these per-example solutions to yield a program that satisfies all examples. We introduce the Cross Aggregator neural network module based on a multi-head attention mechanism that learns to combine the cues present in these per-example solutions to synthesize a global solution. Evaluation across programs of different lengths and under two different experimental settings reveal that when given the same time budget, our technique significantly improves the success rate over PCCoder [Zohar et. al 2018] and other ablation baselines.

Impact of Aliasing on Generalization in Deep Convolutional Networks

Cristina Vasconcelos

Vincent Dumoulin

Rob Romijnders

Nicolas Le Roux

Ross Goroshin

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are una… (see more)ble to prevent it due to structural limitations in widely used architectures. Drawing insights from frequency analysis theory, we take a closer look at ResNet and EfficientNet architectures and review the trade-off between aliasing and information loss in each of their major components. We show how to mitigate aliasing by inserting non-trainable low-pass filters at key locations, particularly where networks lack the capacity to learn them. These simple architectural changes lead to substantial improvements in generalization on i.i.d. and even more on out-of-distribution conditions, such as image classification under natural corruptions on ImageNet-C [11] and few-shot learning on Meta-Dataset [26]. State-of-the art results are achieved on both datasets without introducing additional trainable parameters and using the default hyper-parameters of open source codebases.

2021-10-10

2021 IEEE/CVF International Conference on Computer Vision (ICCV) (published)

DIBS: Diversity inducing Information Bottleneck in Model Ensembles

Samarth Sinha

Homanga Bharadhwaj

Anirudh Goyal

Animesh Garg

Florian Shkurti

2021-05-18

Proceedings of the AAAI Conference on Artificial Intelligence (published)

Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark

Vincent Dumoulin

Neil Houlsby

Utku Evci

Xiaohua Zhai

Ross Goroshin

Sylvain Gelly

Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art ad… (see more)vances in each family are measured largely in isolation of each other. As a result of diverging evaluation norms, a direct or thorough comparison of different approaches is challenging. To bridge this gap, we perform a cross-family study of the best transfer and meta learners on both a large-scale meta-learning benchmark (Meta-Dataset, MD), and a transfer learning benchmark (Visual Task Adaptation Benchmark, VTAB). We find that, on average, large-scale transfer methods (Big Transfer, BiT) outperform competing approaches on MD, even when trained only on ImageNet. In contrast, meta-learning approaches struggle to compete on VTAB when trained and validated on MD. However, BiT is not without limitations, and pushing for scale does not improve performance on highly out-of-distribution MD tasks. In performing this study, we reveal a number of discrepancies in evaluation norms and study some of these in light of the performance gap. We hope that this work facilitates sharing of insights from each community, and accelerates progress on few-shot learning.

2021-04-06

ArXiv (preprint)