Low rank matrix factorization is a fundamental building block in machine learning, used for instance to summarize gene expression profile data or word-document counts. To be robust to outliers and differences in scale across features, a matrix factorization step is usually preceded by ad-hoc feature normalization steps, such as \texttt{tf-idf} scaling or data whitening. We propose in this work to learn these normalization operators jointly with the factorization itself. More precisely, given a $d\times n$ matrix $X$ of $d$ features measured on $n$ individuals, we propose to learn the parameters of quantile normalization operators that can operate row-wise on the values of $X$ and/or of its factorization $UV$ to improve the quality of the low-rank representation of $X$ itself. This optimization is facilitated by the introduction of a new differentiable quantile normalization operator built using optimal transport, providing new results on top of existing work by (Cuturi et al. 2019). We demonstrate the applicability of these techniques on synthetic and genomics datasets.
MINES ParisTech（巴黎矿业学院）；PSL Research University（巴黎文理研究大学）；Institut Curie（居里研究所）；INSERM（法国国家健康与医学研究院）；Ecole Normale Supérieure（巴黎高等师范学院）
Quantile normalisation is a popular normalisation method for data subject to unwanted variations such as images, speech, or genomic data. It applies a monotonic transformation to the feature values of each sample to ensure that after normalisation, they follow the same target distribution for each sample. Choosing a "good" target distribution remains however largely empirical and heuristic, and is usually done independently of the subsequent analysis of normalised data. We propose instead to couple the quantile normalisation step with the subsequent analysis, and to optimise the target distrib…
We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. This design reduces the intrinsic cross-sample dependency of BN and enhances the generalization of the teacher. EMAN improves strong baselines for self-supervised learning by…
We propose a new embedding method, named Quantile-Quantile Embedding (QQE), for distribution transformation and manifold embedding with the ability to choose the embedding distribution. QQE, which uses the concept of quantile-quantile plot from visual statistical tests, can transform the distribution of data to any theoretical desired distribution or empirical reference sample. Moreover, QQE gives the user a choice of embedding distribution in embedding the manifold of data into the low dimensional embedding space. It can also be used for modifying the embedding distribution of other dimension…
Omics technologies are powerful tools for analyzing patterns in gene expression data for thousands of genes. Due to a number of systematic variations in experiments, the raw gene expression data is often obfuscated by undesirable technical noises. Various normalization techniques were designed in an attempt to remove these non-biological errors prior to any statistical analysis. One of the reasons for normalizing data is the need for recovering the covariance matrix used in gene network analysis. In this paper, we introduce a novel normalization technique, called the covariance shift (C-SHIFT)…
In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models. Our findings indicate that Batch Normalization (BN) statistics play a crucial role, and that updating only the BN statistics of a pre-trained SSL backbone improves its downstream fairness (36% worst subgroup, 25% mean subgroup gap). This procedure is competitive with supervised learning, while taking 4.4x less time to train and requiring only 0.35% as many parameters to be updated. Finally, inspired by recent work in supervised learning, we find that updating BN statistics and tra…
In recent years, semi-supervised multi-view nonnegative matrix factorization (MVNMF) algorithms have achieved promising performances for multi-view clustering. While most of semi-supervised MVNMFs have failed to effectively consider discriminative information among clusters and feature alignment from multiple views simultaneously. In this paper, a novel Discriminatively Constrained Semi-Supervised Multi-View Nonnegative Matrix Factorization (DCS^2MVNMF) is proposed. Specifically, a discriminative weighting matrix is introduced for the auxiliary matrix of each view, which enhances the inter-cla…
University of Southern California（南加利福尼亚大学）；Amazon Web Services（亚马逊云科技）
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsu…
The University of Tokyo（东京大学）；Physics & Informatics Laboratories, NTT Research, Inc.（NTT研究公司物理与信息学实验室）；Harvard University（哈佛大学）；University of Michigan（密歇根大学）；RIKEN Center for Emergent Matter Science (CEMS)（理化学研究所涌现物质科学中心）
Prevention of complete and dimensional collapse of representations has recently become a design principle for self-supervised learning (SSL). However, questions remain in our theoretical understanding: When do those collapses occur? What are the mechanisms and causes? We answer these questions by deriving and thoroughly analyzing an analytically tractable theory of SSL loss landscapes. In this theory, we identify the causes of the dimensional collapse and study the effect of normalization and bias. Finally, we leverage the interpretability afforded by the analytical theory to understand how di…
In this paper, we present a novel approach, Momentum$^2$ Teacher, for student-teacher based self-supervised learning. The approach performs momentum update on both network weights and batch normalization (BN) statistics. The teacher's weight is a momentum update of the student, and the teacher's BN statistics is a momentum update of those in history. The Momentum$^2$ Teacher is simple and efficient. It can achieve the state of the art results (74.5\%) under ImageNet linear evaluation protocol using small-batch size(\eg, 128), without requiring large-batch training on special hardware like TPU …
Thanks to breakthroughs in AI and Deep learning methodology, Computer vision techniques are rapidly improving. Most computer vision applications require sophisticated image segmentation to comprehend what is image and to make an analysis of each section easier. Training deep learning networks for semantic segmentation required a large amount of annotated data, which presents a major challenge in practice as it is expensive and labor-intensive to produce such data. The paper presents 1. Self-supervised techniques to boost semantic segmentation performance using multi-task learning with Depth pr…
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation. From an augmented view of an image, BYOL trains an online network to predict a target network representation of a different augmented view of the same image. Unlike contrastive methods, BYOL does not explicitly use a repulsion term built from negative pairs in its training objective. Yet, it avoids collapse to a trivial, constant representation. Thus, it has recently been hypothesized that batch normalization (BN) is critical to prevent collapse in BYOL. Indeed, BN flows gradients across batch ele…
SEMF: Supervised Expectation-Maximization Framework for Predicting Intervals
HEC, University of Lausanne, Lausanne, Switzerland（洛桑大学HEC学院，洛桑，瑞士）；HEC, University of Lausanne, Expertise Center for Climate Extremes (ECCE), Lausanne, Switzerland（洛桑大学HEC学院，洛桑，瑞士）
Jagiellonian University（雅盖隆大学）；Nomagic；New York University（纽约大学）
Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this phenomenon for image classification on the CIFAR-10 and the ImageNet datasets, and with many other forms of domain shifts applied (e.g. salt-and-pepper noise). Our main contribution is Split Batch Normalization (Split-BN), a technique to improve SSL when the additional unlabeled data comes from a shifted distribution. We achieve it by using separate batch n…
Inspired by the recent progress in self-supervised learning for computer vision that generates supervision using data augmentations, we explore a new general-purpose audio representation learning approach. We propose learning general-purpose audio representation from a single audio segment without expecting relationships between different time segments of audio samples. To implement this principle, we introduce Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced "viola"), an audio self-supervised learning method based on BYOL for learning general-purpose audio representation. Unlike…
NASA Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心）
Blazars are active galactic nuclei with relativistic jets pointed almost directly at Earth. Blazars are characterized by strong, apparently stochastic flux variability at virtually all observed wavelengths and timescales, from minutes to years, the physical origin of which is still poorly understood. In the high-energy gamma-ray band, the Large Area Telescope aboard the Fermi space telescope (Fermi-LAT) has conducted regular monitoring of thousands of blazars since 2008. Deep learning can help uncover structure in gamma-ray blazars' complex variability patterns that traditional methods based o…
In this paper, we present SANTA, a scalable framework to automatically normalize E-commerce attribute values (e.g. "Win 10 Pro") to a fixed set of pre-defined canonical values (e.g. "Windows 10"). Earlier works on attribute normalization focused on fuzzy string matching (also referred as syntactic matching in this paper). In this work, we first perform an extensive study of nine syntactic matching algorithms and establish that 'cosine' similarity leads to best results, showing 2.7% improvement over commonly used Jaccard index. Next, we argue that string similarity alone is not sufficient for a…
Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obta…
Performance of deep learning algorithms decreases drastically if the data distributions of the training and testing sets are different. Due to variations in staining protocols, reagent brands, and habits of technicians, color variation in digital histopathology images is quite common. Color variation causes problems for the deployment of deep learning-based solutions for automatic diagnosis system in histopathology. Previously proposed color normalization methods consider a small patch as a reference for normalization, which creates artifacts on out-of-distribution source images. These methods…
Scuola Normale Superiore（高等师范学校）；INFN（意大利国家核物理研究所）；Università di Pisa（比萨大学）
Over the years, there has been growing interest in using Machine Learning techniques for biomedical data processing. When tackling these tasks, one needs to bear in mind that biomedical data depends on a variety of characteristics, such as demographic aspects (age, gender, etc) or the acquisition technology, which might be unrelated with the target of the analysis. In supervised tasks, failing to match the ground truth targets with respect to such characteristics, called confounders, may lead to very misleading estimates of the predictive performance. Many strategies have been proposed to hand…
Southeast University（东南大学）；University of California, Berkeley（加州大学伯克利分校）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；International Computer Science Institute（国际计算机科学研究所）
Federated learning (FL) is a promising way to use the computing power of mobile devices while maintaining the privacy of users. Current work in FL, however, makes the unrealistic assumption that the users have ground-truth labels on their devices, while also assuming that the server has neither data nor labels. In this work, we consider the more realistic scenario where the users have only unlabeled data, while the server has some labeled data, and where the amount of labeled data is smaller than the amount of unlabeled data. We call this learning problem semi-supervised federated learning (SS…
Tokyo Metropolitan University（东京都立大学）；The University of Tokyo（东京大学）；Chiba University（千叶大学）
Vanishing component analysis (VCA) computes approximate generators of vanishing ideals of samples, which are further used for extracting nonlinear features of the samples. Recent studies have shown that normalization of approximate generators plays an important role and different normalization leads to generators of different properties. In this paper, inspired by recent self-supervised frameworks, we propose a contrastive normalization method for VCA, where we impose the generators to vanish on the target samples and to be normalized on the transformed samples. We theoretically show that a co…
In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set. This initialization is followed by an expectation maximization algorithm, where further training reduces classification entropy on the unlabeled da…
NEC Laboratories America（NEC美国实验室）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Recent semi-supervised learning algorithms have demonstrated greater success with higher overall performance due to better-unlabeled data representations. Nonetheless, recent research suggests that the performance of the SSL algorithm can be degraded when the unlabeled set contains out-of-distribution examples (OODs). This work addresses the following question: How do out-of-distribution (OOD) data adversely affect semi-supervised learning algorithms? To answer this question, we investigate the critical causes of OOD's negative effect on SSL algorithms. In particular, we found that 1) certain …
Large pre-trained models, such as Bert, GPT, and Wav2Vec, have demonstrated great potential for learning representations that are transferable to a wide variety of downstream tasks . It is difficult to obtain a large quantity of supervised data due to the limited availability of resources and time. In light of this, a significant amount of research has been conducted in the area of adopting large pre-trained datasets for diverse downstream tasks via fine tuning, linear probing, or prompt tuning in low resource settings. Normalization techniques are essential for accelerating training and impro…
Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）；Indian Institute of Science Education and Research Kolkata（印度科学教育与研究学院加尔各答分院）
A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as search/retrieval and classification over all the available data, we need robust algorithms for text normalization, i.e., for cleaning different kinds of noise in the text. There have been several efforts towards cleaning or normalizing noisy text; however, many of the existing text normalization methods are supervised and require language-dependent resources or large …
Real world data is mostly unlabeled or only few instances are labeled. Manually labeling data is a very expensive and daunting task. This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as semi-supervised/supervised techniques. Contrastive self-supervised learning has emerged as a powerful direction, in some cases outperforming supervised techniques. In this study, we propose, SelfGNN, a novel contrastive self-supervised graph neural network (GNN) without relying on explicit contrastive terms. We leverage Batch Normalization, which introduces i…
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Incorporating sparsity priors in learning tasks can give rise to simple, and interpretable models for complex high dimensional data. Sparse models have found widespread use in structure discovery, recovering data from corruptions, and a variety of large scale unsupervised and supervised learning problems. Assuming the availability of sufficient data, these methods infer dictionaries for sparse representations by optimizing for high-fidelity reconstruction. In most scenarios, the reconstruction quality is measured using the squared Euclidean distance, and efficient algorithms have been develope…
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labelled development data, which is highly expensive in most cases. We present a cheap PLDA training approach, which assumes that speakers in the same session can be easily separated, and speakers in different sessions are simply different. This results in `weak labels' which are not fully accurate but cheap, leading to a weak PLDA training. Our experimental results on real-life large-scale telephony custom…
Facebook AI Research（脸书人工智能研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models. Our approach first randomly masks out a portion of the input sequence and then predicts the feature of the masked regions. We study five different types of features and find Histograms of Oriented Gradients (HOG), a hand-crafted feature descriptor, works particularly well in terms of both performance and efficiency. We observe that the local contrast normalization in HOG is essential for good results, which is in line with earlier work using HOG for visual recognition. Our approach can learn abund…
University of Cambridge（剑桥大学）；Alan Turing Institute（阿兰·图灵研究所）
Wearable devices such as smartwatches are becoming increasingly popular tools for objectively monitoring physical activity in free-living conditions. To date, research has primarily focused on the purely supervised task of human activity recognition, demonstrating limited success in inferring high-level health outcomes from low-level signals. Here, we present a novel self-supervised representation learning method using activity and heart rate (HR) signals without semantic labels. With a deep neural network, we set HR responses as the supervisory signal for the activity data, leveraging their u…
