Quantification is the research field that studies methods for counting the number of data points that belong to each class in an unlabeled sample. Traditionally, researchers in this field assume the availability of labelled observations for all classes to induce a quantification model. However, we often face situations where the number of classes is large or even unknown, or we have reliable data for a single class. When inducing a multi-class quantifier is infeasible, we are often concerned with estimates for a specific class of interest. In this context, we have proposed a novel setting known as One-class Quantification (OCQ). In contrast, Positive and Unlabeled Learning (PUL), another branch of Machine Learning, has offered solutions to OCQ, despite quantification not being the focal point of PUL. This article closes the gap between PUL and OCQ and brings both areas together under a unified view. We compare our method, Passive Aggressive Threshold (PAT), against PUL methods and show that PAT generally is the fastest and most accurate algorithm. PAT induces quantification models that can be reused to quantify different samples of data. We additionally introduce Exhaustive TIcE (ExTIcE), an improved version of the PUL algorithm Tree Induction for c Estimation (TIcE). We show that ExTIcE quantifies more accurately than PAT and the other assessed algorithms in scenarios where several negative observations are identical to the positive ones.
Most machine learning (ML) algorithms have several stochastic elements, and their performances are affected by these sources of randomness. This paper uses an empirical study to systematically examine the effects of two sources: randomness in model training and randomness in the partitioning of a dataset into training and test subsets. We quantify and compare the magnitude of the variation in predictive performance for the following ML algorithms: Random Forests (RFs), Gradient Boosting Machines (GBMs), and Feedforward Neural Networks (FFNNs). Among the different algorithms, randomness in mode…
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We th…
Weizmann Institute of Science（魏茨曼科学研究所）；Stanford University（斯坦福大学）
A learning algorithm $A$ trained on a dataset $D$ is revealed to have poor performance on some subpopulation at test time. Where should the responsibility for this lay? It can be argued that the data is responsible, if for example training $A$ on a more representative dataset $D'$ would have improved the performance. But it can similarly be argued that $A$ itself is at fault, if training a different variant $A'$ on the same dataset $D$ would have improved performance. As ML becomes widespread and such failure cases more common, these types of questions are proving to be far from hypothetical. …
Monash University（莫纳什大学）；University College London（伦敦大学学院）
In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour. Despite the importance, there is no public tool that supports such analysis of pre-training corpora at large scale. To help research in this space, we launch Koala, a searchable index over large pre-training corpora using compressed suffix arrays with highly efficient compression rate and search support. In its first release we index the public proportion of OPT 175B pre-training data. Koala provides a framework to do forensic analysis on the curren…
The notion of disentangled autoencoders was proposed as an extension to the variational autoencoder by introducing a disentanglement parameter $β$, controlling the learning pressure put on the possible underlying latent representations. For certain values of $β$ this kind of autoencoders is capable of encoding independent input generative factors in separate elements of the code, leading to a more interpretable and predictable model behaviour. In this paper we quantify the effects of the parameter $β$ on the model performance and disentanglement. After training multiple models with the same va…
School of Informatics and Computing, Indiana University（印第安纳大学信息学与计算学院）；Indiana University Network Science Institute（印第安纳大学网络科学研究所）
Social media have become the main vehicle of information production and consumption online. Millions of users every day log on their Facebook or Twitter accounts to get updates and news, read about their topics of interest, and become exposed to new opportunities and interactions. Although recent studies suggest that the contents users produce will affect the emotions of their readers, we still lack a rigorous understanding of the role and effects of contents sentiment on the dynamics of information diffusion. This work aims at quantifying the effect of sentiment on information diffusion, to u…
Quantifying the Ease of Reproducing Training Data in Unconditional Diffusion Models
Graduate School of Informatics, Nagoya University（名古屋大学信息学研究科）；Institute of Materials and Systems for Sustainability, Nagoya University（名古屋大学可持续性材料与系统研究所）
Element AI；Mila（米拉）；Université de Montréal（蒙特利尔大学）；Polytechnique Montréal（蒙特利尔高等理工学院）；CIRAIG
From an environmental standpoint, there are a few crucial aspects of training a neural network that have a major impact on the quantity of carbon that it emits. These factors include: the location of the server used for training and the energy grid that it uses, the length of the training procedure, and even the make and model of hardware on which the training takes place. In order to approximate these emissions, we present our Machine Learning Emissions Calculator, a tool for our community to better understand the environmental impact of training ML models. We accompany this tool with an expl…
Projected Boosting with Fairness Constraints: Quantifying the Cost of Fair Training Distributions
Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN 37232, USA（生物统计学系，范德比尔特大学医学中心）；Department of Informatics, King's College London, WC2R 2LS London, UK（信息学系，伦敦国王学院）
National University of Singapore（新加坡国立大学）；Cardiff University（卡迪夫大学）
Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show the possibility of these membership inference (tracing) attacks against complex deep learning models. However, the attack results are dependent on the specific training data, can be obtained only after the tedious process of training the model and performing the attack, and are missing any measure of the confidence and unused potential power of the attack. …
College of Aerospace Science and Engineering National University of Defense Technology（国防科技大学航空航天学院）；Defense Innovation Institute Chinese Academy of Military Science（中国人民解放军军事科学院国防创新研究院）
For the temperature field reconstruction (TFR), a complex image-to-image regression problem, the convolutional neural network (CNN) is a powerful surrogate model due to the convolutional layer's good image feature extraction ability. However, a lot of labeled data is needed to train CNN, and the common CNN can not quantify the aleatoric uncertainty caused by data noise. In actual engineering, the noiseless and labeled training data is hardly obtained for the TFR. To solve these two problems, this paper proposes a deep Monte Carlo quantile regression (Deep MC-QR) method for reconstructing the t…
Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen using heuristics of either distribution shift or augmentation diversity. Inspired by these, we seek to quantify how data augmentation improves model generalization. To this end, we introduce interpretable and easy-to-compute measures: Affinity and Diversity. We find that augmentation performance is predicted not by either of these alone but by jointly optimiz…
Quantifying Out-of-Training Uncertainty of Neural-Network based Turbulence Closures
Mechanical and Aerospace Engineering, Utah State University（犹他州立大学机械与航空航天工程学院）；Idaho National Laboratory（爱达荷国家实验室）；School of Nuclear Science and Engineering, Oregon State University（俄勒冈州立大学核科学与工程学院）
Neuroimaging datasets keep growing in size to address increasingly complex medical questions. However, even the largest datasets today alone are too small for training complex machine learning models. A potential solution is to increase sample size by pooling scans from several datasets. In this work, we combine 12,207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data. First, we systematically define these biases. Second, we detect bias by experimentally showing that scans can be correctly assigned to the…
Google Research（谷歌研究院）；University of Pennsylvania（宾夕法尼亚大学）；Cornell University（康奈尔大学）
Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing user data), degrades utility (repeated easy-to-memorize text is often low quality), and hurts fairness (some texts are memorized over others). We describe three log-linear relationships that quantify the degree to which LMs emit memorized training data. Memorization significantly grows as we increase (1) the capacity of a model, (2) the number of times an ex…
Boston University（波士顿大学）；Microsoft Research New England（微软新英格兰研究院）
Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in {\em word embedding}, a popular framework to represent text data. As their use becomes increasingly common, applications can inadvertently amplify unwanted stereotypes. We show across multiple datasets that the embeddings contain significant gender stereotypes, especially with regard to profe…
Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
Hong Kong University of Science and Technology（香港科技大学）；Shanghai Jiao Tong University（上海交通大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深港协同创新研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
This paper discusses a crowdsourcing based method that we designed to quantify the importance of different attributes of a dataset in determining the outcome of a classification problem. This heuristic, provided by humans acts as the initial weight seed for machine learning models and guides the model towards a better optimal during the gradient descent process. Often times when dealing with data, it is not uncommon to deal with skewed datasets, that over represent items of certain classes, while underrepresenting the rest. Skewed datasets may lead to unforeseen issues with models such as lear…
Istanbul Technical University（伊斯坦布尔理工大学）；University of Dundee（邓迪大学）
Graph neural networks (GNNs) have witnessed an unprecedented proliferation in tackling several problems in computer vision, computer-aided diagnosis, and related fields. While prior studies have focused on boosting the model accuracy, quantifying the reproducibility of the most discriminative features identified by GNNs is still an intact problem that yields concerns about their reliability in clinical applications in particular. Specifically, the reproducibility of biological markers across clinical datasets and distribution shifts across classes (e.g., healthy and disordered brains) is of pa…
Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion
School of Computer Science, Tel Aviv University（特拉维夫大学计算机科学学院）；Faculty of Law, Tel Aviv University（特拉维夫大学法学院）；School of Electrical Engineering, Tel Aviv University（特拉维夫大学电气工程学院）
Technical Report: Quantifying and Analyzing the Generalization Power of a DNN
University of Electronic Science and Technology of China（电子科技大学）；Shanghai Jiao Tong University（上海交通大学）；Institute of Artificial Intelligence, China Telecom（中国电信人工智能研究院）
Hong Kong University of Science and Technology（香港科技大学）；Clustar Technology Co., Ltd.（星环科技有限公司）；Peng Cheng Lab（鹏城实验室）
The scarcity of data and isolated data islands encourage different organizations to share data with each other to train machine learning models. However, there are increasing concerns on the problems of data privacy and security, which urges people to seek a solution like Federated Transfer Learning (FTL) to share training data without violating data privacy. FTL leverages transfer learning techniques to utilize data from different sources for training, while achieving data privacy protection without significant accuracy loss. However, the benefits come with a cost of extra computation and com…
Quantifying Overfitting: Evaluating Neural Network Performance through Analysis of Null Space
Iran University of Science and Technology（伊朗科技大学）；Okinawa Institute of Science and Technology（冲绳科学技术研究所）；Institute For Research In Fundamental Sciences（基础科学研究所）
Recent advances in reconstruction methods for inverse problems leverage powerful data-driven models, e.g., deep neural networks. These techniques have demonstrated state-of-the-art performances for several imaging tasks, but they often do not provide uncertainty on the obtained reconstruction. In this work, we develop a scalable, data-driven, knowledge-aided computational framework to quantify the model uncertainty via Bayesian neural networks. The approach builds on, and extends deep gradient descent, a recently developed greedy iterative training scheme, and recasts it within a probabilistic…
Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
Department of Physics, University of Maryland, College Park（马里兰大学物理系）；Department of Computer Science, University of Maryland, College Park（马里兰大学计算机科学系）；Joint Quantum Institute, University of Maryland, College Park（马里兰大学联合量子研究所）；Meta Superintelligence Labs, Fundamental AI Research（Meta超智能实验室，基础人工智能研究）
University of Melbourne（墨尔本大学）；Macquarie University（麦考瑞大学）
Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing success of these attacks motivates the need for modelling membership information leakage using information theory and for investigating properties of machine learning models and training algorithms that can reduce membership information leakage. We use conditional mutual information leakage to measure the amount of information leakage from the trained machine learning model ab…
SAP（SAP公司）；Salzburg University of Applied Sciences（萨尔茨堡应用科学大学）；University of Heidelberg（海德堡大学）；University of Waterloo（滑铁卢大学）
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters $(ε,δ)$. Choosing meaningful privacy parameters is key, since models trained with weak privacy parameters might result in excessive privacy leakage, while strong privacy parameters might overly degrade model utility. However, privacy parameter values are difficult to choose for two main reasons. First, the theoretical upper bound on privacy loss $(ε,δ)$ might be loose, depending on the cho…
The University of Melbourne（墨尔本大学）；RMIT University（皇家墨尔本理工大学）
Public datasets are often used to evaluate the efficacy and generalizability of state-of-the-art methods for many tasks in natural language processing (NLP). However, the presence of overlap between the train and test datasets can lead to inflated results, inadvertently evaluating the model's ability to memorize and interpreting it as the ability to generalize. In addition, such data sets may not provide an effective indicator of the performance of these methods in real world scenarios. We identify leakage of training data into test data on several publicly available datasets used to evaluate …
Millions of vulnerable consumer IoT devices in home networks are the enabler for cyber crimes putting user privacy and Internet security at risk. Internet service providers (ISPs) are best poised to play key roles in mitigating risks by automatically inferring active IoT devices per household and notifying users of vulnerable ones. Developing a scalable inference method that can perform robustly across thousands of home networks is a non-trivial task. This paper focuses on the challenges of developing and applying data-driven inference models when labeled data of device behaviors is limited an…
