اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدThe Prevalence of Errors in Machine Learning Experiments
88
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Context: Conducting experiments is central to research machine learning research to benchmark, evaluate and compare learning algorithms. Consequently it is important we conduct reliable, trustworthy experiments. Objective: We investigate the incidence of errors in a sample of machine learning experiments in the domain of software defect prediction. Our focus is simple arithmetical and statistical errors. Method: We analyse 49 papers describing 2456 individual experimental results from a previously undertaken systematic review comparing supervised and unsupervised defect prediction classifiers. We extract the confusion matrices and test for relevant constraints, e.g., the marginal probabilities must sum to one. We also check for multiple statistical significance testing errors. Results: We find that a total of 22 out of 49 papers contain demonstrable errors. Of these 7 were statistical and 16 related to confusion matrix inconsistency (one paper contained both classes of error). Conclusions: Whilst some errors may be of a relatively trivial nature, e.g., transcription errors their presence does not engender confidence. We strongly urge researchers to follow open science principles so errors can be more easily be detected and corrected, thus as a community reduce this worryingly high error rate with our computational experiments.
قيم البحث
اقرأ أيضاً
Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for machine lear
ning models. They cause significant gaps between model performance in the lab and in the real world. Our work is a solution to prevalence bias. Prevalence bias is the discrepancy between the prevalence of a pathology and its sampling rate in the training dataset, introduced upon collecting data or due to the practioner rebalancing the training batches. This paper lays the theoretical and computational framework for training models, and for prediction, in the presence of prevalence bias. Concretely a bias-corrected loss function, as well as bias-corrected predictive rules, are derived under the principles of Bayesian risk minimization. The loss exhibits a direct connection to the information gain. It offers a principled alternative to heuristic training losses and complements test-time procedures based on selecting an operating point from summary curves. It integrates seamlessly in the current paradigm of (deep) learning using stochastic backpropagation and naturally with Bayesian models.
Logit models are usually applied when studying individual travel behavior, i.e., to predict travel mode choice and to gain behavioral insights on traveler preferences. Recently, some studies have applied machine learning to model travel mode choice a
nd reported higher out-of-sample predictive accuracy than traditional logit models (e.g., multinomial logit). However, little research focuses on comparing the interpretability of machine learning with logit models. In other words, how to draw behavioral insights from the high-performance black-box machine-learning models remains largely unsolved in the field of travel behavior modeling. This paper aims at providing a comprehensive comparison between the two approaches by examining the key similarities and differences in model development, evaluation, and behavioral interpretation between logit and machine-learning models for travel mode choice modeling. To complement the theoretical discussions, the paper also empirically evaluates the two approaches on the stated-preference survey data for a new type of transit system integrating high-frequency fixed-route services and ridesourcing. The results show that machine learning can produce significantly higher predictive accuracy than logit models. Moreover, machine learning and logit models largely agree on many aspects of behavioral interpretations. In addition, machine learning can automatically capture the nonlinear relationship between the input features and choice outcomes. The paper concludes that there is great potential in merging ideas from machine learning and conventional statistical methods to develop refined models for travel behavior research and suggests some new research directions.
Most problems in Earth sciences aim to do inferences about the system, where accurate predictions are just a tiny part of the whole problem. Inferences mean understanding variables relations, deriving models that are physically interpretable, that ar
e simple parsimonious, and mathematically tractable. Machine learning models alone are excellent approximators, but very often do not respect the most elementary laws of physics, like mass or energy conservation, so consistency and confidence are compromised. In this paper, we describe the main challenges ahead in the field, and introduce several ways to live in the Physics and machine learning interplay: to encode differential equations from data, constrain data-driven models with physics-priors and dependence constraints, improve parameterizations, emulate physical models, and blend data-driven and process-based models. This is a collective long-term AI agenda towards developing and applying algorithms capable of discovering knowledge in the Earth system.
Machine learning (ML) currently exerts an outsized influence on the world, increasingly affecting communities and institutional practices. It is therefore critical that we question vague conceptions of the field as value-neutral or universally benefi
cial, and investigate what specific values the field is advancing. In this paper, we present a rigorous examination of the values of the field by quantitatively and qualitatively analyzing 100 highly cited ML papers published at premier ML conferences, ICML and NeurIPS. We annotate key features of papers which reveal their values: how they justify their choice of project, which aspects they uplift, their consideration of potential negative consequences, and their institutional affiliations and funding sources. We find that societal needs are typically very loosely connected to the choice of project, if mentioned at all, and that consideration of negative consequences is extremely rare. We identify 67 values that are uplifted in machine learning research, and, of these, we find that papers most frequently justify and assess themselves based on performance, generalization, efficiency, researcher understanding, novelty, and building on previous work. We present extensive textual evidence and analysis of how these values are operationalized. Notably, we find that each of these top values is currently being defined and applied with assumptions and implications generally supporting the centralization of power. Finally, we find increasingly close ties between these highly cited papers and tech companies and elite universities.
The Right to be Forgotten is part of the recently enacted General Data Protection Regulation (GDPR) law that affects any data holder that has data on European Union residents. It gives EU residents the ability to request deletion of their personal da
ta, including training records used to train machine learning models. Unfortunately, Deep Neural Network models are vulnerable to information leaking attacks such as model inversion attacks which extract class information from a trained model and membership inference attacks which determine the presence of an example in a models training data. If a malicious party can mount an attack and learn private information that was meant to be removed, then it implies that the model owner has not properly protected their users rights and their models may not be compliant with the GDPR law. In this paper, we present two efficient methods that address this question of how a model owner or data holder may delete personal data from models in such a way that they may not be vulnerable to model inversion and membership inference attacks while maintaining model efficacy. We start by presenting a real-world threat model that shows that simply removing training data is insufficient to protect users. We follow that up with two data removal methods, namely Unlearning and Amnesiac Unlearning, that enable model owners to protect themselves against such attacks while being compliant with regulations. We provide extensive empirical analysis that show that these methods are indeed efficient, safe to apply, effectively remove learned information about sensitive data from trained models while maintaining model efficacy.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
