Despite the success of deep neural networks (DNNs) in enabling on-device voice assistants, increasing evidence of bias and discrimination in machine learning is raising the urgency of investigating the fairness of these systems. Speaker verification is a form of biometric identification that gives access to voice assistants. Due to a lack of fairness metrics and evaluation frameworks that are appropriate for testing the fairness of speaker verification components, little is known about how model performance varies across subgroups, and what factors influence performance variation. To tackle this emerging challenge, we design and develop SVEva Fair, an accessible, actionable and model-agnostic framework for evaluating the fairness of speaker verification components. The framework provides evaluation measures and visualisations to interrogate model performance across speaker subgroups and compare fairness between models. We demonstrate SVEva Fair in a case study with end-to-end DNNs trained on the VoxCeleb datasets to reveal potential bias in existing embedded speech recognition systems based on the demographic attributes of speakers. Our evaluation shows that publicly accessible benchmark models are not fair and consistently produce worse predictions for some nationalities, and for female speakers of most nationalities. To pave the way for fair and reliable embedded speaker verification, SVEva Fair has been implemented as an open-source python library and can be integrated into the embedded ML development pipeline to facilitate developers and researchers in troubleshooting unreliable speaker verification performance, and selecting high impact approaches for mitigating fairness challenges
相關內容
Easier access to the internet and social media has made disseminating information through online sources very easy. Sources like Facebook, Twitter, online news sites and personal blogs of self-proclaimed journalists have become significant players in providing news content. The sheer amount of information and the speed at which it is generated online makes it practically beyond the scope of human verification. There is, hence, a pressing need to develop technologies that can assist humans with automatic fact-checking and reliable identification of fake news. This paper summarizes the multiple approaches that were undertaken and the experiments that were carried out for the task. Credibility information and metadata associated with the news article have been used for improved results. The experiments also show how modelling justification or evidence can lead to improved results. Additionally, the use of visual features in addition to linguistic features is demonstrated. A detailed comparison of the results showing that our models perform significantly well when compared to robust baselines as well as state-of-the-art models are presented.
Auditing trained deep learning (DL) models prior to deployment is vital in preventing unintended consequences. One of the biggest challenges in auditing is in understanding how we can obtain human-interpretable specifications that are directly useful to the end-user. We address this challenge through a sequence of semantically-aligned unit tests, where each unit test verifies whether a predefined specification (e.g., accuracy over 95%) is satisfied with respect to controlled and semantically aligned variations in the input space (e.g., in face recognition, the angle relative to the camera). We perform these unit tests by directly verifying the semantically aligned variations in an interpretable latent space of a generative model. Our framework, AuditAI, bridges the gap between interpretable formal verification and scalability. With evaluations on four different datasets, covering images of towers, chest X-rays, human faces, and ImageNet classes, we show how AuditAI allows us to obtain controlled variations for verification and certified training while addressing the limitations of verifying using only pixel-space perturbations. A blog post accompanying the paper is at this link //developer.nvidia.com/blog/nvidia-research-auditing-ai-models-for-verified-deployment-under-semantic-specifications
In some problem spaces, the high cost of obtaining ground truth labels necessitates use of lower quality reference datasets. It is difficult to benchmark model performance using these datasets, as evaluation results may be biased. We propose a supplement to using reference labels, which we call an approximate ground truth refinement (AGTR). Using an AGTR, we prove that bounds on specific metrics used to evaluate clustering algorithms and multi-class classifiers can be computed without reference labels. We also introduce a procedure that uses an AGTR to identify inaccurate evaluation results produced from datasets of dubious quality. Creating an AGTR requires domain knowledge, and malware family classification is a task with robust domain knowledge approaches that support the construction of an AGTR. We demonstrate our AGTR evaluation framework by applying it to a popular malware labeling tool to diagnose over-fitting in prior testing and evaluate changes whose impact could not be meaningfully quantified under previous data.
In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society. The intention of developing AI is to benefit humans, by reducing human labor, bringing everyday convenience to human lives, and promoting social good. However, recent research and AI applications show that AI can cause unintentional harm to humans, such as making unreliable decisions in safety-critical scenarios or undermining fairness by inadvertently discriminating against one group. Thus, trustworthy AI has attracted immense attention recently, which requires careful consideration to avoid the adverse effects that AI may bring to humans, so that humans can fully trust and live in harmony with AI technologies. Recent years have witnessed a tremendous amount of research on trustworthy AI. In this survey, we present a comprehensive survey of trustworthy AI from a computational perspective, to help readers understand the latest technologies for achieving trustworthy AI. Trustworthy AI is a large and complex area, involving various dimensions. In this work, we focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems. We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.
Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables and propose a novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute and the final predictions, on the graph. We also consider the scenario when the directions on certain edges within those paths cannot be determined. Our framework is also model agnostic and applicable to a variety of quantitative disparity measures. Empirical evaluations on both synthetic and real-world data sets are provided to show that our method can provide precise and comprehensive explanations to the model disparities.
Training datasets for machine learning often have some form of missingness. For example, to learn a model for deciding whom to give a loan, the available training data includes individuals who were given a loan in the past, but not those who were not. This missingness, if ignored, nullifies any fairness guarantee of the training procedure when the model is deployed. Using causal graphs, we characterize the missingness mechanisms in different real-world scenarios. We show conditions under which various distributions, used in popular fairness algorithms, can or can not be recovered from the training data. Our theoretical results imply that many of these algorithms can not guarantee fairness in practice. Modeling missingness also helps to identify correct design principles for fair algorithms. For example, in multi-stage settings where decisions are made in multiple screening rounds, we use our framework to derive the minimal distributions required to design a fair algorithm. Our proposed algorithm decentralizes the decision-making process and still achieves similar performance to the optimal algorithm that requires centralization and non-recoverable distributions.
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage costs and cannot be done indefinitely. In this work, we seek to improve the identification and verification accuracy of a text-independent speaker recognition system without use of extra data or deeper and more complex models by augmenting the training and testing data, finding the optimal dimensionality of embedding space and use of more discriminative loss functions. Results of experiments on VoxCeleb dataset suggest that: (i) Simple repetition and random time-reversion of utterances can reduce prediction errors by up to 18%. (ii) Lower dimensional embeddings are more suitable for verification. (iii) Use of proposed logistic margin loss function leads to unified embeddings with state-of-the-art identification and competitive verification accuracies.
Rankings of people and items are at the heart of selection-making, match-making, and recommender systems, ranging from employment sites to sharing economy platforms. As ranking positions influence the amount of attention the ranked subjects receive, biases in rankings can lead to unfair distribution of opportunities and resources, such as jobs or income. This paper proposes new measures and mechanisms to quantify and mitigate unfairness from a bias inherent to all rankings, namely, the position bias, which leads to disproportionately less attention being paid to low-ranked subjects. Our approach differs from recent fair ranking approaches in two important ways. First, existing works measure unfairness at the level of subject groups while our measures capture unfairness at the level of individual subjects, and as such subsume group unfairness. Second, as no single ranking can achieve individual attention fairness, we propose a novel mechanism that achieves amortized fairness, where attention accumulated across a series of rankings is proportional to accumulated relevance. We formulate the challenge of achieving amortized individual fairness subject to constraints on ranking quality as an online optimization problem and show that it can be solved as an integer linear program. Our experimental evaluation reveals that unfair attention distribution in rankings can be substantial, and demonstrates that our method can improve individual fairness while retaining high ranking quality.
We present a challenging and realistic novel dataset for evaluating 6-DOF object tracking algorithms. Existing datasets show serious limitations---notably, unrealistic synthetic data, or real data with large fiducial markers---preventing the community from obtaining an accurate picture of the state-of-the-art. Our key contribution is a novel pipeline for acquiring accurate ground truth poses of real objects w.r.t a Kinect V2 sensor by using a commercial motion capture system. A total of 100 calibrated sequences of real objects are acquired in three different scenarios to evaluate the performance of trackers in various scenarios: stability, robustness to occlusion and accuracy during challenging interactions between a person and the object. We conduct an extensive study of a deep 6-DOF tracking architecture and determine a set of optimal parameters. We enhance the architecture and the training methodology to train a 6-DOF tracker that can robustly generalize to objects never seen during training, and demonstrate favorable performance compared to previous approaches trained specifically on the objects to track.
Person re-identification (re-id) is a critical problem in video analytics applications such as security and surveillance. The public release of several datasets and code for vision algorithms has facilitated rapid progress in this area over the last few years. However, directly comparing re-id algorithms reported in the literature has become difficult since a wide variety of features, experimental protocols, and evaluation metrics are employed. In order to address this need, we present an extensive review and performance evaluation of single- and multi-shot re-id algorithms. The experimental protocol incorporates the most recent advances in both feature extraction and metric learning. To ensure a fair comparison, all of the approaches were implemented using a unified code library that includes 11 feature extraction algorithms and 22 metric learning and ranking techniques. All approaches were evaluated using a new large-scale dataset that closely mimics a real-world problem setting, in addition to 16 other publicly available datasets: VIPeR, GRID, CAVIAR, DukeMTMC4ReID, 3DPeS, PRID, V47, WARD, SAIVT-SoftBio, CUHK01, CHUK02, CUHK03, RAiD, iLIDSVID, HDA+ and Market1501. The evaluation codebase and results will be made publicly available for community use.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191