The literature for fairness-aware machine learning knows a plethora of different fairness notions. It is however wellknown, that it is impossible to satisfy all of them, as certain notions contradict each other. In this paper, we take a closer look at academic performance prediction (APP) systems and try to distil which fairness notions suit this task most. For this, we scan recent literature proposing guidelines as to which fairness notion to use and apply these guidelines onto APP. Our findings suggest equalised odds as most suitable notion for APP, based on APP's WYSIWYG worldview as well as potential long-term improvements for the population.

I had no success using regression, so first I'll use classification to determine which samples are zero, then do regression on the rest. The regression approach works quite well when there aren't a ton of zero values in y) Is this a valid approach to improving the ROC score? I can't see any reason why not but ML is not my specialty and I might be missing something. If it is valid, do I have to watch out for any class imbalances in the resulting high confidence test set when computing the ROC score?

For new participants - Executive summary: (1) The task is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content, paralinguistic attributes, intelligibility and naturalness. (2) Training, development and evaluation datasets are provided in addition to 3 different baseline anonymization systems, evaluation scripts, and metrics. Participants apply their developed anonymization systems, run evaluation scripts and submit objective evaluation results and anonymized speech data to the organizers. (3) Results will be presented at a workshop held in conjunction with INTERSPEECH 2022 to which all participants are invited to present their challenge systems and to submit additional workshop papers. For readers familiar with the VoicePrivacy Challenge - Changes w.r.t. 2020: (1) A stronger, semi-informed attack model in the form of an automatic speaker verification (ASV) system trained on anonymized (per-utterance) speech data. (2) Complementary metrics comprising the equal error rate (EER) as a privacy metric, the word error rate (WER) as a primary utility metric, and the pitch correlation and gain of voice distinctiveness as secondary utility metrics. (3) A new ranking policy based upon a set of minimum target privacy requirements.

Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training strategy for the OSR problems. In the first stage, we introduce a self-supervised feature decoupling method that finds the content features of the input samples from the known classes. Specifically, our feature decoupling approach learns a representation that can be split into content features and transformation features. In the second stage, we fine-tune the content features with the class labels. The fine-tuned content features are then used for the OSR problems. Moreover, we consider an unsupervised OSR scenario, where we cluster the content features learned from the first stage. To measure representation quality, we introduce intra-inter ratio (IIR). Our experimental results indicate that our proposed self-supervised approach outperforms others in image and malware OSR problems. Also, our analyses indicate that IIR is correlated with OSR performance.

Anomaly-based Intrusion Detection System (IDS) has been a hot research topic because of its ability to detect new threats rather than only memorized signatures threats of signature-based IDS. Especially after the availability of advanced technologies that increase the number of hacking tools and increase the risk impact of an attack. The problem of any anomaly-based model is its high false-positive rate. The high false-positive rate is the reason why anomaly IDS is not commonly applied in practice. Because anomaly-based models classify an unseen pattern as a threat where it may be normal but not included in the training dataset. This type of problem is called overfitting where the model is not able to generalize. Optimizing Anomaly-based models by having a big training dataset that includes all possible normal cases may be an optimal solution but could not be applied in practice. Although we can increase the number of training samples to include much more normal cases, still we need a model that has more ability to generalize. In this research paper, we propose applying deep model instead of traditional models because it has more ability to generalize. Thus, we will obtain less false-positive by using big data and deep model. We made a comparison between machine learning and deep learning algorithms in the optimization of anomaly-based IDS by decreasing the false-positive rate. We did an experiment on the NSL-KDD benchmark and compared our results with one of the best used classifiers in traditional learning in IDS optimization. The experiment shows 10% lower false-positive by using deep learning instead of traditional learning.

An appropriate ethical framework around the use of Artificial Intelligence (AI) in healthcare has become a key desirable with the increasingly widespread deployment of this technology. Advances in AI hold the promise of improving the precision of outcome prediction at the level of the individual. However, the addition of these technologies to patient-clinician interactions, as with any complex human interaction, has potential pitfalls. While physicians have always had to carefully consider the ethical background and implications of their actions, detailed deliberations around fast-moving technological progress may not have kept up. We use a common but key challenge in healthcare interactions, the disclosure of bad news (likely imminent death), to illustrate how the philosophical framework of the 'Felicific Calculus' developed in the 18th century by Jeremy Bentham, may have a timely quasi-quantitative application in the age of AI. We show how this ethical algorithm can be used to assess, across seven mutually exclusive and exhaustive domains, whether an AI-supported action can be morally justified.

A central challenge in building robotic prostheses is the creation of a sensor-based system able to read physiological signals from the lower limb and instruct a robotic hand to perform various tasks. Existing systems typically perform discrete gestures such as pointing or grasping, by employing electromyography (EMG) or ultrasound (US) technologies to analyze muscle states. While estimating finger gestures has been done in the past by detecting prominent gestures, we are interested in detection, or inference, done in the context of fine motions that evolve over time. Examples include motions occurring when performing fine and dexterous tasks such as keyboard typing or piano playing. We consider this task as an important step towards higher adoption rates of robotic prostheses among arm amputees, as it has the potential to dramatically increase functionality in performing daily tasks. To this end, we present an end-to-end robotic system, which can successfully infer fine finger motions. This is achieved by modeling the hand as a robotic manipulator and using it as an intermediate representation to encode muscles' dynamics from a sequence of US images. We evaluated our method by collecting data from a group of subjects and demonstrating how it can be used to replay music played or text typed. To the best of our knowledge, this is the first study demonstrating these downstream tasks within an end-to-end system.

The paucity of labeled data is a typical challenge in the automotive industry. Annotating time-series measurements requires solid domain knowledge and in-depth exploratory data analysis, which implies a high labeling effort. Conventional Active Learning (AL) addresses this issue by actively querying the most informative instances based on the estimated classification probability and retraining the model iteratively. However, the learning efficiency strongly relies on the initial model, resulting in the trade-off between the size of the initial dataset and the query number. This paper proposes a novel Few-Shot Learning (FSL)-based AL framework, which addresses the trade-off problem by incorporating a Prototypical Network (ProtoNet) in the AL iterations. The results show an improvement, on the one hand, in the robustness to the initial model and, on the other hand, in the learning efficiency of the ProtoNet through the active selection of the support set in each iteration. This framework was validated on UCI HAR/HAPT dataset and a real-world braking maneuver dataset. The learning performance significantly surpasses traditional AL algorithms on both datasets, achieving 90% classification accuracy with 10% and 5% labeling effort, respectively.

Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. Although various algorithms have been extensively studied for AUPRC optimization, the generalization is only guaranteed in the multi-query case. In this work, we present the first trial in the single-query generalization of stochastic AUPRC optimization. For sharper generalization bounds, we focus on algorithm-dependent generalization. There are both algorithmic and theoretical obstacles to our destination. From an algorithmic perspective, we notice that the majority of existing stochastic estimators are biased only when the sampling strategy is biased, and is leave-one-out unstable due to the non-decomposability. To address these issues, we propose a sampling-rate-invariant unbiased stochastic estimator with superior stability. On top of this, the AUPRC optimization is formulated as a composition optimization problem, and a stochastic algorithm is proposed to solve this problem. From a theoretical perspective, standard techniques of the algorithm-dependent generalization analysis cannot be directly applied to such a listwise compositional optimization problem. To fill this gap, we extend the model stability from instancewise losses to listwise losses and bridge the corresponding generalization and stability. Additionally, we construct state transition matrices to describe the recurrence of the stability, and simplify calculations by matrix spectrum. Practically, experimental results on three image retrieval datasets on speak to the effectiveness and soundness of our framework.

The accelerated growth in synthetic visual media generation and manipulation has now reached the point of raising significant concerns and posing enormous intimidations towards society. There is an imperative need for automatic detection networks towards false digital content and avoid the spread of dangerous artificial information to contend with this threat. In this paper, we utilize and compare two kinds of handcrafted features(SIFT and HoG) and two kinds of deep features(Xception and CNN+RNN) for the deepfake detection task. We also check the performance of these features when there are mismatches between training sets and test sets. Evaluation is performed on the famous FaceForensics++ dataset, which contains four sub-datasets, Deepfakes, Face2Face, FaceSwap and NeuralTextures. The best results are from Xception, where the accuracy could surpass over 99\% when the training and test set are both from the same sub-dataset. In comparison, the results drop dramatically when the training set mismatches the test set. This phenomenon reveals the challenge of creating a universal deepfake detection system.