The FAIR Guiding Principles aim to improve the findability, accessibility, interoperability, and reusability of digital content by making them both human and machine actionable. However, these principles have not yet been broadly adopted in the domain of machine learning-based program analyses and optimizations for High-Performance Computing (HPC). In this paper, we design a methodology to make HPC datasets and machine learning models FAIR after investigating existing FAIRness assessment and improvement techniques. Our methodology includes a comprehensive, quantitative assessment for elected data, followed by concrete, actionable suggestions to improve FAIRness with respect to common issues related to persistent identifiers, rich metadata descriptions, license and provenance information. Moreover, we select a representative training dataset to evaluate our methodology. The experiment shows the methodology can effectively improve the dataset and model's FAIRness from an initial score of 19.1% to the final score of 83.0%.

CatBoost is a popular machine learning library. CatBoost models are based on oblivious decision trees, making training and evaluation rapid. CatBoost has many applications, and some require low latency and high throughput evaluation. This paper investigates the possibilities for improving CatBoost's performance in single-core CPU computations. We explore the new features provided by the AVX instruction sets to optimize evaluation. We increase performance by 20-40% using AVX2 instructions without quality impact. We also introduce a new trade-off between speed and quality. Using float16 for leaf values and AVX-512 instructions, we achieve 50-70% speed-up.

It is well known that different algorithms perform differently well on an instance of an algorithmic problem, motivating algorithm selection (AS): Given an instance of an algorithmic problem, which is the most suitable algorithm to solve it? As such, the AS problem has received considerable attention resulting in various approaches - many of which either solve a regression or ranking problem under the hood. Although both of these formulations yield very natural ways to tackle AS, they have considerable weaknesses. On the one hand, correctly predicting the performance of an algorithm on an instance is a sufficient, but not a necessary condition to produce a correct ranking over algorithms and in particular ranking the best algorithm first. On the other hand, classical ranking approaches often do not account for concrete performance values available in the training data, but only leverage rankings composed from such data. We propose HARRIS- Hybrid rAnking and RegRessIon foreSts - a new algorithm selector leveraging special forests, combining the strengths of both approaches while alleviating their weaknesses. HARRIS' decisions are based on a forest model, whose trees are created based on splits optimized on a hybrid ranking and regression loss function. As our preliminary experimental study on ASLib shows, HARRIS improves over standard algorithm selection approaches on some scenarios showing that combining ranking and regression in trees is indeed promising for AS.

As opaque decision systems are being increasingly adopted in almost any application field, issues about their lack of transparency and human readability are a concrete concern for end-users. Amongst existing proposals to associate human-interpretable knowledge with accurate predictions provided by opaque models, there are rule extraction techniques, capable of extracting symbolic knowledge out of an opaque model. However, how to assess the level of readability of the extracted knowledge quantitatively is still an open issue. Finding such a metric would be the key, for instance, to enable automatic comparison between a set of different knowledge representations, paving the way for the development of parameter autotuning algorithms for knowledge extractors. In this paper we discuss the need for such a metric as well as the criticalities of readability assessment and evaluation, taking into account the most common knowledge representations while highlighting the most puzzling issues.

Federated Learning (FL) is a novel distributed privacy-preserving learning paradigm, which enables the collaboration among several participants (e.g., Internet of Things devices) for the training of machine learning models. However, selecting the participants that would contribute to this collaborative training is highly challenging. Adopting a random selection strategy would entail substantial problems due to the heterogeneity in terms of data quality, and computational and communication resources across the participants. Although several approaches have been proposed in the literature to overcome the problem of random selection, most of these approaches follow a unilateral selection strategy. In fact, they base their selection strategy on only the federated server's side, while overlooking the interests of the client devices in the process. To overcome this problem, we present in this paper FedMint, an intelligent client selection approach for federated learning on IoT devices using game theory and bootstrapping mechanism. Our solution involves the design of: (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several factors such as accuracy and price, (2) intelligent matching algorithms that take into account the preferences of both parties in their design, and (3) bootstrapping technique that capitalizes on the collaboration of multiple federated servers in order to assign initial accuracy value for the newly connected IoT devices. Based on our simulation findings, our strategy surpasses the VanillaFL selection approach in terms of maximizing both the revenues of the client devices and accuracy of the global federated learning model.

Department of Statistics, Stanford University, Stanford, California, United States of America *Authors contributed equally to this work Correspondence should be addressed to teinav@fredhutch.org Abstract A central challenge in every field of biology is to use existing measurements to predict the outcomes of future experiments. In this work, we consider the wealth of antibody inhibition data against variants of the influenza virus. Due to this virus's genetic diversity and evolvability, the variants examined in one study will often have little-to-no overlap with other studies, making it difficult to discern common patterns or unify datasets for further analysis. To that end, we develop a computational framework that predicts how an antibody or serum would inhibit any variant from any other study. We use this framework to greatly expand seven influenza datasets utilizing hemagglutination inhibition, validating our method upon 200,000 existing measurements and predicting 2,000,000 new values uncertainties. With these new values, we quantify the transferability between seven vaccination and infection studies in humans and ferrets, show that the serum potency is negatively correlated with breadth, and present a tool for pandemic preparedness. This data-driven approach does not require any information beyond each virus's name and measurements, and even datasets with as few as 5 viruses can be expanded, making this approach widely applicable. Future influenza studies using hemagglutination inhibition can directly utilize our curated datasets to predict newly measured antibody responses against 80 H3N2 influenza viruses from 1968-2011, whereas immunological studies utilizing other viruses or a different assay only need a single partially-overlapping dataset to extend their work. In essence, this approach enables a shift in perspective when analyzing data from "what you see is what you get" into "what anyone sees is what everyone gets." Introduction Our understanding of how antibody-mediated immunity drives viral evolution and escape relies upon painstaking measurements of antibody binding, inhibition, or neutralization against variants of concern (Petrova and Russell, 2017). Every interaction is unique because: (1) the antibody response (serum) changes even in the absence of viral exposure and (2) for rapidly evolving viruses such as influenza, the specific variants examined in one study will often have little-to-no overlap with other studies (Figure 1).

Several decision points exist in business processes (e.g., whether a purchase order needs a manager's approval or not), and different decisions are made for different process instances based on their characteristics (e.g., a purchase order higher than e500 needs a manager approval). Decision mining in process mining aims to describe/predict the routing of a process instance at a decision point of the process. By predicting the decision, one can take proactive actions to improve the process. For instance, when a bottleneck is developing in one of the possible decisions, one can predict the decision and bypass the bottleneck. However, despite its huge potential for such operational support, existing techniques for decision mining have focused largely on describing decisions but not on predicting them, deploying decision trees to produce logical expressions to explain the decision. In this work, we aim to enhance the predictive capability of decision mining to enable proactive operational support by deploying more advanced machine learning algorithms. Our proposed approach provides explanations of the predicted decisions using SHAP values to support the elicitation of proactive actions. We have implemented a Web application to support the proposed approach and evaluated the approach using the implementation.

Machine Learning (ML) has gained prominence in recent years because of its ability to be applied across scores of industries and solve complex problems effectively. Yet, research shows that nearly 90% of AI/ML models never actually make it into production or hit the market. The main challenge is that ML/AI models require huge volumes of high-quality, accurate, and timely data to be effective, but organizations have long been reluctant to share sensitive information due to security and privacy concerns. Personal data is becoming more pervasive, causing privacy concerns to grow. As a result, global data protection laws have become stricter, and organizations face increasingly higher noncompliance risks. Mitigating such concerns and taking AI/ML to the next level requires a new approach to collaboration -- secure collaborative learning.

Cardiovascular activities are directly related to the response of a body in a stressed condition. Stress, based on its intensity, can be divided into two types i.e. Acute stress (short-term stress) and Chronic stress (long-term stress). Repeated acute stress and continuous chronic stress may play a vital role in inflammation in the circulatory system and thus leads to a heart attack or to a stroke. In this study, we have reviewed commonly used machine learning classification techniques applied to different stress-indicating parameters used in stress monitoring devices. These parameters include Photoplethysmograph (PPG), Electrocardiographs (ECG), Electromyograph (EMG), Galvanic Skin Response (GSR), Heart Rate Variation (HRV), skin temperature, respiratory rate, Electroencephalograph (EEG) and salivary cortisol, used in stress monitoring devices. This study also provides a discussion on choosing a classifier, which depends upon a number of factors other than accuracy, like the number of subjects involved in an experiment, type of signals processing and computational limitations.

While startup valuations are influenced by revenues, risks, age, and macroeconomic conditions, specific causality is traditionally a black box. Because valuations are not disclosed, roles played by other factors (industry, geography, and intellectual property) can often only be guessed at. VC valuation research indicates the importance of establishing a factor-hierarchy to better understand startup valuations and their dynamics, suggesting the wisdom of hiring data-scientists for this purpose. Bespoke understanding can be established via construction of hierarchical prediction models based on decision trees and random forests. These have the advantage of understanding which factors matter most. In combination with OLS, the also tell us the circumstances of when specific causalities apply. This study explores the deterministic role of categorical variables on the valuation of start-ups (i.e. the joint-combination geographic, urban, and sectoral denomination-variables), in order to be able to build a generalized valuation scorecard approach. Using a dataset of 1,091 venture-capital investments, containing 1,044 unique EU and EEA, this study examines microeconomic, sectoral, and local-level impacts on startup valuation. In principle, the study relies on Fixedeffects and Joint-fixed-effects regressions as well as the analysis and exploration of divergent micropopulations and fault-lines by means of non-parametric approaches combining econometric and machinelearning techniques.