Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid game-theoretic principles, Shapley values uniquely satisfy several desirable properties, which is why they are increasingly used to explain the predictions of possibly complex and highly non-linear machine learning models. Shapley values are well calibrated to a user's intuition when features are independent, but may lead to undesirable, counterintuitive explanations when the independence assumption is violated. In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. By employing Pearl's do-calculus, we show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties. Moreover, causal Shapley values enable us to separate the contribution of direct and indirect effects. We provide a practical implementation for computing causal Shapley values based on causal chain graphs when only partial information is available and illustrate their utility on a real-world example.

Given a classification problem, which performance metric should the classifier optimize? This question is often faced by practitioners while developing machine learning solutions. For example, consider cancer diagnosis where the doctor applies a cost-sensitive predictive model to classify patients into cancer categories [53, 56]. Although it is clear that the chosen costs directly determine the model decisions and thus patient outcomes, it is not clear how to quantify expert intuition into precise quantitative cost tradeoffs, i.e. the performance metric. Indeed this is also true for a variety of other domains where picking the right metric is a critical challenge [8]. Hiranandani et al. [16, 17] addressed this issue by formalizing the problem of Metric Elicitation (ME), where the goal is to estimate a performance metric using preference feedback from a user. The motivation is that by employing metrics that reflect a user's innate tradeoffs, one can learn models that best capture the user preferences [16].

What is a fair performance metric? We consider the choice of fairness metrics through the lens of metric elicitation -- a principled framework for selecting performance metrics that best reflect implicit preferences. The use of metric elicitation enables a practitioner to tune the performance and fairness metrics to the task, context, and population at hand. Specifically, we propose a novel strategy to elicit group-fair performance metrics for multiclass classification problems with multiple sensitive groups that also includes selecting the trade-off between predictive performance and fairness violation. The proposed elicitation strategy requires only relative preference feedback and is robust to both finite sample and feedback noise.

Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. The popularity of graph neural networks has sparked interest, both in academia and in industry, in developing methods that scale to very large graphs such as Facebook or Twitter social networks. In most of these approaches, the computational cost is alleviated by a sampling strategy retaining a subset of node neighbors or subgraphs at training time. In this paper we propose a new, efficient and scalable graph deep learning architecture which sidesteps the need for graph sampling by using graph convolutional filters of different size that are amenable to efficient precomputation, allowing extremely fast training and inference. Our architecture allows using different local graph operators (e.g. motif-induced adjacency matrices or Personalized Page Rank diffusion matrix) to best suit the task at hand. We conduct extensive experimental evaluation on various open benchmarks and show that our approach is competitive with other state-of-the-art architectures, while requiring a fraction of the training and inference time. Moreover, we obtain state-of-the-art results on ogbn-papers100M, the largest public graph dataset, with over 110 million nodes and 1.5 billion edges.

Many real-world planning domains involve diverse information sources, external entities, and variable-reliability agents, all of which may impact the confidence, risk, and sensitivity of plans. Humans reviewing a plan may lack context about these factors; however, this information is available during the domain generation, which means it can also be interwoven into the planner and its resulting plans. This paper presents a provenance-based approach to explaining automated plans. Our approach (1) extends the SHOP3 HTN planner to generate dependency information, (2) transforms the dependency information into an established PROV-O representation, and (3) uses graph propagation and TMS-inspired algorithms to support dynamic and counter-factual assessment of information flow, confidence, and support. We qualified our approach's explanatory scope with respect to explanation targets from the automated planning literature and the information analysis literature, and we demonstrate its ability to assess a plan's pertinence, sensitivity, risk, assumption support, diversity, and relative confidence.

Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less.

The TRAIF Preview 2020 is a sneak peek into how the IEAI and its partners are promoting a sustainable, inclusive and comprehensiveframework for the use of AI that delivers global benefit. Presenting a first taste of what's to come in The Responsible AI Forum (TRAIF) from 7-9 June 2021, in our virtual TRAIF Preview on 12 and 13 November 2020, we will share with you the IEAI’s current research on AI ethics as well as expert panels on responsible use of AI in managing pandemics and the opportunities and challenges of AI in Africa. These sessions will be held in close cooperation with the Global AI Ethics Consortium and the Responsible AI Network-Africa. The year 2020, not least through the COVID-19 pandemic, has proven that responsible, transparent and accountable use of AI is already an inevitable necessity to solve critical issues around the world. International collaboration will be just as vital as technical and interdisciplinary expertise. The TRAIF Preview will provide a glimpse into how the IEAI is playing its part through research, by connecting experts around the globe and, of course, through hosting TRAIF 2021.

The market research report on the Global Deep Learning Market has been formulated through a series of extensive primary and secondary research approaches. The data is further verified and validated by industry experts and professionals. The forecast for 2020-2027 has been covered in the report and offers an extensive historical analysis for the key segments of the Deep Learning market. The well-formulated research report aims to provide the readers with a better understanding of the industry and help them formulate strategic investment plans. The report also evaluates the market dynamics, including drivers, restraints, opportunities, threats, challenges, and other key segments.

The Reputed Garner Insights website offers vast reports on different market.They cover all industry and these reports are very precise and reliable. It also offers Machine Learning as a Service (MLaaS) Market Report 2020 in its research report store. It is the most comprehensive report available on this market. The report study provides information on market trends and development, drivers, capacities, technologies, and on the changing investment structure of the Global Machine Learning as a Service (MLaaS) Market. The study gives a transparent view on the Global Machine Learning as a Service (MLaaS) Market and includes a thorough competitive scenario and portfolio of the key players functioning in it.

ResearchMoz is the one stop online destination to find and buy market research reports & Industry Analysis. We fulfil all your research needs spanning across industry verticals with our huge collection of market research reports. We provide our services to all sizes of organisations and across all industry verticals and markets. Our Research Coordinators have in-depth knowledge of reports as well as publishers and will assist you in making an informed decision by giving you unbiased and deep insights on which reports will satisfy your needs at the best price.