We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to satisfy non-linear rate constraints such as predictive parity fairness, distribution divergences or churn ratios. We extend previous two-player game approaches for constrained optimization to a game between three players to decouple the classifier rates from the non-linear objective, and seek to find an equilibrium of the game. Our approach generalizes many existing algorithms, and makes possible new algorithms with more flexibility and tighter handling of non-linear rate constraints. We provide convergence guarantees for convex functions of rates, and show how our methodology can be extended to handle sums of ratios of rates. Experiments on different fairness tasks confirm the efficacy of our approach.

We present a pairwise learning to rank approach based on a neural net, called DirectRanker, that generalizes the RankNet architecture. We show mathematically that our model is reflexive, antisymmetric, and transitive allowing for simplified training and improved performance. Experimental results on the LETOR MSLR-WEB10K, MQ2007 and MQ2008 datasets show that our model outperforms numerous state-of-the-art methods, while being inherently simpler in structure and using a pairwise approach only. Keywords: Information Retrieval · Machine learning · Learning to rank.

Voting has served as a fundamental tool for aggregating preferences of a set of people over a set of alternatives from centuries. A typical voting system consists of a set of alternatives, a set of voters each having a linear order over the set of alternatives as her preference, and a voting rule which selects a set of alternatives as winners depending on the voters' preferences. However, classical results show that every reasonable voting system with at least 3 alternatives can suffer from manipulation [Gib73, Sat75] -- an agent may be able to make her more favored alternative win by misreporting her preference. Bartholdi et al. pioneered the idea of using computational intractability as a barrier to safe guard elections against manipulation [BTT89, BO91]. Indeed, if we have m alternatives and even if the manipulator exactly knows the preferences of all other voters, na ıvely going over all ( m! 1) possible preferences and report the one which results in best outcome for the manipulator is not feasible for any computationally bounded manipulator . Although the idea of Bartholdi et al. was to use computational intractability as a barrier against manipulation, the computational problem of manipulation turns out to be polynomial time solvable for most of the commonly used voting rules such as the scoring rules, maximin, Copeland, etc. with prominent exception being the single transferable (STV) voting rule. Even for voting rules (STV for example) for which the computational barrier exists against manipulation, it seems that the barrier, in reality, may be substantially weak due to existence of heuristics which work well in practice [FP10, FKKN11, MR15, and references there in]. Motivation: The computational problem of manipulation has mostly been studied in what is called the complete information setting -- the manipulator exactly knows the preferences of all other voters.

Data science and artificial intelligence are driven by a plethora of diverse data-related assets including datasets, data streams, algorithms, processing software, compute resources, and domain knowledge. As providing all these assets requires a huge investment, data sciences and artificial intelligence are currently dominated by a small number of providers who can afford these investments. In this paper, we present a vision of a data ecosystem to democratize data science and artificial intelligence. In particular, we envision a data infrastructure for fine-grained asset exchange in combination with scalable systems operation. This will overcome lock-in effects and remove entry barriers for new asset providers. Our goal is to enable companies, research organizations, and individuals to have equal access to data, data science, and artificial intelligence. Such an open ecosystem has recently been put on the agenda of several governments and industrial associations. We point out the requirements and the research challenges as well as outline an initial data infrastructure architecture for building such a data ecosystem.

Partitioning a graph using graph separators, and particularly clique separators, are well-known techniques to decompose a graph into smaller units which can be treated independently. It was previously known that the treewidth was bounded above by the sum of the size of the separator plus the treewidth of disjoint components, and this was obtained by the heuristic of filling in all edges of the separator making it into a clique. In this paper, we present a new, tighter upper bound on the treewidth of a graph obtained by only partially filling in the edges of a separator. In particular, the method completes just those pairs of separator vertices that are adjacent to a common component, and indicates a more effective heuristic than filling in the entire separator. We discuss the relevance of this result for combinatorial algorithms and give an example of how the tighter bound can be exploited in the domain of constraint satisfaction problems.

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation function from a family of solutions to an ordinary differential equation. Specifically, each neuron may change its functional form during training based on the behavior of the other parts of the network. We show that using neurons with DEU activation functions results in a more compact network capable of achieving comparable, if not superior, performance when is compared to much larger networks.

Machine learning models deployed in real-world applications are often evaluated with precision-based metrics such as F1-score or AUC-PR (Area Under the Curve of Precision Recall). Heavily dependent on the class prior, such metrics may sometimes lead to wrong conclusions about the performance. For example, when dealing with non-stationary data streams, they do not allow the user to discern the reasons why a model performance varies across different periods. In this paper, we propose a way to calibrate the metrics so that they are no longer tied to the class prior. It corresponds to a readjustment, based on probabilities, to the value that the metric would have if the class prior was equal to a reference prior (user parameter). We conduct a large number of experiments on balanced and imbalanced data to assess the behavior of calibrated metrics and show that they improve interpretability and provide a better control over what is really measured. We describe specific real-world use-cases where calibration is beneficial such as, for instance, model monitoring in production, reporting, or fairness evaluation.

We describe a detailed analysis of a sample of large benchmark of commonsense reasoning problems that has been automatically obtained from WordNet, SUMO and their mapping. The objective is to provide a better assessment of the quality of both the benchmark and the involved knowledge resources for advanced commonsense reasoning tasks. By means of this analysis, we are able to detect some knowledge misalignments, mapping errors and lack of knowledge and resources. Our final objective is the extraction of some guidelines towards a better exploitation of this commonsense knowledge framework by the improvement of the included resources.

Companies increasingly expose machine learning (ML) models trained over sensitive user data to untrusted domains, such as end-user devices and wide-access model stores. We present Sage, a differentially private (DP) ML platform that bounds the cumulative leakage of training data through models. Sage builds upon the rich literature on DP ML algorithms and contributes pragmatic solutions to two of the most pressing systems challenges of global DP: running out of privacy budget and the privacy-utility tradeoff. To address the former, we develop block composition, a new privacy loss accounting method that leverages the growing database regime of ML workloads to keep training models endlessly on a sensitive data stream while enforcing a global DP guarantee for the stream. To address the latter, we develop privacy-adaptive training, a process that trains a model on growing amounts of data and/or with increasing privacy parameters until, with high probability, the model meets developer-configured quality criteria. They illustrate how a systems focus on characteristics of ML workloads enables pragmatic solutions that are not apparent when one focuses on individual algorithms, as most DP ML literature does.

There is a small number of case studies of automatic land cover classification on the coastal area. Here, I test extraction of seagrass beds, sandy area, oyster farming rafts at Mangoku-ura Lagoon, Miyagi, Japan by comparing manual tracing, simple image segmentation, and image transformation using deep learning. The result was used to extract the changes before and after the earthquake and tsunami. The output resolution was best in the image transformation method, which showed more than 69% accuracy for vegetation classification by an assessment using random points on independent test data. The distribution of oyster farming rafts was detected by the segmentation model. Assessment of the change before and after the earthquake by the manual tracing and image transformation result revealed increase of sand area and decrease of the vegetation. By the segmentation model only the decrease of the oyster farming was detected. These results demonstrate the potential to extract the spatial pattern of these elements after an earthquake and tsunami. Index Terms: Great East Japan Earthquake of 2011, Land use land cover (LULC), Zosteracea seagrass, cultured oyster, deep learning, Mangoku Bay