Deep neural networks are in the limelight of machine learning with their excellent performance in many data-driven applications. However, they can lead to inaccurate predictions when queried in out-of-distribution data points, which can have detrimental effects especially in sensitive domains, such as healthcare and transportation, where erroneous predictions can be very costly and/or dangerous. Subsequently, quantifying the uncertainty of the output of a neural network is often leveraged to evaluate the confidence of its predictions, and ensemble models have proved to be effective in measuring the uncertainty by utilizing the variance of predictions over a pool of models. In this paper, we propose a novel approach for uncertainty quantification via ensembles, called Random Activation Functions (RAFs) Ensemble, that aims at improving the ensemble diversity toward a more robust estimation, by accommodating each neural network with a different (random) activation function. Extensive empirical study demonstrates that RAFs Ensemble outperforms state-of-the-art ensemble uncertainty quantification methods on both synthetic and real-world datasets in a series of regression tasks.

Ensemble models are widely used as an effective technique in time-series forecasting, and recently, are inclined toward leveraging meta-learning methods due to their proven predictive advantages in combining individual models in an ensemble. However, finding the optimal strategy for ensemble aggregation is an open research question, particularly, when the ensemble needs to be adapted in real-time. In this paper, we pro-pose a novel meta-learning approach for aggregation of linearly weighted ensembles for the task of time-series forecasting. We outline a deep reinforcement learning framework with a coherent design of the components of the environment and the objective function as an aggregation method in our task. In this framework, the combination policy in ensembles is modeled as a sequential decision making process which is able to capture the temporal behavior in time-series, and an actor-critic model aims at learning the optimal weights in a continuous action space. An extensive empirical study on various real-world datasets demonstrates that our method achieves excellent or on par results in comparison to the state-of-the-art approaches as well as several baselines.

The emergence of structured databases for Question Answering (QA) systems has led to developing methods, in which the problem of learning the correct answer efficiently is based on a linking task between the constituents of the question and the corresponding entries in the database. As a result, parsing the questions in order to determine their main elements, which are required for answer retrieval, becomes crucial. However, most datasets for QA systems lack gold annotations for parsing, i.e., labels are only available in the form of (question, formal-query, answer). In this paper, we propose a distantly supervised learning framework based on reinforcement learning to learn the mentions of entities and relations in questions. We leverage the provided formal queries to characterize delayed rewards for optimizing a policy gradient objective for the parsing model. An empirical evaluation of our approach shows a significant improvement in the performance of entity and relation linking compared to the state of the art. We also demonstrate that a more accurate parsing component enhances the overall performance of QA systems.

Recent advances in machine learning have led to emerging new approaches to deal with different kinds of biases that exist in the data. On the one hand, counterfactual learning copes with biases in the policy used for sampling (or logging) the data in order to evaluate and learn new policies. On the other hand, fairness-aware learning aims at learning fair models to avoid discrimination against certain individuals or groups. In this paper, we design a counterfactual framework to model fairness-aware learning which benefits from counterfactual reasoning to achieve more fair decision support systems. We utilize a definition of fairness to determine the bandit feedback in the counterfactual setting that learns a classification strategy from the offline data, and balances classification performance versus fairness measure. In the experiments, we demonstrate that a counterfactual setting can be perfectly exerted to learn fair models with competitive results compared to a well-known baseline system.

Recommender systems aim to capture interests of users to provide tailored recommendations. User interests are however often unique and depend on many unobservable factors including a user's mood and the local weather. We take a contextual session-based approach and propose a sequential framework using factored Markov decision processes (fMDPs) to detect the user's goal (the topic) of a session. We show that an independence assumption on the attributes of items leads to a set of independent models that can be optimised efficiently. Our approach results in interpretable topics that can be effectively turned into recommendations. Empirical results on a real world click log from a large e-commerce company exhibit highly accurate topic prediction rates of about 90%. Translating our approach into a topic-driven recommender system outperforms several baseline competitors.