In this paper, we present a method aimed at integrating domain knowledge abstracted as logic rules into the predictive behaviour of a neural network using feature extracting functions for visual sentiment analysis. We combine the declarative first-order logic rules which represent the human knowledge in a logically-structured format making use of feature-extracting functions. These functions are embodied as programming functions which can represent, in a straightforward manner, the applicable domain knowledge as a set of logical instructions and provide a cumulative set of probability distributions of the input data. These distributions can then be used during the training process in a mini-batch strategy. In contrast with other neural logic approaches, the programmatic nature in practice of these functions do not require any kind of special mathematical encoding, which makes our method very general in nature. We also illustrate the utility of our method for sentiment analysis and compare our results to those obtained using a number of alternatives elsewhere in the literature.

Decision-making module enables autonomous vehicles to reach appropriate maneuvers in the complex urban environments, especially the intersection situations. This work proposes a deep reinforcement learning (DRL) based left-turn decision-making framework at unsignalized intersection for autonomous vehicles. The objective of the studied automated vehicle is to make an efficient and safe left-turn maneuver at a four-way unsignalized intersection. The exploited DRL methods include deep Q-learning (DQL) and double DQL. Simulation results indicate that the presented decision-making strategy could efficaciously reduce the collision rate and improve transport efficiency. This work also reveals that the constructed left-turn control structure has a great potential to be applied in real-time.

Open Government Data (OGD) is being published by various public administration organizations around the globe. Within the metadata of OGD data catalogs, the publishing organizations (1) are not uniquely and unambiguously identifiable and, even worse, (2) change over time, by public administration units being merged or restructured. In order to enable fine-grained analyses or searches on Open Government Data on the level of publishing organizations, linking those from OGD portals to publicly available knowledge graphs (KGs) such as Wikidata and DBpedia seems like an obvious solution. Still, as we show in this position paper, organization linking faces significant challenges, both in terms of available (portal) metadata and KGs in terms of data quality and completeness. We herein specifically highlight five main challenges, namely regarding (1) temporal changes in organizations and in the portal metadata, (2) lack of a base ontology for describing organizational structures and changes in public knowledge graphs, (3) metadata and KG data quality, (4) multilinguality, and (5) disambiguating public sector organizations. Based on available OGD portal metadata from the Open Data Portal Watch, we provide an in-depth analysis of these issues, make suggestions for concrete starting points on how to tackle them along with a call to the community to jointly work on these open challenges.

Recently, deep reinforcement learning algorithms have been successfully applied to a wide range of domains ([1], [2], [3], [4]). However, their success relies heavily on dense rewards being given to the agent; and learning in environments with sparse rewards is still a major limitation of RL due to the low sample efficiency of the current algorithms in such scenarios. In sparse rewards settings, the sample inefficiency is essentially caused by the low likelihood of the agent obtaining a reward by random exploration. Recent attempts to tackle this issue revolve around providing the agent an intrinsic reward that encourages exploring new states of the environment, thus increasing the likelihood of reaching the reward ([5], [6], [7]). An alternative way to improve the sample efficiency is curriculum learning ([8]). It consists in first training the agent on an easy version of the task at hand, where it can get reward more easily and learn, then training on increasingly difficult versions using the previously learned policy and finally, training on the task at hand. Its usage is not limited to reinforcement learning and robotics tasks, but also to supervised tasks. Curriculum learning may be decomposed into two parts: 1. Defining the curriculum, i.e. the set of tasks the learner may be trained on.

Identifying optimal values for a high-dimensional set of hyperparameters is a problem that has received growing attention given its importance to large-scale machine learning applications such as neural architecture search. Recently developed optimization methods can be used to select thousands or even millions of hyperparameters. Such methods often yield overfit models, however, leading to poor performance on unseen data. We argue that this overfitting results from using the standard hyperparameter optimization objective function. Here we present an alternative objective that is equivalent to a Probably Approximately Correct-Bayes (PAC-Bayes) bound on the expected out-of-sample error. We then devise an efficient gradient-based algorithm to minimize this objective; the proposed method has asymptotic space and time complexity equal to or better than other gradient-based hyperparameter optimization methods. We show that this new method significantly reduces out-of-sample error when applied to hyperparameter optimization problems known to be prone to overfitting.

We propose an efficient algorithm for solving group synchronization under high levels of corruption and noise, while we focus on rotation synchronization. We first describe our recent theoretically guaranteed message passing algorithm that estimates the corruption levels of the measured group ratios. We then propose a novel reweighted least squares method to estimate the group elements, where the weights are initialized and iteratively updated using the estimated corruption levels. We demonstrate the superior performance of our algorithm over state-of-the-art methods for rotation synchronization using both synthetic and real data.

We propose a reward function estimation framework for inverse reinforcement learning with deep energy-based policies. We name our method PQR, as it sequentially estimates the Policy, the $Q$-function, and the Reward function by deep learning. PQR does not assume that the reward solely depends on the state, instead it allows for a dependency on the choice of action. Moreover, PQR allows for stochastic state transitions. To accomplish this, we assume the existence of one anchor action whose reward is known, typically the action of doing nothing, yielding no reward. We present both estimators and algorithms for the PQR method. When the environment transition is known, we prove that the PQR reward estimator uniquely recovers the true reward. With unknown transitions, we bound the estimation error of PQR. Finally, the performance of PQR is demonstrated by synthetic and real-world datasets.

Clustering is essential for exploratory data mining, data structure analysis and a common technique for statistical data analysis. It is widely used in many fields, including machine learning, pattern recognition, image analysis, information retrieval, bioinformatics, data compression, and computer graphics. Many clustering approaches exist with different intrinsic notions of what a cluster is. In the standard setup, the goal is to group objects into subsets, known as clusters, such that objects within a given cluster are more related to one another than the ones from a different cluster. Clustering is already quite well-known (see [4, 27] and references therein) conversely to Extreme Value Theory (EVT) which is a newer field in the machine learning community that has been used in anomaly detection [14, 28, 45, 51], classification [31, 32, 54] or clustering [10, 12, 13, 33] when dedicated to the most extreme regions of the sample space.

Due to confidentiality issues, it can be difficult to access or share interesting datasets for methodological development in actuarial science, or other fields where personal data are important. We show how to design three different types of generative adversarial networks (GANs) that can build a synthetic insurance dataset from a confidential original dataset. The goal is to obtain synthetic data that no longer contains sensitive information but still has the same structure as the original dataset and retains the multivariate relationships. In order to adequately model the specific characteristics of insurance data, we use GAN architectures adapted for multi-categorical data: a Wassertein GAN with gradient penalty (MC-WGAN-GP), a conditional tabular GAN (CTGAN) and a Mixed Numerical and Categorical Differentially Private GAN (MNCDP-GAN). For transparency, the approaches are illustrated using a public dataset, the French motor third party liability data. We compare the three different GANs on various aspects: ability to reproduce the original data structure and predictive models, privacy, and ease of use. We find that the MC-WGAN-GP synthesizes the best data, the CTGAN is the easiest to use, and the MNCDP-GAN guarantees differential privacy.

Although precision and recall are standard performance measures for anomaly detection, their statistical properties in sequential detection settings are poorly understood. In this work, we formalize a notion of precision and recall with temporal tolerance for point-based anomaly detection in sequential data. These measures are based on time-tolerant confusion matrices that may be used to compute time-tolerant variants of many other standard measures. However, care has to be taken to preserve interpretability. We perform a statistical simulation study to demonstrate that precision and recall may overestimate the performance of a detector, when computed with temporal tolerance. To alleviate this problem, we show how to obtain null distributions for the two measures to assess the statistical significance of reported results.