This paper formulates hypothesis verification as an RL problem. Specifically, we aim to build an agent that, given a hypothesis about the dynamics of the world, can take actions to generate observations which can help predict whether the hypothesis is true or false. Existing RL algorithms fail to solve this task, even for simple environments. In order to train the agents, we exploit the underlying structure of many hypotheses, factorizing them as {pre-condition, action sequence, post-condition} triplets. By leveraging this structure we show that RL agents are able to succeed at the task. Furthermore, subsequent fine-tuning of the policies allows the agent to correctly verify hypotheses not amenable to the above factorization.

Research in interpretable machine learning proposes different computational and human subject approaches to evaluate model saliency explanations. These approaches measure different qualities of explanations to achieve diverse goals in designing interpretable machine learning systems. In this paper, we propose a human attention benchmark for image and text domains using multi-layer human attention masks aggregated from multiple human annotators. We then present an evaluation study to evaluate model saliency explanations obtained using Grad-cam and LIME techniques. We demonstrate our benchmark's utility for quantitative evaluation of model explanations by comparing it with human subjective ratings and ground-truth single-layer segmentation masks evaluations. Our study results show that our threshold agnostic evaluation method with the human attention baseline is more effective than single-layer object segmentation masks to ground truth. Our experiments also reveal user biases in the subjective rating of model saliency explanations.

We study the open-domain named entity recognition (NER) problem under distant supervision. The distant supervision, though does not require large amounts of manual annotations, yields highly incomplete and noisy distant labels via external knowledge bases. To address this challenge, we propose a new computational framework -- BOND, which leverages the power of pre-trained language models (e.g., BERT and RoBERTa) to improve the prediction performance of NER models. Specifically, we propose a two-stage training algorithm: In the first stage, we adapt the pre-trained language model to the NER tasks using the distant labels, which can significantly improve the recall and precision; In the second stage, we drop the distant labels, and propose a self-training approach to further improve the model performance. Thorough experiments on 5 benchmark datasets demonstrate the superiority of BOND over existing distantly supervised NER methods. The code and distantly labeled data have been released in https://github.com/cliang1453/BOND.

Telepresence robots are used in various forms in various use-cases that helps to avoid physical human presence at the scene of action. In this work, we focus on a telepresence robot that can be used to attend a meeting remotely with a group of people. Unlike a one-to-one meeting, participants in a group meeting can be located at a different part of the room, especially in an informal setup. As a result, all of them may not be at the viewing angle of the robot, a.k.a. the remote participant. In such a case, to provide a better meeting experience, the robot should localize the speaker and bring the speaker at the center of the viewing angle. Though sound source localization can easily be done using a microphone-array, bringing the speaker or set of speakers at the viewing angle is not a trivial task. First of all, the robot should react only to a human voice, but not to the random noises. Secondly, if there are multiple speakers, to whom the robot should face or should it rotate continuously with every new speaker? Lastly, most robotic platforms are resource-constrained and to achieve a real-time response, i.e., avoiding network delay, all the algorithms should be implemented within the robot itself. This article presents a study and implementation of an attention shifting scheme in a telepresence meeting scenario which best suits the needs and expectations of the collocated and remote attendees. We define a policy to decide when a robot should rotate and how much based on real-time speaker localization. Using user satisfaction study, we show the efficacy and usability of our system in the meeting scenario. Moreover, our system can be easily adapted to other scenarios where multiple people are located.

This paper is motivated by applications of a Census Bureau interested in releasing aggregate socioeconomic data about a large population without revealing sensitive information about any individual. The released information can be the number of individuals living alone, the number of cars they own, or their salary brackets. Recent events have identified some of the privacy challenges faced by these organizations [5]. To address them, this paper presents a novel differential-privacy mechanism for releasing hierarchical counts of individuals. The counts are reported at multiple granularities (e.g., the national, state, and county levels) and must be consistent across all levels. The core of the mechanism is an optimization model that redistributes the noise introduced to achieve differential privacy in order to meet the consistency constraints between the hierarchical levels. The key technical contribution of the paper shows that this optimization problem can be solved in polynomial time by exploiting the structure of its cost functions. Experimental results on very large, real datasets show that the proposed mechanism provides improvements of up to two orders of magnitude in terms of computational efficiency and accuracy with respect to other state-of-the-art techniques.

The broad deployment of 802.11 (a.k.a., WiFi) access points and significant enhancement of the energy efficiency of these wireless transceivers has resulted in increasing interest in building 802.11-based IoT systems. Unfortunately, the main energy efficiency mechanisms of 802.11, namely PSM and APSD, fall short when used in IoT applications. PSM increases latency and intensifies channel access contention after each beacon instance, and APSD does not inform stations about when they need to wake up to receive their downlink packets. In this paper, we present a new mechanism---edge-assisted predictive sleep scheduling (EAPS)---to adjust the sleep duration of stations while they expect downlink packets. We first implement a Linux-based access point that enables us to collect parameters affecting communication latency. Using this access point, we build a testbed that, in addition to offering traffic pattern customization, replicates the characteristics of real-world environments. We then use multiple machine learning algorithms to predict downlink packet delivery. Our empirical evaluations confirm that when using EAPS the energy consumption of IoT stations is as low as PSM, whereas the delay of packet delivery is close to the case where the station is always awake.

In this paper, we introduce VPNet, a novel model-driven neural network architecture based on variable projections (VP). The application of VP operators in neural networks implies learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet as well as experiments. The concept was evaluated in the context of signal processing. We performed classification tasks on a synthetic dataset, and real electrocardiogram (ECG) signals. Compared to fully-connected and 1D convolutional networks, VPNet features fast learning ability and good accuracy at a low computational cost in both of the training and inference. Based on the promising results and mentioned advantages, we expect broader impact in signal processing, including classification, regression, and even clustering problems.

The space of synthesizable molecules is greater than $10^{60}$, meaning only a vanishingly small fraction of these molecules have ever been realized in the lab. In order to prioritize which regions of this space to explore next, synthetic chemists need access to accurate molecular property predictions. While great advances in molecular machine learning have been made, there is a dearth of benchmarks featuring properties that are useful for the synthetic chemist. Focussing directly on the needs of the synthetic chemist, we introduce the Photoswitch Dataset, a new benchmark for molecular machine learning where improvements in model performance can be immediately observed in the throughput of promising molecules synthesized in the lab. Photoswitches are a versatile class of molecule for medical and renewable energy applications where a molecule's efficacy is governed by its electronic transition wavelengths. We demonstrate superior performance in predicting these wavelengths compared to both time-dependent density functional theory (TD-DFT), the incumbent first principles quantum mechanical approach, as well as a panel of human experts. Our baseline models are currently being deployed in the lab as part of the decision process for candidate synthesis. It is our hope that this benchmark can drive real discoveries in photoswitch chemistry and that future benchmarks can be introduced to pivot learning algorithm development to benefit more expansive areas of synthetic chemistry.

Implicit feedback data is extensively explored in recommendation as it is easy to collect and generally applicable. However, predicting users' preference on implicit feedback data is a challenging task since we can only observe positive (voted) samples and unvoted samples. It is difficult to distinguish between the negative samples and unlabeled positive samples from the unvoted ones. Existing works, such as Bayesian Personalized Ranking (BPR), sample unvoted items as negative samples uniformly, therefore suffer from a critical noisy-label issue. To address this gap, we design an adaptive sampler based on noisy-label robust learning for implicit feedback data. To formulate the issue, we first introduce Bayesian Point-wise Optimization (BPO) to learn a model, e.g., Matrix Factorization (MF), by maximum likelihood estimation. We predict users' preferences with the model and learn it by maximizing likelihood of observed data labels, i.e., a user prefers her positive samples and has no interests in her unvoted samples. However, in reality, a user may have interests in some of her unvoted samples, which are indeed positive samples mislabeled as negative ones. We then consider the risk of these noisy labels, and propose a Noisy-label Robust BPO (NBPO). NBPO also maximizes the observation likelihood while connects users' preference and observed labels by the likelihood of label flipping based on the Bayes' theorem. In NBPO, a user prefers her true positive samples and shows no interests in her true negative samples, hence the optimization quality is dramatically improved. Extensive experiments on two public real-world datasets show the significant improvement of our proposed optimization methods.

Low rank tensor ring model is powerful for image completion which recovers missing entries in data acquisition and transformation. The recently proposed tensor ring (TR) based completion algorithms generally solve the low rank optimization problem by alternating least squares method with predefined ranks, which may easily lead to overfitting when the unknown ranks are set too large and only a few measurements are available. In this paper, we present a Bayesian low rank tensor ring model for image completion by automatically learning the low rank structure of data. A multiplicative interaction model is developed for the low-rank tensor ring decomposition, where core factors are enforced to be sparse by assuming their entries obey Student-T distribution. Compared with most of the existing methods, the proposed one is free of parameter-tuning, and the TR ranks can be obtained by Bayesian inference. Numerical Experiments, including synthetic data, color images with different sizes and YaleFace dataset B with respect to one pose, show that the proposed approach outperforms state-of-the-art ones, especially in terms of recovery accuracy.