We propose a Distributional Approach to address Controlled Text Generation from pre-trained Language Models (LMs). This view permits to define, in a single formal framework, "pointwise" and "distributional" constraints over the target LM -- to our knowledge, this is the first approach with such generality -- while minimizing KL divergence with the initial LM distribution. The optimal target distribution is then uniquely determined as an explicit EBM (Energy-Based Model) representation. From that optimal representation we then train the target controlled autoregressive LM through an adaptive distributional variant of Policy Gradient. We conduct a first set of experiments over pointwise constraints showing the advantages of our approach over a set of baselines, in terms of obtaining a controlled LM balancing constraint satisfaction with divergence from the initial LM (GPT-2). We then perform experiments over distributional constraints, a unique feature of our approach, demonstrating its potential as a remedy to the problem of Bias in Language Models. Through an ablation study we show the effectiveness of our adaptive technique for obtaining faster convergence.

Health misinformation on social media devastates physical and mental health, invalidates health gains, and potentially costs lives. Understanding how health misinformation is transmitted is an urgent goal for researchers, social media platforms, health sectors, and policymakers to mitigate those ramifications. Deep learning methods have been deployed to predict the spread of misinformation. While achieving the state-of-the-art predictive performance, deep learning methods lack the interpretability due to their blackbox nature. To remedy this gap, this study proposes a novel interpretable deep learning approach, Generative Adversarial Network based Piecewise Wide and Attention Deep Learning (GAN-PiWAD), to predict health misinformation transmission in social media. Improving upon state-of-the-art interpretable methods, GAN-PiWAD captures the interactions among multi-modal data, offers unbiased estimation of the total effect of each feature, and models the dynamic total effect of each feature when its value varies. We select features according to social exchange theory and evaluate GAN-PiWAD on 4,445 misinformation videos. The proposed approach outperformed strong benchmarks. Interpretation of GAN-PiWAD indicates video description, negative video content, and channel credibility are key features that drive viral transmission of misinformation. This study contributes to IS with a novel interpretable deep learning method that is generalizable to understand other human decision factors. Our findings provide direct implications for social media platforms and policymakers to design proactive interventions to identify misinformation, control transmissions, and manage infodemics.

Recently, commodity Wi-Fi devices have been shown to be able to construct human pose images, i.e., human skeletons, as fine-grained as cameras. Existing papers achieve good results when constructing the images of subjects who are in the prior training samples. However, the performance drops when it comes to new subjects, i.e., the subjects who are not in the training samples. This paper focuses on solving the subject-generalization problem in human pose image construction. To this end, we define the subject as the domain. Then we design a Domain-Independent Neural Network (DINN) to extract subject-independent features and convert them into fine-grained human pose images. We also propose a novel training method to train the DINN and it has no re-training overhead comparing with the domain-adversarial approach. We build a prototype system and experimental results demonstrate that our system can construct fine-grained human pose images of new subjects with commodity Wi-Fi in both the visible and through-wall scenarios, which shows the effectiveness and the subject-generalization ability of our model.

Deep learning models have demonstrated superior performance in several application problems, such as image classification and speech processing. However, creating a deep learning model using health record data requires addressing certain privacy challenges that bring unique concerns to researchers working in this domain. One effective way to handle such private data issues is to generate realistic synthetic data that can provide practically acceptable data quality and correspondingly the model performance. To tackle this challenge, we develop a differentially private framework for synthetic data generation using R\'enyi differential privacy. Our approach builds on convolutional autoencoders and convolutional generative adversarial networks to preserve some of the critical characteristics of the generated synthetic data. In addition, our model can also capture the temporal information and feature correlations that might be present in the original data. We demonstrate that our model outperforms existing state-of-the-art models under the same privacy budget using several publicly available benchmark medical datasets in both supervised and unsupervised settings.

Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods such as adversarial training explicitly uses an "attack" (e.g., $\ell_{\infty}$-norm bounded perturbation) to generate adversarial examples during model training for improving adversarial robustness. In this paper, we take a different perspective and propose a new framework called SPROUT, self-progressing robust training. During model training, SPROUT progressively adjusts training label distribution via our proposed parametrized label smoothing technique, making training free of attack generation and more scalable. We also motivate SPROUT using a general formulation based on vicinity risk minimization, which includes many robust training methods as special cases. Compared with state-of-the-art adversarial training methods (PGD-l_inf and TRADES) under l_inf-norm bounded attacks and various invariance tests, SPROUT consistently attains superior performance and is more scalable to large neural networks. Our results shed new light on scalable, effective and attack-independent robust training methods.

Real-time artificial intelligence (AI) applications mapped onto edge computing need to perform data capture, process data, and device actuation within given bounds while using the available devices. Task synchronization across the devices is an important problem that affects the timely progress of an AI application by determining the quality of the captured data, time to process the data, and the quality of actuation. In this paper, we develop a fast edge-based synchronization scheme that can time align the execution of input-output tasks as well compute tasks. The primary idea of the fast synchronizer is to cluster the devices into groups that are highly synchronized in their task executions and statically determine few synchronization points using a game-theoretic solver. The cluster of devices use a late notification protocol to select the best point among the pre-computed synchronization points to reach a time aligned task execution as quickly as possible. We evaluate the performance of our synchronization scheme using trace-driven simulations and we compare the performance with existing distributed synchronization schemes for real-time AI application tasks. We implement our synchronization scheme and compare its training accuracy and training time with other parameter server synchronization frameworks.

We propose a novel Transformer encoder-based architecture with syntactical knowledge encoded for intent detection and slot filling. Specifically, we encode syntactic knowledge into the Transformer encoder by jointly training it to predict syntactic parse ancestors and part-of-speech of each token via multi-task learning. Our model is based on self-attention and feed-forward layers and does not require external syntactic information to be available at inference time. Experiments show that on two benchmark datasets, our models with only two Transformer encoder layers achieve state-of-the-art results. Compared to the previously best performed model without pre-training, our models achieve absolute F1 score and accuracy improvement of 1.59% and 0.85% for slot filling and intent detection on the SNIPS dataset, respectively. Our models also achieve absolute F1 score and accuracy improvement of 0.1% and 0.34% for slot filling and intent detection on the ATIS dataset, respectively, over the previously best performed model. Furthermore, the visualization of the self-attention weights illustrates the benefits of incorporating syntactic information during training.

We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world robotic scenarios. The modular structure of the simulator enables users to train and validate their algorithms on a large number of scenarios with various robots, environments and tasks. Compared to existing toolkits (e.g. OpenAI Gym, Roboschool) which are suitable for classical RL, myGym is also prepared for visuomotor (combining vision & movement) unsupervised tasks that require intrinsic motivation, i.e. the robots are able to generate their own goals. There are also collaborative scenarios intended for human-robot interaction. The toolkit provides pretrained visual modules for visuomotor tasks allowing rapid prototyping, and, moreover, users can customize the visual submodules and retrain with their own set of objects. In practice, the user selects the desired environment, robot, objects, task and type of reward as simulation parameters, and the training, visualization and testing themselves are handled automatically. The user can thus fully focus on development of the neural network architecture while controlling the behaviour of the environment using predefined parameters.

Traditional biomedical version of embeddings obtained from pre-trained language models have recently shown state-of-the-art results for relation extraction (RE) tasks in the medical domain. In this paper, we explore how to incorporate domain knowledge, available in the form of molecular structure of drugs, for predicting Drug-Drug Interaction from textual corpus. We propose a method, BERTChem-DDI, to efficiently combine drug embeddings obtained from the rich chemical structure of drugs along with off-the-shelf domain-specific BioBERT embedding-based RE architecture. Experiments conducted on the DDIExtraction 2013 corpus clearly indicate that this strategy improves other strong baselines architectures by 3.4\% macro F1-score.

When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the answer for a question. Over the last few years, we have seen significant progress on visual question answering. Though impressive as the accuracy grows, it still lags behind to get knowing whether these models are undertaking grounding visual reasoning or just leveraging spurious correlations in the training data. Recently, a number of works have attempted to answer this question from perspectives such as grounding and robustness. However, most of them are either focusing on the language side or coarsely studying the pixel-level attention maps. In this paper, by leveraging the step-wise object grounding annotations provided in the GQA dataset, we first present a systematical object-centric diagnosis of visual reasoning on grounding and robustness, particularly on the vision side. According to the extensive comparisons across different models, we find that even models with high accuracy are not good at grounding objects precisely, nor robust to visual content perturbations. In contrast, symbolic and modular models have a relatively better grounding and robustness, though at the cost of accuracy. To reconcile these different aspects, we further develop a diagnostic model, namely Graph Reasoning Machine. Our model replaces purely symbolic visual representation with probabilistic scene graph and then applies teacher-forcing training for the visual reasoning module. The designed model improves the performance on all three metrics over the vanilla neural-symbolic model while inheriting the transparency. Further ablation studies suggest that this improvement is mainly due to more accurate image understanding and proper intermediate reasoning supervisions.