Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.

We regard pre-trained residual networks (ResNets) as nonlinear systems and use linearization, a common method used in the qualitative analysis of nonlinear systems, to understand the behavior of the networks under small perturbations of the input images. We work with ResNet-56 and ResNet-110 trained on the CIFAR-10 data set. We linearize these networks at the level of residual units and network stages, and the singular value decomposition is used in the stability analysis of these components. It is found that most of the singular values of the linearizations of residual units are 1 and, in spite of the fact that the linearizations depend directly on the activation maps, the singular values differ only slightly for different input images. However, adjusting the scaling of the skip connection or the values of the weights in a residual unit has a significant impact on the singular value distributions. Inspection of how random and adversarial perturbations of input images propagate through the network reveals that there is a dramatic jump in the magnitude of adversarial perturbations towards the end of the final stage of the network that is not present in the case of random perturbations. We attempt to gain a better understanding of this phenomenon by projecting the perturbations onto singular vectors of the linearizations of the residual units.

We present a deep reinforcement learning approach to optimizing the execution cost of computation graphs in a static compiler. The key idea is to combine a neural network policy with a genetic algorithm, the Biased Random-Key Genetic Algorithm (BRKGA). The policy is trained to predict, given an input graph to be optimized, the node-level probability distributions for sampling mutations and crossovers in BRKGA. Our approach, "REINFORCE-based Genetic Algorithm Learning" (REGAL), uses the policy's ability to transfer to new graphs to significantly improve the solution quality of the genetic algorithm for the same objective evaluation budget. As a concrete application, we show results for minimizing peak memory in TensorFlow graphs by jointly optimizing device placement and scheduling. REGAL achieves on average 3.56% lower peak memory than BRKGA on previously unseen graphs, outperforming all the algorithms we compare to, and giving 4.4x bigger improvement than the next best algorithm. We also evaluate REGAL on a production compiler team's performance benchmark of XLA graphs and achieve on average 3.74% lower peak memory than BRKGA, again outperforming all others. Our approach and analysis is made possible by collecting a dataset of 372 unique real-world TensorFlow graphs, more than an order of magnitude more data than previous work.

The ability of reasoning beyond data fitting is substantial to deep learning systems in order to make a leap forward towards artificial general intelligence. A lot of efforts have been made to model neural-based reasoning as an iterative decision-making process based on recurrent networks and reinforcement learning. Instead, inspired by the consciousness prior proposed by Yoshua Bengio, we explore reasoning with the notion of attentive awareness from a cognitive perspective, and formulate it in the form of attentive message passing on graphs, called neural consciousness flow (NeuCFlow). Aiming to bridge the gap between deep learning systems and reasoning, we propose an attentive computation framework with a three-layer architecture, which consists of an unconsciousness flow layer, a consciousness flow layer, and an attention flow layer. We implement the NeuCFlow model with graph neural networks (GNNs) and conditional transition matrices. Our attentive computation greatly reduces the complexity of vanilla GNN-based methods, capable of running on large-scale graphs. We validate our model for knowledge graph reasoning by solving a series of knowledge base completion (KBC) tasks. The experimental results show NeuCFlow significantly outperforms previous state-of-the-art KBC methods, including the embedding-based and the path-based. The reproducible code can be found by the link below.

AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.

In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied as online recommendation and network routing. On the other hand, these applications typically contain contextual information that can guide the learning process which, however, is ignored by most of existing work. To utilize this information, we associate each arm with a context vector and assume the reward follows the generalized linear model (GLM). We adopt the notion of Pareto regret to evaluate the learner's performance and develop a novel algorithm for minimizing it. The essential idea is to apply a variant of the online Newton step to estimate model parameters, based on which we utilize the upper confidence bound (UCB) policy to construct an approximation of the Pareto front, and then uniformly at random choose one arm from the approximate Pareto front. Theoretical analysis shows that the proposed algorithm achieves an $\tilde O(d\sqrt{T})$ Pareto regret, where $T$ is the time horizon and $d$ is the dimension of contexts, which matches the optimal result for single objective contextual bandits problem. Numerical experiments demonstrate the effectiveness of our method.

We present a novel approach to train pixel resolution segmentation models on whole slide images in a weakly supervised setup. The model is trained to classify patches extracted from slides. This leads the training to be made under noisy labeled data. We solve the problem with two complementary strategies. First, the patches are sampled online using the model's knowledge by focusing on regions where the model's confidence is higher. Second, we propose an extension of the KL divergence that is robust to noisy labels. Our preliminary experiment on CAMELYON 16 data set show promising results.

Hiring robots for the workplaces is a challenging task as robots have to cater to customer demands, follow organizational protocols and behave with social etiquette. In this study, we propose to have a humanoid social robot, Nadine, as a customer service agent in an open social work environment. The objective of this study is to analyze the effects of humanoid robots on customers at work environment, and see if it can handle social scenarios. We propose to evaluate these objectives through two modes, namely, survey questionnaire and customer feedback. We also propose a novel approach to analyze customer feedback data (text) using sentic computing methods. Specifically, we employ aspect extraction and sentiment analysis to analyze the data. From our framework, we detect sentiment associated to the aspects that mainly concerned the customers during their interaction. This allows us to understand customers expectations and current limitations of robots as employees.

We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence. Based on a Frank-Wolfe optimization strategy, our approach proceeds by populating the support of the barycenter incrementally, without requiring any pre-allocation. We consider discrete as well as continuous distributions, proving convergence rates of the proposed algorithm in both settings. Key elements of our analysis are a new result showing that the Sinkhorn divergence on compact domains has Lipschitz continuous gradient with respect to the Total Variation and a characterization of the sample complexity of Sinkhorn potentials. Experiments validate the effectiveness of our method in practice.

Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data. To tackle highly variable and noisy real-world data, we introduce Particle Filter Recurrent Neural Networks (PF-RNNs), a new RNN family that explicitly models uncertainty in its internal structure: while an RNN relies on a long, deterministic latent state vector, a PF-RNN maintains a latent state distribution, approximated as a set of particles. For effective learning, we provide a fully differentiable particle filter algorithm that updates the PF-RNN latent state distribution according to the Bayes rule. Experiments demonstrate that the proposed PF-RNNs outperform the corresponding standard gated RNNs on a synthetic robot localization dataset and 10 real-world sequence prediction datasets for text classification, stock price prediction, etc.