The research on human emotion under multimedia stimulation based on physiological signals is an emerging field, and important progress has been achieved for emotion recognition based on multi-modal signals. However, it is challenging to make full use of the complementarity among spatial-spectral-temporal domain features for emotion recognition, as well as model the heterogeneity and correlation among multi-modal signals. In this paper, we propose a novel two-stream heterogeneous graph recurrent neural network, named HetEmotionNet, fusing multi-modal physiological signals for emotion recognition. Specifically, HetEmotionNet consists of the spatial-temporal stream and the spatial-spectral stream, which can fuse spatial-spectral-temporal domain features in a unified framework. Each stream is composed of the graph transformer network for modeling the heterogeneity, the graph convolutional network for modeling the correlation, and the gated recurrent unit for capturing the temporal domain or spectral domain dependency. Extensive experiments on two real-world datasets demonstrate that our proposed model achieves better performance than state-of-the-art baselines.

This paper addresses the problem of optimizing partition functions in a stochastic learning setting. We propose a stochastic variant of the bound majorization algorithm from [29] that relies on upperbounding the partition function with a quadratic surrogate. The update of the proposed method, that we refer to as Stochastic Partition Function Bound (SPFB), resembles scaled stochastic gradient descent where the scaling factor relies on a second order term that is however different from the Hessian. Similarly to quasi-Newton schemes, this term is constructed using the stochastic approximation of the value of the function and its gradient. We prove sub-linear convergence rate of the proposed method and show the construction of its low-rank variant (LSPFB). Experiments on logistic regression demonstrate that the proposed schemes significantly outperform SGD. We also discuss how to use quadratic partition function bound for efficient training of deep learning models and in non-convex optimization.

Abstract--Bayesian networks are powerful statistical models to study the probabilistic relationships among set random variables with major applications in disease modeling and prediction. Here, we propose a continuous time Bayesian network with conditional dependencies, represented as Poisson regression, to model the impact of exogenous variables on the conditional dependencies of the network. We also propose an adaptive regularization method with an intuitive early stopping feature based on density based clustering for efficient learning of the structure and parameters of the proposed network. Using a dataset of patients with multiple chronic conditions extracted from electronic health records of the Department of Veterans Affairs we compare the performance of the proposed approach with some of the existing methods in the literature for both short-term (one-year ahead) and long-term (multi-year ahead) predictions. The proposed approach provides a sparse intuitive representation of the complex functional relationships between multiple chronic conditions. It also provides the capability of analyzing multiple disease trajectories over time given any combination of prior conditions.

How about converting Taylor series to a network to solve the black-box nature of Neural Networks? Controllable and readable polynomial neural network (Gang transform or CR-PNN) is the Taylor expansion in the form of network, which is about ten times more efficient than typical BPNN for forward-propagation. Additionally, we can control the approximation precision and explain the internal structure of the network; thus, it is used for prediction and system identification. However, as the network depth increases, the computational complexity increases. Here, we presented an accelerated method based on an expanded order to optimize CR-PNN. The running speed of the structure of CR-PNN II is significantly higher than CR-PNN I under preserving the properties of CR-PNN I.

There are two famous function decomposition methods in math: 1) Taylor Series and 2) Fourier Series. The Fourier series developed into the Fourier spectrum, which was applied to signal analysis. However, Because a function without a functional expression cannot be solved for its Taylor series, Taylor Series has rarely been used in engineering. Here we have solved this problem, learned from Fourier, developed Taylor series, constructed a relation spectrum, and applied it to system analysis. Specific engineering application: the knowledge of the intuitive link between muscle activity and the finger movement is vital for the design of commercial prosthetic hands that do not need user pre-training. However, this link has yet to be understood due to the complexity of human hand. In this study, the relation spectrum was developed for the first time and applied to analyze the muscle-finger system. We established controllable and human-readable polynomial neural network (CR-PNN) models for six degrees of freedom ( DOFs) in 8 subjects. Multiple fingers may be controlled by a single muscle, or multiple muscles may control a single finger. Thus, the research is based on two aspects: muscle synergy and muscle coupling for hand. The research gave the relation spectrum of the muscle-finger system and the knowledge of muscle coupling. The article is very short but significant. The contributions of this paper can be divided into two parts: (1) The findings of hand can contribute to design prosthetic hands. (2) The relation spectrum using CR-PNN can provide a reference for analyzing complex systems in multiple areas. (We're strong believers in Open Source, and provide CR-PNN code for others. GitHub: https://github.com/liugang1234567/CR-PNN#cr-pnn. )

Deep Reinforcement Learning (RL) is proven powerful for decision making in simulated environments. However, training deep RL model is challenging in real world applications such as production-scale health-care or recommender systems because of the expensiveness of interaction and limitation of budget at deployment. One aspect of the data inefficiency comes from the expensive hyper-parameter tuning when optimizing deep neural networks. We propose Adaptive Behavior Policy Sharing (ABPS), a data-efficient training algorithm that allows sharing of experience collected by behavior policy that is adaptively selected from a pool of agents trained with an ensemble of hyper-parameters. We further extend ABPS to evolve hyper-parameters during training by hybridizing ABPS with an adapted version of Population Based Training (ABPS-PBT). We conduct experiments with multiple Atari games with up to 16 hyper-parameter/architecture setups. ABPS achieves superior overall performance, reduced variance on top 25% agents, and equivalent performance on the best agent compared to conventional hyper-parameter tuning with independent training, even though ABPS only requires the same number of environmental interactions as training a single agent. We also show that ABPS-PBT further improves the convergence speed and reduces the variance.

We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users. RecSim allows the creation of new environments that reflect particular aspects of user behavior and item structure at a level of abstraction well-suited to pushing the limits of current reinforcement learning (RL) and RS techniques in sequential interactive recommendation problems. Environments can be easily configured that vary assumptions about: user preferences and item familiarity; user latent state and its dynamics; and choice models and other user response behavior. We outline how RecSim offers value to RL and RS researchers and practitioners, and how it can serve as a vehicle for academic-industrial collaboration.

Suffering from the multi-view data diversity and complexity for semi-supervised classification, most of existing graph convolutional networks focus on the networks architecture construction or the salient graph structure preservation, and ignore the the complete graph structure for semi-supervised classification contribution. To mine the more complete distribution structure from multi-view data with the consideration of the specificity and the commonality, we propose structure fusion based on graph convolutional networks (SF-GCN) for improving the performance of semi-supervised classification. SF-GCN can not only retain the special characteristic of each view data by spectral embedding, but also capture the common style of multi-view data by distance metric between multi-graph structures. Suppose the linear relationship between multi-graph structures, we can construct the optimization function of structure fusion model by balancing the specificity loss and the commonality loss. By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification. Experiments demonstrate that the performance of SF-GCN outperforms that of the state of the arts on three challenging datasets, which are Cora,Citeseer and Pubmed in citation networks.

Recommender systems have become ubiquitous, transforming user interactions with products, services and content in a wide variety of domains. In content recommendation, recommenders generally surface relevant and/or novel personalized content based on learned models of user preferences (e.g., as in collaborative filtering [Breese et al., 1998, Konstan et al., 1997, Srebro et al., 2004, Salakhutdinov and Mnih, 2007]) or predictive models of user responses to specific recommendations. Well-known applications of recommender systems include video recommendations on YouTube [Covington et al., 2016], movie recommendations on Netflix [Gomez-Uribe and Hunt, 2016] and playlist construction on Spotify [Jacobson et al., 2016]. It is increasingly common to train deep neural networks (DNNs) [van den Oord et al., 2013, Wang et al., 2015, Covington et al., 2016, Cheng et al., 2016] to predict user responses (e.g., click-through rates, content engagement, ratings, likes) to generate, score and serve candidate recommendations. Practical recommender systems largely focus on myopic prediction--estimating a user's immediate response to a recommendation--without considering the long-term impact on subsequent user behavior. This can be limiting: modeling a recommendation's stochastic impact on the future affords opportunities to trade off user engagement in the near-term for longer-term benefit (e.g., by probing a user's interests, or improving satisfaction).

Motivated by the important archaeological application of exploring cultural heritage objects, in this paper we study the challenging problem of automatically segmenting curve structures that are very weakly stamped or carved on an object surface in the form of a highly noisy depth map. Different from most classical low-level image segmentation methods that are known to be very sensitive to the noise and occlusions, we propose a new supervised learning algorithm based on Convolutional Neural Network (CNN) to implicitly learn and utilize more curve geometry and pattern information for addressing this challenging problem. More specifically, we first propose a Fully Convolutional Network (FCN) to estimate the skeleton of curve structures and at each skeleton pixel, a scale value is estimated to reflect the local curve width. Then we propose a dense prediction network to refine the estimated curve skeletons. Based on the estimated scale values, we finally develop an adaptive thresholding algorithm to achieve the final segmentation of curve structures. In the experiment, we validate the performance of the proposed method on a dataset of depth images scanned from unearthed pottery shards dating to the Woodland period of Southeastern North America.