Recurrent Neural Hidden Markov Model for High-order Transition

We propose a method to pay attention to high-order relations among latent states to improve the conventional HMMs that focus only on the latest latent state, since they assume Markov property. To address the high-order relations, we apply an RNN to each sequence of latent states, because the RNN can represent the information of an arbitrary-length sequence with their cell: a fixed-size vector. However, the simplest way, which provides all latent sequences explicitly for the RNN, is intractable due to the combinatorial explosion of the search space of latent states. Thus, we modify the RNN to represent the history of latent states from the beginning of the sequence to the current state with a fixed number of RNN cells whose number is equal to the number of possible states. We conduct experiments on unsupervised POS tagging and synthetic datasets. Experimental results show that the proposed method achieves better performance than previous methods. In addition, the results on the synthetic dataset indicate that the proposed method can capture the high-order relations.

A Graph Theoretic Approach for Multi-Objective Budget Constrained Capsule Wardrobe Recommendation

Traditionally, capsule wardrobes are manually designed by expert fashionistas through their creativity and technical prowess. The goal is to curate minimal fashion items that can be assembled into several compatible and versatile outfits. It is usually a cost and time intensive process, and hence lacks scalability. Although there are a few approaches that attempt to automate the process, they tend to ignore the price of items or shopping budget. In this article, we formulate this task as a multi-objective budget constrained capsule wardrobe recommendation ( MOBCCWR ) problem. It is modeled as a bipartite graph having two disjoint vertex sets corresponding to top-wear and bottom-wear items, respectively. An edge represents compatibility between the corresponding item pairs. The objective is to find a 1-neighbor subset of fashion items as a capsule wardrobe that jointly maximize compatibility and versatility scores by considering corresponding user-specified preference weight coefficients and an overall shopping budget as a means of achieving personalization. We study the complexity class of MOBCCWR , show that it is NP-Complete, and propose a greedy algorithm for finding a near-optimal solution in real time. We also analyze the time complexity and approximation bound for our algorithm. Experimental results show the effectiveness of the proposed approach on both real and synthetic datasets.

State Estimation in Electric Power Systems Leveraging Graph Neural Networks

The goal of the state estimation (SE) algorithm is to estimate complex bus voltages as state variables based on the available set of measurements in the power system. Because phasor measurement units (PMUs) are increasingly being used in transmission power systems, there is a need for a fast SE solver that can take advantage of PMU high sampling rates. This paper proposes training a graph neural network (GNN) to learn the estimates given the PMU voltage and current measurements as inputs, with the intent of obtaining fast and accurate predictions during the evaluation phase. GNN is trained using synthetic datasets, created by randomly sampling sets of measurements in the power system and labelling them with a solution obtained using a linear SE with PMUs solver. The presented results display the accuracy of GNN predictions in various test scenarios and tackle the sensitivity of the predictions to the missing input data.

State Estimation in Electric Power Systems Leveraging Graph Neural Networks

The goal of the state estimation (SE) algorithm is to estimate complex bus voltages as state variables based on the available set of measurements in the power system. Because phasor measurement units (PMUs) are increasingly being used in transmission power systems, there is a need for a fast SE solver that can take advantage of PMU high sampling rates. This paper proposes training a graph neural network (GNN) to learn the estimates given the PMU voltage and current measurements as inputs, with the intent of obtaining fast and accurate predictions during the evaluation phase. GNN is trained using synthetic datasets, created by randomly sampling sets of measurements in the power system and labelling them with a solution obtained using a linear SE with PMUs solver. The presented results display the accuracy of GNN predictions in various test scenarios and tackle the sensitivity of the predictions to the missing input data.

PACAM: A Pairwise-Allocated Strategy and Capability Average Matrix-Based Task Scheduling Approach for Edge Computing

With the development of the smart Internet of Things (IoT), an increasing number of tasks are deployed on the edge of the network. Considering the substantially limited processing capability of IoT devices, task scheduling as an effective solution offers low latency and flexible computation to improve the system performance and increase the quality of services. However, limited computing resources make it challenging to assign the right tasks to the right devices at the edge of the network. To this end, we propose a polynomial-time solution, which consists of three steps, i.e., identifying available devices, estimating device quantity, and searching for feasible schedules. In order to shrink the number of potential schedules, we present a pairwise-allocated strategy (PA). Based on these, a capability average matrix (CAM)-based index is designed to further boost efficiency. In addition, we evaluate the schedules by the technique for order preference by similarity to an ideal solution (TOPSIS). Extensive experimental evaluation using both real and synthetic datasets demonstrates the efficiency and effectiveness of our proposed approach.

Single Image Re ection Removal via Deep Feature Contrast

Removing undesired re ection from a single image is in demand for computational photography. Re ection removal methods are gradually effective because of the fast development of deep neural networks. However, current results of re ection removal methods usually leave salient re ection residues due to the challenge of recognizing diverse re ection patterns. In this paper, we present a one-stage re ection removal framework with an end-to-end manner that considers both low-level information correlation and efficient feature separation. Our approach employs the criss-cross attention mechanism to extract low-level features and to efficiently enhance contextual correlation. To thoroughly remove re ection residues in the background image, we punish the similar texture feature by contrasting the parallel feature separa- tion networks, and thus unrelated textures in the background image could be progressively separated during model training. Experiments on both real-world and synthetic datasets manifest our approach can reach the state-of-the-art effect quantitatively and qualitatively.

Multiple weak supervision for short text classification

For short text classification, insufficient labeled data, data sparsity, and imbalanced classification have become three major challenges. For this, we proposed multiple weak supervision, which can label unlabeled data automatically. Different from prior work, the proposed method can generate probabilistic labels through conditional independent model. What’s more, experiments were conducted to verify the effectiveness of multiple weak supervision. According to experimental results on public dadasets, real datasets and synthetic datasets, unlabeled imbalanced short text classification problem can be solved effectively by multiple weak supervision. Notably, without reducing precision, recall, and F1-score can be improved by adding distant supervision clustering, which can be used to meet different application needs.

Synthetic Data Generation with Differential Privacy via Bayesian Networks

This paper describes PrivBayes, a differentially private method for generating synthetic datasets that was used in the 2018 Differential Privacy Synthetic Data Challenge organized by NIST.

Epi-MEIF, a flexible and efficient method for detection of high order epistatic interactions from complex phenotypic traits

Understanding the relationship between genetic variations and variations in complex and quantitative phenotypes remains an ongoing challenge. While genome-wide association studies (GWAS) have become a vital tool for identifying single-locus associations, we lack methods for identifying epistatic interactions. In this article, we propose a novel method for high-order epistasis detection using mixed effect conditional inference forest (epiMEIF). The epiMEIF model is fitted on a group of potential causal SNPs and the tree structure in the forest facilitates the identification of n-way interactions between the SNPs. Additional testing strategies further improve the robustness of the method. We demonstrate its ability to detect true n-way interactions via extensive simulations in both cross-sectional and longitudinal synthetic datasets. This is further illustrated in an application to reveal epistatic interactions from natural variations of cardiac traits in flies (Drosophila). Overall, the method provides a generalized way to identify high order interactions from any GWAS data, thereby greatly improving the detection of the genetic architecture of complex phenotypes.