arXiv subjects

Boyu Wang

Publications and source records attributed to Boyu Wang.

104 records · Page 6Linked to original sources

arXiv2020

Discriminative Active Learning for Domain Adaptation

Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marginal feature distributions using the adversarial training methods while assuming the conditional relations between the source and target domain remained unchanged, $i.e.$, ignoring the conditional shift problem. However, recent works have shown that such a conditional shift problem exists and can hinder the adaptation process. To address this issue, we have to leverage labelled data from the target domain, but collecting labelled data can be quite expensive and time-consuming. To this end, we introduce a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation. Specifically, we propose three-stage active adversarial training of neural networks: invariant feature space learning (first stage), uncertainty and diversity criteria and their trade-off for query strategy (second stage) and re-training with queried target labels (third stage). Empirical comparisons with existing domain adaptation methods using four benchmark datasets demonstrate the effectiveness of the proposed approach.

cs.LG↗

arXiv2020

Deep Active Learning: Unified and Principled Method for Query and Training

In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights from the intuition of modeling the interactive procedure in active learning as distribution matching, by adopting the Wasserstein distance. As a consequence, we derived a new training loss from the theoretical analysis, which is decomposed into optimizing deep neural network parameters and batch query selection through alternative optimization. In addition, the loss for training a deep neural network is naturally formulated as a min-max optimization problem through leveraging the unlabeled data information. Moreover, the proposed principles also indicate an explicit uncertainty-diversity trade-off in the query batch selection. Finally, we evaluate our proposed method on different benchmarks, consistently showing better empirical performances and a better time-efficient query strategy compared to the baselines.

cs.LG↗

arXiv2019

Multi-view Subspace Clustering via Partition Fusion

Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way. Among various methods, the multi-view subspace clustering approach has gained increasing attention due to its encouraging performance. Basically, it integrates multi-view information into graphs, which are then fed into spectral clustering algorithm for final result. However, its performance may degrade due to noises existing in each individual view or inconsistency between heterogeneous features. Orthogonal to current work, we propose to fuse multi-view information in a partition space, which enhances the robustness of Multi-view clustering. Specifically, we generate multiple partitions and integrate them to find the shared partition. The proposed model unifies graph learning, generation of basic partitions, and view weight learning. These three components co-evolve towards better quality outputs. We have conducted comprehensive experiments on benchmark datasets and our empirical results verify the effectiveness and robustness of our approach.

cs.LG↗

arXiv2019

Efficient Projection-Free Online Methods with Stochastic Recursive Gradient

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-iteration computational costs. Experimental results demonstrate the efficiency of the proposed methods compared to state-of-the-arts.

cs.LG↗

arXiv2019

Visual Understanding of Multiple Attributes Learning Model of X-Ray Scattering Images

This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images. The system focuses on studying the model behaviors related to multiple structural attributes. It allows users to explore the images in the feature space, the classification output of different attributes, with respect to the actual attributes labelled by domain scientists. Abundant interactions allow users to flexibly select instance images, their clusters, and compare them visually in details. Two preliminary case studies demonstrate its functionalities and usefulness.

cs.LG↗

arXiv2019

A Principled Approach for Learning Task Similarity in Multitask Learning

Multitask learning aims at solving a set of related tasks simultaneously, by exploiting the shared knowledge for improving the performance on individual tasks. Hence, an important aspect of multitask learning is to understand the similarities within a set of tasks. Previous works have incorporated this similarity information explicitly (e.g., weighted loss for each task) or implicitly (e.g., adversarial loss for feature adaptation), for achieving good empirical performances. However, the theoretical motivations for adding task similarity knowledge are often missing or incomplete. In this paper, we give a different perspective from a theoretical point of view to understand this practice. We first provide an upper bound on the generalization error of multitask learning, showing the benefit of explicit and implicit task similarity knowledge. We systematically derive the bounds based on two distinct task similarity metrics: H divergence and Wasserstein distance. From these theoretical results, we revisit the Adversarial Multi-task Neural Network, proposing a new training algorithm to learn the task relation coefficients and neural network parameters iteratively. We assess our new algorithm empirically on several benchmarks, showing not only that we find interesting and robust task relations, but that the proposed approach outperforms the baselines, reaffirming the benefits of theoretical insight in algorithm design.

cs.LG↗

arXiv2019

Clustering with Similarity Preserving

Graph-based clustering has shown promising performance in many tasks. A key step of graph-based approach is the similarity graph construction. In general, learning graph in kernel space can enhance clustering accuracy due to the incorporation of nonlinearity. However, most existing kernel-based graph learning mechanisms is not similarity-preserving, hence leads to sub-optimal performance. To overcome this drawback, we propose a more discriminative graph learning method which can preserve the pairwise similarities between samples in an adaptive manner for the first time. Specifically, we require the learned graph be close to a kernel matrix, which serves as a measure of similarity in raw data. Moreover, the structure is adaptively tuned so that the number of connected components of the graph is exactly equal to the number of clusters. Finally, our method unifies clustering and graph learning which can directly obtain cluster indicators from the graph itself without performing further clustering step. The effectiveness of this approach is examined on both single and multiple kernel learning scenarios in several datasets.

cs.LG↗

arXiv2019

Superconducting Fault Current Limiter Allocation in Reconfigurable Smart Grids

Superconducting fault current limiters (SFCLs) are new high-precision and fast-response devices which help to reduce the fault current within the breaking capacity of the protective relays. Nevertheless, the reconfigurable structure of the distribution network can affect their performance negatively by changing the supplying path of the electrical loads and thus keeping SFCL in a useless point which cannot limit the high fault currents. This paper proposes an aggregated approach to solve the optimal placement of SFCLs considering the reconfiguration of feeders through the pre-located tie and sectionalizing switches. While SFCL placement problem aims to minimize the number of SFCLs and limit the high short circuit currents in the first seconds of the fault, the reconfiguration strategy is used to minimize the total grid costs incorporating the cost of power losses and customer interruptions. According to the high non-linearity and complexity of the proposed problem, social spider algorithm (SSA) with a two-phase modification method is developed to solve the proposed problem. The feasibility and performance of the proposed method are examined on an IEEE test system.

eess.SY↗

arXiv2019

When to Preempt? Age of Information Minimization under Link Capacity Constraint

In this paper, we consider a scenario where a source continuously monitors an object and sends time-stamped status updates to a destination through a rate-limited link. We assume updates arrive randomly at the source according to a Bernoulli process. Due to the link capacity constraint, it takes multiple time slots for the source to complete the transmission of an update. Therefore, when a new update arrives at the source during the transmission of another update, the source needs to decide whether to skip the new arrival or to switch to it, in order to minimize the expected average age of information (AoI) at the destination. We start with the setting where all updates are of the same size, and prove that within a broadly defined class of online policies, the optimal policy should be a renewal policy, and has a sequential switching property. We then show that the optimal decision of the source in any time slot has threshold structures, and only depends on the age of the update being transmitted and the AoI at the destination. We then consider the setting where updates are of different sizes, and show that the optimal Markovian policy also has a multiple-threshold structure. For each of the settings, we explicitly identify the thresholds by formulating the problem as a Markov Decision Process (MDP), and solve it through value iteration. Special structural properties of the corresponding optimal policy are utilized to reduce the computational complexity of the value iteration algorithm.

cs.IT↗

arXiv2018

Leveraging Disease Progression Learning for Medical Image Recognition

Unlike natural images, medical images often have intrinsic characteristics that can be leveraged for neural network learning. For example, images that belong to different stages of a disease may continuously follow a certain progression pattern. In this paper, we propose a novel method that leverages disease progression learning for medical image recognition. In our method, sequences of images ordered by disease stages are learned by a neural network that consists of a shared vision model for feature extraction and a long short-term memory network for the learning of stage sequences. Auxiliary vision outputs are also included to capture stage features that tend to be discrete along the disease progression. Our proposed method is evaluated on a public diabetic retinopathy dataset, and achieves about 3.3% improvement in disease staging accuracy, compared to the baseline method that does not use disease progression learning.

cs.CV↗

arXiv2018

To Skip or to Switch? Minimizing Age of Information under Link Capacity Constraint

Consider a scenario where a source continuously monitors an object and sends time-stamped status updates to a destination through a rate-limited link. In order to measure the "freshness" of the status information available at the destination, we adopt the metric called Age of Information (AoI). We assume all updates are of the same size, and arrive randomly at the source according to a Bernoulli process. Due to the link capacity constraint, it takes $d$ ($d\geq 2$) time slots for the source to complete the transmission of an update. Therefore, when a new update when arrives at the source and it is transmitting another update, the source needs to decide whether to skip the new arrival or to switch to it, in order to minimize the expected average AoI at the destination. We prove that within a broadly defined class of online policies, the optimal policy should be a renewal policy, and has a sequential switching property. We then show that the optimal decision the source should take in any time slot has a multiple-threshold structure, and only depends on the age of the update being transmitted and the AoI in the system. The thresholds are then numerically identified by formulating the problem as a Markov Decision Process (MDP).

cs.IT↗

arXiv2016

Random samples of quantum states: Online resources

This is the documentation for generating random samples from the quantum state space in accordance with a specified distribution, associated with this webpage: http://tinyurl.com/QSampling . Ready-made samples (each with at least a million points) from various distributions are available for download, or one can generate one's own samples from a chosen distribution using the provided source codes. The sampling relies on the Hamiltonian Monte Carlo algorithm as described in New J. Phys. 17, 043018 (2015). The random samples are reposited in the hope that they would be useful for a variety of tasks in quantum information and quantum computation. Constructing credible regions for tomographic data, optimizing a function over the quantum state space with a complicated landscape, testing the typicality of entanglement among states from a multipartite quantum system, or computing the average of some quantity of interest over a subset of quantum states are but some exemplary applications among many.

quant-ph↗

arXiv2016

X-ray Scattering Image Classification Using Deep Learning

Visual inspection of x-ray scattering images is a powerful technique for probing the physical structure of materials at the molecular scale. In this paper, we explore the use of deep learning to develop methods for automatically analyzing x-ray scattering images. In particular, we apply Convolutional Neural Networks and Convolutional Autoencoders for x-ray scattering image classification. To acquire enough training data for deep learning, we use simulation software to generate synthetic x-ray scattering images. Experiments show that deep learning methods outperform previously published methods by 10\% on synthetic and real datasets.

cs.CV↗

arXiv2013

Online Ensemble Learning for Imbalanced Data Streams

While both cost-sensitive learning and online learning have been studied extensively, the effort in simultaneously dealing with these two issues is limited. Aiming at this challenge task, a novel learning framework is proposed in this paper. The key idea is based on the fusion of online ensemble algorithms and the state of the art batch mode cost-sensitive bagging/boosting algorithms. Within this framework, two separately developed research areas are bridged together, and a batch of theoretically sound online cost-sensitive bagging and online cost-sensitive boosting algorithms are first proposed. Unlike other online cost-sensitive learning algorithms lacking theoretical analysis of asymptotic properties, the convergence of the proposed algorithms is guaranteed under certain conditions, and the experimental evidence with benchmark data sets also validates the effectiveness and efficiency of the proposed methods.

cs.LG↗