Searcharxiv⌕ Search

arXiv subjects

Fei Wu

Publications and source records attributed to Fei Wu.

At least 379 records · Page 21Linked to original sources
arXiv2019

Scheduling and Trade-off Analysis for Multi-Source Multi-Processor Systems with Divisible Loads

The main goal of parallel processing is to provide users with performance that is much better than that of single processor systems. The execution of jobs is scheduled, which requires certain resources in order to meet certain criteria. Divisible load is a special but widely used type of data which can be divided into arbitrary sizes and independently processed in parallel. It can be used in applications which are processing a great amount of similar data units.

cs.DC↗
arXiv2019

Optimal Divisible Load Scheduling for Resource-Sharing Network

Scheduling is an important task allowing parallel systems to perform efficiently and reliably. For modern computation systems, divisible load is a special type of data which can be divided into arbitrary sizes and independently processed in parallel. Such loads are commonly encountered in applications which are processing a great amount of similar data units. For a multi-task processor, the processor's speed may be time-varying due to the arrival and departure of other background jobs. This paper studies an optimal divisible loads scheduling problem on a single level tree network, whose processing speeds and channel speeds are time-varying. Two recursive algorithms are provided to solve this problem when the arrival and departure times of the background jobs are known a priori and an iterative algorithm is provided to solve the case where such times are not known. Numerical tests and evaluations are performed for these three algorithms under different numbers of background jobs and processors.

cs.DC↗
arXiv2019

Reinforcement Learning for Optimal Load Distribution Sequencing in Resource-Sharing System

Divisible Load Theory (DLT) is a powerful tool for modeling divisible load problems in data-intensive systems. This paper studied an optimal divisible load distribution sequencing problem using a machine learning framework. The problem is to decide the optimal sequence to distribute divisible load to processors in order to achieve minimum finishing time. The scheduling is performed in a resource-sharing system where each physical processor is virtualized to multiple virtual processors. A reinforcement learning method called Multi-armed bandit (MAB) is used for our problem. We first provide a naive solution using the MAB algorithm and then several optimizations are performed. Various numerical tests are conducted. Our algorithm shows an increasing performance during the training progress and the global optimum will be acheived when the sample size is large enough.

cs.DC↗
arXiv2018

Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction

Distant supervision leverages knowledge bases to automatically label instances, thus allowing us to train relation extractor without human annotations. However, the generated training data typically contain massive noise, and may result in poor performances with the vanilla supervised learning. In this paper, we propose to conduct multi-instance learning with a novel Cross-relation Cross-bag Selective Attention (C$^2$SA), which leads to noise-robust training for distant supervised relation extractor. Specifically, we employ the sentence-level selective attention to reduce the effect of noisy or mismatched sentences, while the correlation among relations were captured to improve the quality of attention weights. Moreover, instead of treating all entity-pairs equally, we try to pay more attention to entity-pairs with a higher quality. Similarly, we adopt the selective attention mechanism to achieve this goal. Experiments with two types of relation extractor demonstrate the superiority of the proposed approach over the state-of-the-art, while further ablation studies verify our intuitions and demonstrate the effectiveness of our proposed two techniques.

cs.CL↗
arXiv2018

Bi-Adversarial Auto-Encoder for Zero-Shot Learning

Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well. In this paper, we propose to synthesize visual features based on an auto-encoder framework paired with bi-adversarial networks respectively for visual and semantic modalities to reinforce the visual-semantic interactions with a bi-directional alignment, which ensures the synthesized visual features to fit the real visual distribution and to be highly related to the semantics. The encoder aims at synthesizing real-like visual features while the decoder forces both the real and the synthesized visual features to be more related to the class semantics. To further capture the discriminative information of the synthesized visual features, both the real and synthesized visual features are forced to be classified into the correct classes via a classification network. Experimental results on four benchmark datasets show that the proposed approach is particularly competitive on both the traditional ZSL and the generalized ZSL tasks.

cs.CV↗
arXiv2018

Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection

This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of intervals of multiple actions. Specifically, we first assemble video clips according to class labels by an attention mechanism that learns class-variable attention weights and thus helps the noise relieving from background or other actions. Secondly, we build temporal relationship between actions by feeding the assembled features into an enhanced recurrent neural network. Finally, we transform the output of recurrent neural network into the corresponding action distribution. In order to generate more precise temporal proposals, we design a score term called segregated temporal gradient-weighted class activation mapping (ST-GradCAM) fused with attention weights. Experiments on THUMOS'14 and ActivityNet1.3 datasets show that our approach outperforms the state-of-the-art weakly-supervised method, and performs at par with the fully-supervised counterparts.

cs.CV↗
arXiv2018

Textually Guided Ranking Network for Attentional Image Retweet Modeling

Retweet prediction is a challenging problem in social media sites (SMS). In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees. Unlike previous studies, we learn user preference ranking model from their past retweeted image tweets in SMS. We first propose heterogeneous image retweet modeling network (IRM) that exploits users' past retweeted image tweets with associated contexts, their following relations in SMS and preference of their followees. We then develop a novel attentional multi-faceted ranking network learning framework with textually guided multi-modal neural networks for the proposed heterogenous IRM network to learn the joint image tweet representations and user preference representations for prediction task. The extensive experiments on a large-scale dataset from Twitter site shows that our method achieves better performance than other state-of-the-art solutions to the problem.

cs.IR↗
arXiv2018

Context-Aware Deep Spatio-Temporal Network for Hand Pose Estimation from Depth Images

As a fundamental and challenging problem in computer vision, hand pose estimation aims to estimate the hand joint locations from depth images. Typically, the problem is modeled as learning a mapping function from images to hand joint coordinates in a data-driven manner. In this paper, we propose Context-Aware Deep Spatio-Temporal Network (CADSTN), a novel method to jointly model the spatio-temporal properties for hand pose estimation. Our proposed network is able to learn the representations of the spatial information and the temporal structure from the image sequences. Moreover, by adopting adaptive fusion method, the model is capable of dynamically weighting different predictions to lay emphasis on sufficient context. Our method is examined on two common benchmarks, the experimental results demonstrate that our proposed approach achieves the best or the second-best performance with state-of-the-art methods and runs in 60fps.

cs.CV↗
arXiv2018

Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions

We propose a novel attentive sequence to sequence translator (ASST) for clip localization in videos by natural language descriptions. We make two contributions. First, we propose a bi-directional Recurrent Neural Network (RNN) with a finely calibrated vision-language attentive mechanism to comprehensively understand the free-formed natural language descriptions. The RNN parses natural language descriptions in two directions, and the attentive model attends every meaningful word or phrase to each frame, thereby resulting in a more detailed understanding of video content and description semantics. Second, we design a hierarchical architecture for the network to jointly model language descriptions and video content. Given a video-description pair, the network generates a matrix representation, i.e., a sequence of vectors. Each vector in the matrix represents a video frame conditioned by the description. The 2D representation not only preserves the temporal dependencies of frames but also provides an effective way to perform frame-level video-language matching. The hierarchical architecture exploits video content with multiple granularities, ranging from subtle details to global context. Integration of the multiple granularities yields a robust representation for multi-level video-language abstraction. We validate the effectiveness of our ASST on two large-scale datasets. Our ASST outperforms the state-of-the-art by $4.28\%$ in Rank$@1$ on the DiDeMo dataset. On the Charades-STA dataset, we significantly improve the state-of-the-art by $13.41\%$ in Rank$@1,IoU=0.5$.

cs.CV↗
arXiv2018

Deep Sequence Learning with Auxiliary Information for Traffic Prediction

Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved. In this paper, we intend to improve traffic prediction by appropriate integration of three kinds of implicit but essential factors encoded in auxiliary information. We do this within an encoder-decoder sequence learning framework that integrates the following data: 1) offline geographical and social attributes. For example, the geographical structure of roads or public social events such as national celebrations; 2) road intersection information. In general, traffic congestion occurs at major junctions; 3) online crowd queries. For example, when many online queries issued for the same destination due to a public performance, the traffic around the destination will potentially become heavier at this location after a while. Qualitative and quantitative experiments on a real-world dataset from Baidu have demonstrated the effectiveness of our framework.

cs.CV↗
arXiv2018

Distribution-based Label Space Transformation for Multi-label Learning

Multi-label learning problems have manifested themselves in various machine learning applications. The key to successful multi-label learning algorithms lies in the exploration of inter-label correlations, which usually incur great computational cost. Another notable factor in multi-label learning is that the label vectors are usually extremely sparse, especially when the candidate label vocabulary is very large and only a few instances are assigned to each category. Recently, a label space transformation (LST) framework has been proposed targeting these challenges. However, current methods based on LST usually suffer from information loss in the label space dimension reduction process and fail to address the sparsity problem effectively. In this paper, we propose a distribution-based label space transformation (DLST) model. By defining the distribution based on the similarity of label vectors, a more comprehensive label structure can be captured. Then, by minimizing KL-divergence of two distributions, the information of the original label space can be approximately preserved in the latent space. Consequently, multi-label classifier trained using the dense latent codes yields better performance. The leverage of distribution enables DLST to fill out additional information about the label correlations. This endows DLST the capability to handle label set sparsity and training data sparsity in multi-label learning problems. With the optimal latent code, a kernel logistic regression function is learned for the mapping from feature space to the latent space. Then ML-KNN is employed to recover the original label vector from the transformed latent code. Extensive experiments on several benchmark datasets demonstrate that DLST not only achieves high classification performance but also is computationally more efficient.

cs.CV↗
arXiv2018

State Distribution-aware Sampling for Deep Q-learning

A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer or sampled based on their priority measured by temporal-difference (TD) error. However, these approaches do not fully take into consideration the intrinsic characteristics of transition distribution in the state space and could result in redundant and unnecessary TD updates, slowing down the convergence of the learning procedure. To overcome this problem, we propose a novel state distribution-aware sampling method to balance the replay times for transitions with skew distribution, which takes into account both the occurrence frequencies of transitions and the uncertainty of state-action values. Consequently, our approach could reduce the unnecessary TD updates and increase the TD updates for state-action value with more uncertainty, making the experience replay more effective and efficient. Extensive experiments are conducted on both classic control tasks and Atari 2600 games based on OpenAI gym platform and the experimental results demonstrate the effectiveness of our approach in comparison with the standard DQN approach.

cs.LG↗
arXiv2018

A Semantic QA-Based Approach for Text Summarization Evaluation

Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.

cs.CL↗
arXiv2018

Semantic Exploration of Traffic Dynamics

Given a large collection of urban datasets, how can we find their hidden correlations? For example, New York City (NYC) provides open access to taxi data from year 2012 to 2015 with about half million taxi trips generated per day. In the meantime, we have a rich set of urban data in NYC including points-of-interest (POIs), geo-tagged tweets, weather, vehicle collisions, etc. Is it possible that these ubiquitous datasets can be used to explain the city traffic? Understanding the hidden correlation between external data and traffic data would allow us to answer many important questions in urban computing such as: If we observe a high traffic volume at Madison Square Garden (MSG) in NYC, is it because of the regular peak hour or a big event being held at MSG? If a disaster weather such as a hurricane or a snow storm hits the city, how would the traffic be affected? While existing studies may utilize external datasets for prediction task, they do not explicitly seek for direct explanations from the external datasets. In this paper, we present our results in attempts to understand taxi traffic dynamics in NYC from multiple external data sources. We use four real-world ubiquitous urban datasets, including POI, weather, geo-tagged tweet, and collision records. To address the heterogeneity of ubiquitous urban data, we present carefully-designed feature representations for various datasets. Extensive experiments on real data demonstrate the explanatory power on taxi traffic by using external datasets. More specifically, our analysis suggests that POIs can well describe the regular traffic patterns. At the same time, geo-tagged tweets can explain irregular traffic caused by big events and weather can explain the abnormal traffic drop.

cs.CY↗
arXiv2018

To Stay or to Leave: Churn Prediction for Urban Migrants in the Initial Period

In China, 260 million people migrate to cities to realize their urban dreams. Despite that these migrants play an important role in the rapid urbanization process, many of them fail to settle down and eventually leave the city. The integration process of migrants thus raises an important issue for scholars and policymakers. In this paper, we use Shanghai as an example to investigate migrants' behavior in their first weeks and in particular, how their behavior relates to early departure. Our dataset consists of a one-month complete dataset of 698 telecommunication logs between 54 million users, plus a novel and publicly available housing price data for 18K real estates in Shanghai. We find that migrants who end up leaving early tend to neither develop diverse connections in their first weeks nor move around the city. Their active areas also have higher housing prices than that of staying migrants. We formulate a churn prediction problem to determine whether a migrant is going to leave based on her behavior in the first few days. The prediction performance improves as we include data from more days. Interestingly, when using the same features, the classifier trained from only the first few days is already as good as the classifier trained using full data, suggesting that the performance difference mainly lies in the difference between features.

cs.SI↗
arXiv2018

Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction

Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.

cs.LG↗
arXiv2018

High Throughput Low Delay Wireless Multicast via Multi-Channel Moving Window Codes

A fundamental challenge in wireless multicast has been how to simultaneously achieve high-throughput and low-delay for reliably serving a large number of users. In this paper, we show how to harness substantial throughput and delay gains by exploiting multi-channel resources. We develop a new scheme called Multi-Channel Moving Window Codes (MC-MWC) for multi-channel multi-session wireless multicast. The salient features of MC-MWC are three-fold. (i) High throughput: we show that MC-MWC achieves order-optimal throughput in the many-user many-channel asymptotic regime. Moreover, the number of channels required by a conventional channel-allocation based scheme is shown to be doubly-exponentially larger than that required by MC-MWC. (ii) Low delay: using large deviations theory, we show that the delay of MC-MWC decreases linearly with the number of channels, while the delay reduction of conventional schemes is no more than a finite constant. (iii) Low feedback overhead: the feedback overhead of MC-MWC is a constant that is independent of both the number of receivers in each session and the number of sessions in the network. Finally, our trace-driven simulation and numerical results validate the analytical results and show that the implementation complexity of MC-MWC is low.

cs.IT↗