Search Results for author: Xin Liu

Found 188 papers, 68 papers with code

Scalable and Sample Efficient Distributed Policy Gradient Algorithms in Multi-Agent Networked Systems

no code implementations13 Dec 2022 Xin Liu, Honghao Wei, Lei Ying

The proposed algorithm is distributed in two aspects: (i) the learned policy is a distributed policy that maps a local state of an agent to its local action and (ii) the learning/training is distributed, during which each agent updates its policy based on its own and neighbors' information.

Multi-agent Reinforcement Learning reinforcement-learning +1

On the Discredibility of Membership Inference Attacks

no code implementations6 Dec 2022 Shahbaz Rezaei, Xin Liu

We showcase a practical application of membership inference attacks where it is used by an auditor (investigator) to prove to a judge/jury that an auditee unlawfully used sensitive data during training.

Efficient stereo matching on embedded GPUs with zero-means cross correlation

no code implementations1 Dec 2022 Qiong Chang, Aolong Zha, Weimin WANG, Xin Liu, Masaki Onishi, Lei Lei, Meng Joo Er, Tsutomu Maruyama

By combining this technique with the domain transformation (DT) algorithm, our system show real-time processing speed of 32 fps, on a Jetson Tx2 GPU for 1, 280x384 pixel images with a maximum disparity of 128.

Stereo Matching

Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraints

no code implementations27 Nov 2022 Hengquan Guo, Qi Zhu, Xin Liu

This paper studies the problem of stochastic continuum-armed bandit with constraints (SCBwC), where we optimize a black-box reward function $f(x)$ subject to a black-box constraint function $g(x)\leq 0$ over a continuous space $\mathcal X$.

Gaussian Processes

Federated Learning Hyper-Parameter Tuning from a System Perspective

1 code implementation24 Nov 2022 Huanle Zhang, Lei Fu, Mi Zhang, Pengfei Hu, Xiuzhen Cheng, Prasant Mohapatra, Xin Liu

In this paper, we propose FedTune, an automatic FL hyper-parameter tuning algorithm tailored to applications' diverse system requirements in FL training.

Federated Learning

FolkScope: Intention Knowledge Graph Construction for Discovering E-commerce Commonsense

no code implementations15 Nov 2022 Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

We annotate a large amount of assertions for both plausibility and typicality of an intention that can explain a purchasing or co-purchasing behavior, where the intention can be an open reason or a predicate falling into one of 18 categories aligning with ConceptNet, e. g., IsA, MadeOf, UsedFor, etc.

graph construction

Quantifying the Impact of Label Noise on Federated Learning

no code implementations15 Nov 2022 Shuqi Ke, Chao Huang, Xin Liu

Federated Learning (FL) is a distributed machine learning paradigm where clients collaboratively train a model using their local (human-generated) datasets.

Federated Learning

Getting the Most out of Simile Recognition

no code implementations11 Nov 2022 Xiaoyue Wang, Linfeng Song, Xin Liu, Chulun Zhou, Jinsong Su

Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i. e., tenors and vehicles).

POS Sentence Classification

Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform

1 code implementation7 Nov 2022 Huiru Xiao, Xin Liu, Yangqiu Song, Ginny Y. Wong, Simon See

However, the performance of the hyperbolic KG embedding models for non-transitive relations is still unpromising, while the complex hyperbolic embeddings do not deal with multi-relations.

Knowledge Graph Embeddings

Client Selection in Federated Learning: Principles, Challenges, and Opportunities

no code implementations3 Nov 2022 Lei Fu, Huanle Zhang, Ge Gao, Huajie Wang, Mi Zhang, Xin Liu

As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) has received tremendous attention from both industry and academia.

Fairness Federated Learning +1

Opportunistic Episodic Reinforcement Learning

no code implementations24 Oct 2022 Xiaoxiao Wang, Nader Bouacida, Xueying Guo, Xin Liu

In this paper, we propose and study opportunistic reinforcement learning - a new variant of reinforcement learning problems where the regret of selecting a suboptimal action varies under an external environmental condition known as the variation factor.

reinforcement-learning reinforcement Learning

Self-Supervised Learning via Maximum Entropy Coding

1 code implementation20 Oct 2022 Xin Liu, Zhongdao Wang, YaLi Li, Shengjin Wang

To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks.

Instance Segmentation object-detection +4

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

1 code implementation19 Oct 2022 Xin Liu, Xiaofei Shao, Bo wang, YaLi Li, Shengjin Wang

First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.

Autonomous Driving Depth Completion +1

Not All Neighbors are Friendly: Learning to Choose Hop Features to Improve Node Classification

1 code implementation CIKM 2022 Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata

With extensive experiments, we show that our proposed model outperforms the state-of-the-art GNN models with remarkable improvements up to 27. 8%.

Node Classification

MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity Recognition

no code implementations14 Oct 2022 Ziqi Gao, Jianguo Chen, Junliang Xing, Shwetak Patel, Yuanchun Shi, Xin Liu, Yuntao Wang

In this paper, we propose a new novel multimodal neural architecture based on RGB and IMU wearable sensors (e. g., accelerometer, gyroscope) for human activity recognition called Multimodal Temporal Segment Attention Network (MMTSA).

Human Activity Recognition

ByteTransformer: A High-Performance Transformer Boosted for Variable-Length Inputs

no code implementations6 Oct 2022 Yujia Zhai, Chengquan Jiang, Leyuan Wang, Xiaoying Jia, Shang Zhang, Zizhong Chen, Xin Liu, Yibo Zhu

The end-to-end performance of ByteTransformer for a standard BERT transformer model surpasses the state-of-the-art Transformer frameworks, such as PyTorch JIT, TensorFlow XLA, Tencent TurboTransformer and NVIDIA FasterTransformer, by 87\%, 131\%, 138\% and 46\%, respectively.

SimPer: Simple Self-Supervised Learning of Periodic Targets

1 code implementation6 Oct 2022 Yuzhe Yang, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes.

Inductive Bias Self-Supervised Learning

Deep Physiological Sensing Toolbox

1 code implementation3 Oct 2022 Xin Liu, XiaoYu Zhang, Girish Narayanswamy, Yuzhe Zhang, Yuntao Wang, Shwetak Patel, Daniel McDuff

Camera physiological measurement is a fast growing field of computer vision.

Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation

no code implementations23 Sep 2022 Zhongwei Wan, Benyou Wang, Xin Liu, Jiezhong Qiu, Boyu Li, Ting Guo, Guangyong Chen, Yang Wang

The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism.

Collaborative Filtering Contrastive Learning +1

Rethinking Efficiency and Redundancy in Training Large-scale Graphs

no code implementations2 Sep 2022 Xin Liu, Xunbin Xiong, Mingyu Yan, Runzhen Xue, Shirui Pan, Xiaochun Ye, Dongrui Fan

Thereby, we propose to drop redundancy and improve efficiency of training large-scale graphs with GNNs, by rethinking the inherent characteristics in a graph.

A high-resolution dynamical view on momentum methods for over-parameterized neural networks

no code implementations8 Aug 2022 Xin Liu, Wei Tao, Jun Wang, Zhisong Pan

Due to the simplicity and efficiency of the first-order gradient method, it has been widely used in training neural networks.

BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation

1 code implementation18 Jul 2022 Yi Zeng, Dongcheng Zhao, Feifei Zhao, Guobin Shen, Yiting Dong, Enmeng Lu, Qian Zhang, Yinqian Sun, Qian Liang, Yuxuan Zhao, Zhuoya Zhao, Hongjian Fang, Yuwei Wang, Yang Li, Xin Liu, Chengcheng Du, Qingqun Kong, Zizhe Ruan, Weida Bi

These brain-inspired AI models have been effectively validated on various supervised, unsupervised, and reinforcement learning tasks, and they can be used to enable AI models to be with multiple brain-inspired cognitive functions.

Decision Making

Brain-inspired Graph Spiking Neural Networks for Commonsense Knowledge Representation and Reasoning

no code implementations11 Jul 2022 Hongjian Fang, Yi Zeng, Jianbo Tang, Yuwei Wang, Yao Liang, Xin Liu

For the fields of neuroscience and cognitive science, the work in this paper provided the foundation of computational modeling for further exploration of the way the human brain represents commonsense knowledge.

Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

no code implementations4 Jul 2022 Haoyi Xiu, Xin Liu, Weimin WANG, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang, Masashi Matsuoka

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information.

Cross-Silo Federated Learning: Challenges and Opportunities

no code implementations26 Jun 2022 Chao Huang, Jianwei Huang, Xin Liu

Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private.

Federated Learning

FedSSO: A Federated Server-Side Second-Order Optimization Algorithm

no code implementations20 Jun 2022 Xin Ma, Renyi Bao, Jinpeng Jiang, Yang Liu, Arthur Jiang, Jun Yan, Xin Liu, Zhisong Pan

In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL).

Federated Learning

Boosting Graph Structure Learning with Dummy Nodes

1 code implementation17 Jun 2022 Xin Liu, Jiayang Cheng, Yangqiu Song, Xin Jiang

We extend graph kernels and graph neural networks with dummy nodes and conduct experiments on graph classification and subgraph isomorphism matching tasks.

Graph Classification Graph Representation Learning +1

A Multi-task Framework for Infrared Small Target Detection and Segmentation

1 code implementation14 Jun 2022 Yuhang Chen, Liyuan Li, Xin Liu, Xiaofeng Su, Fansheng Chen

First, with the use of UNet as the backbone to maintain resolution and semantic information, our model can achieve a higher detection accuracy than other state-of-the-art methods by attaching a simple anchor-free head.

Multi-Task Learning object-detection +2

SCAMPS: Synthetics for Camera Measurement of Physiological Signals

2 code implementations8 Jun 2022 Daniel McDuff, Miah Wander, Xin Liu, Brian L. Hill, Javier Hernandez, Jonathan Lester, Tadas Baltrusaitis

The use of cameras and computational algorithms for noninvasive, low-cost and scalable measurement of physiological (e. g., cardiac and pulmonary) vital signs is very attractive.

Heart Rate Variability

Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment

no code implementations26 May 2022 Zixian Yang, Xin Liu, Lei Ying

To understand the exploration, exploitation, and engagement in these systems, we propose a new model, called MAB-A where "A" stands for abandonment and the abandonment probability depends on the current recommended item and the user's past experience (called state).

Multi-Armed Bandits Q-Learning +1

Selective clustering ensemble based on kappa and F-score

no code implementations23 Apr 2022 Jie Yan, Xin Liu, Ji Qi, Tao You, Zhong-Yuan Zhang

Clustering ensemble has an impressive performance in improving the accuracy and robustness of partition results and has received much attention in recent years.

Clustering Ensemble

A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks

no code implementations18 Apr 2022 Xin Liu, Wei Tao, Zhisong Pan

To the best of our knowledge, this is the first theoretical guarantee for the convergence of NAG to the global minimum in training deep neural networks.

Ethereum Fraud Detection with Heterogeneous Graph Neural Networks

no code implementations23 Mar 2022 Hiroki Kanezashi, Toyotaro Suzumura, Xin Liu, Takahiro Hirofuchi

Specifically, we evaluated the model performance of representative homogeneous GNN models which consider single-type nodes and edges and heterogeneous GNN models which support different types of nodes and edges.

Fraud Detection

Federated Remote Physiological Measurement with Imperfect Data

no code implementations11 Mar 2022 Xin Liu, Mingchuan Zhang, Ziheng Jiang, Shwetak Patel, Daniel McDuff

The growing need for technology that supports remote healthcare is being acutely highlighted by an aging population and the COVID-19 pandemic.

Federated Learning Privacy Preserving

User-Level Membership Inference Attack against Metric Embedding Learning

no code implementations4 Mar 2022 Guoyao Li, Shahbaz Rezaei, Xin Liu

In this paper, we develop a user-level MI attack where the goal is to find if any sample from the target user has been used during training even when no exact training sample is available to the attacker.

Inference Attack Membership Inference Attack +1

An Efficient Subpopulation-based Membership Inference Attack

no code implementations4 Mar 2022 Shahbaz Rezaei, Xin Liu

The intuition is that the model response should not be significantly different between the target sample and its subpopulation if it was not a training sample.

Inference Attack Membership Inference Attack

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention

no code implementations1 Mar 2022 Haoyi Xiu, Xin Liu, Weimin WANG, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang, Masashi Matsuoka

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds.

Scene Segmentation

Survey on Graph Neural Network Acceleration: An Algorithmic Perspective

no code implementations10 Feb 2022 Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye, Dongrui Fan, Shirui Pan, Yuan Xie

Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.

MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing

no code implementations11 Jan 2022 Xin Liu, Yuntao Wang, Sinan Xie, XiaoYu Zhang, Zixian Ma, Daniel McDuff, Shwetak Patel

Camera-based contactless photoplethysmography refers to a set of popular techniques for contactless physiological measurement.

Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function

no code implementations30 Dec 2021 Lei Wang, Xin Liu

In this paper, we focus on the decentralized optimization problem over the Stiefel manifold, which is defined on a connected network of $d$ agents.

Diaformer: Automatic Diagnosis via Symptoms Sequence Generation

1 code implementation20 Dec 2021 Junying Chen, Dongfang Li, Qingcai Chen, Wenxiu Zhou, Xin Liu

Detailed analysis on symptom inquiry prediction demonstrates that the potential of applying symptoms sequence generation for automatic diagnosis.

Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching

1 code implementation16 Dec 2021 Xin Liu, Yangqiu Song

Based on this observation, we propose dual message passing neural networks (DMPNNs) to enhance the substructure representation learning in an asynchronous way for subgraph isomorphism counting and matching as well as unsupervised node classification.

Node Classification Representation Learning

KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

no code implementations15 Dec 2021 Xin Liu, Dayiheng Liu, Baosong Yang, Haibo Zhang, Junwei Ding, Wenqing Yao, Weihua Luo, Haiying Zhang, Jinsong Su

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently.


Leaping Through Time with Gradient-based Adaptation for Recommendation

1 code implementation11 Dec 2021 Nuttapong Chairatanakul, Hoang NT, Xin Liu, Tsuyoshi Murata

Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based meta-learning to model time dependencies.

Meta-Learning Recommendation Systems

CLARA: A Constrained Reinforcement Learning Based Resource Allocation Framework for Network Slicing

no code implementations16 Nov 2021 Yongshuai Liu, Jiaxin Ding, Zhi-Li Zhang, Xin Liu

Network slicing is proposed as a promising solution for resource utilization in 5G and future networks to address this dire need.

Management reinforcement-learning +1

Simplifying approach to Node Classification in Graph Neural Networks

1 code implementation12 Nov 2021 Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata

In this work, we decouple the node feature aggregation step and depth of graph neural network, and empirically analyze how different aggregated features play a role in prediction performance.

Classification Node Classification

RGB Camera-based Physiological Sensing: Challenges and Future Directions

no code implementations26 Oct 2021 Xin Liu, Shwetak Patel, Daniel McDuff

Numerous real-world applications have been driven by the recent algorithmic advancement of artificial intelligence (AI).

Natural Image Reconstruction from fMRI using Deep Learning: A Survey

no code implementations18 Oct 2021 Zarina Rakhimberdina, Quentin Jodelet, Xin Liu, Tsuyoshi Murata

With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information in the human brain.

Brain Decoding Image Reconstruction

Synthetic Data for Multi-Parameter Camera-Based Physiological Sensing

no code implementations10 Oct 2021 Daniel McDuff, Xin Liu, Javier Hernandez, Erroll Wood, Tadas Baltrusaitis

We present systematic experiments showing how physiologically-grounded synthetic data can be used in training camera-based multi-parameter cardiopulmonary sensing.

Learning Higher-Order Dynamics in Video-Based Cardiac Measurement

no code implementations7 Oct 2021 Brian L. Hill, Xin Liu, Daniel McDuff

Recent developments in camera-based vital sign measurement have shown that cardiac measurements can be recovered with impressive accuracy from videos; however, most of the research has focused on extracting summary statistics such as heart rate.

Optical Flow Estimation

FedTune: Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective

1 code implementation6 Oct 2021 Huanle Zhang, Mi Zhang, Xin Liu, Prasant Mohapatra, Michael DeLucia

Federated learning (FL) hyper-parameters significantly affect the training overheads in terms of computation time, transmission time, computation load, and transmission load.

Federated Learning

Spatio-Temporal-Categorical Graph Neural Networks for Fine-Grained Multi-Incident Co-Prediction

1 code implementation CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management 2021 Zhaonan Wang, Renhe Jiang, Zekun Cai, Zipei Fan, Xin Liu, Kyoung-Sook Kim, Xuan Song, Ryosuke Shibasaki

Forecasting incident occurrences (e. g. crime, EMS, traffic accident) is a crucial task for emergency service providers and transportation agencies in performing response time optimization and dynamic fleet management.

Decision Making Management

EfficientPhys: Enabling Simple, Fast, and Accurate Camera-Based Vitals Measurement

no code implementations29 Sep 2021 Xin Liu, Brian L. Hill, Ziheng Jiang, Shwetak Patel, Daniel McDuff

Camera-based physiological measurement is a growing field with neural models providing state-the-art-performance.

Face Detection

Automatic Tuning of Federated Learning Hyper-Parameters from System Perspective

no code implementations29 Sep 2021 Huanle Zhang, Mi Zhang, Xin Liu, Prasant Mohapatra, Michael DeLucia

Federated Learning (FL) is a distributed model training paradigm that preserves clients' data privacy.

Federated Learning

Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph

1 code implementation Findings (EMNLP) 2021 Nuttapong Chairatanakul, Noppayut Sriwatanasakdi, Nontawat Charoenphakdee, Xin Liu, Tsuyoshi Murata

To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations.

Cross-Lingual Transfer text-classification +2

GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware

1 code implementation26 Aug 2021 Xin Liu, Mingyu Yan, Shuhan Song, Zhengyang Lv, WenMing Li, Guangyu Sun, Xiaochun Ye, Dongrui Fan

Extensive experiments show that our method is universal to mainstream sampling algorithms and helps significantly reduce the training time, especially in large-scale graphs.

AGNet: Weighing Black Holes with Deep Learning

1 code implementation17 Aug 2021 Joshua Yao-Yu Lin, Sneh Pandya, Devanshi Pratap, Xin Liu, Matias Carrasco Kind, Volodymyr Kindratenko

We find a 1$\sigma$ scatter of 0. 37 dex between the predicted SMBH mass and the fiducial virial mass estimate based on SDSS single-epoch spectra, which is comparable to the systematic uncertainty in the virial mass estimate.

Time Series

MMChat: Multi-Modal Chat Dataset on Social Media

1 code implementation LREC 2022 Yinhe Zheng, Guanyi Chen, Xin Liu, Jian Sun

To better investigate this issue, we manually annotate 100K dialogues from MMChat and further filter the corpus accordingly, which yields MMChat-hf.

Dialogue Generation

Provable Convergence of Nesterov's Accelerated Gradient Method for Over-Parameterized Neural Networks

no code implementations5 Jul 2021 Xin Liu, Zhisong Pan, Wei Tao

Despite the fact that the objective function is non-convex and non-smooth, we show that NAG converges to a global minimum at a non-asymptotic linear rate $(1-\Theta(1/\sqrt{\kappa}))^t$, where $\kappa > 1$ is the condition number of a gram matrix and $t$ is the number of the iterations.

iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis

1 code implementation CVPR 2021 Xin Liu, Henglin Shi, Haoyu Chen, Zitong Yu, Xiaobai Li, Guoying Zhaoz?

We introduce a new dataset for the emotional artificial intelligence research: identity-free video dataset for Micro-Gesture Understanding and Emotion analysis (iMiGUE).

Emotion Recognition

Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers

no code implementations28 Jun 2021 Rex Liu, Sarina A Fazio, Huanle Zhang, Albara Ah Ramli, Xin Liu, Jason Yeates Adams

In this paper, we target a new healthcare application of human activity recognition, early mobility recognition for Intensive Care Unit(ICU) patients.

Feature Engineering Human Activity Recognition

Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning

1 code implementation ACL 2021 Shuoran Jiang, Qingcai Chen, Xin Liu, Baotian Hu, Lisai Zhang

In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer.

A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes

no code implementations3 Jun 2021 Honghao Wei, Xin Liu, Lei Ying

This paper presents the first model-free, simulator-free reinforcement learning algorithm for Constrained Markov Decision Processes (CMDPs) with sublinear regret and zero constraint violation.

Improving Graph Neural Networks with Simple Architecture Design

1 code implementation17 May 2021 Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata

Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks.

Node Classification

FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal Retrieval

1 code implementation15 May 2021 Xin Liu, Xingzhi Wang, Yiu-ming Cheung

To tackle these issues, we formulate the learning of similarity-preserving hash codes in terms of orthogonally rotating the semantic data so as to minimize the quantization loss of mapping such data to hamming space, and propose an efficient Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval.

Cross-Modal Retrieval Quantization +1

Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches

no code implementations12 May 2021 Albara Ah Ramli, Huanle Zhang, Jiahui Hou, Rex Liu, Xin Liu, Alina Nicorici, Daniel Aranki, Corey Owens, Poonam Prasad, Craig McDonald, Erik Henricson

Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantification of those differences outside of the gait laboratory has been elusive.

Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective

1 code implementation12 May 2021 Shahbaz Rezaei, Zubair Shafiq, Xin Liu

We analyze the impact of various factors in deep ensembles and demonstrate the root cause of the trade-off.

Ensemble Learning Inference Attack +1

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

1 code implementation CVPR 2021 Zikai Zhang, Bineng Zhong, Shengping Zhang, Zhenjun Tang, Xin Liu, Zhaoxiang Zhang

A practical long-term tracker typically contains three key properties, i. e. an efficient model design, an effective global re-detection strategy and a robust distractor awareness mechanism.

Association Multiple Object Tracking +1

A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things

no code implementations21 Apr 2021 Jiehan Zhou, Shouhua Zhang, Qinghua Lu, Wenbin Dai, Min Chen, Xin Liu, Susanna Pirttikangas, Yang Shi, Weishan Zhang, Enrique Herrera-Viedma

Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4. 0 on the edge computing level.

Edge-computing Federated Learning +1

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

1 code implementation5 Apr 2021 Hongming Zhang, Xin Liu, Haojie Pan, Haowen Ke, Jiefu Ou, Tianqing Fang, Yangqiu Song

After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them.

Discourse Parsing

Learning to Filter: Siamese Relation Network for Robust Tracking

1 code implementation CVPR 2021 Siyuan Cheng, Bineng Zhong, Guorong Li, Xin Liu, Zhenjun Tang, Xianxian Li, Jing Wang

RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result.


An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence

no code implementations29 Mar 2021 Rex Liu, Albara Ah Ramli, Huanle Zhang, Erik Henricson, Xin Liu

With the rapid development of the internet of things (IoT) and artificial intelligence (AI) technologies, human activity recognition (HAR) has been applied in a variety of domains such as security and surveillance, human-robot interaction, and entertainment.

Feature Engineering Human Activity Recognition +1

No frame left behind: Full Video Action Recognition

1 code implementation CVPR 2021 Xin Liu, Silvia L. Pintea, Fatemeh Karimi Nejadasl, Olaf Booij, Jan C. van Gemert

A common heuristic is uniformly sampling a small number of video frames and using these to recognize the action.

Action Recognition

Balanced softmax cross-entropy for incremental learning with and without memory

no code implementations23 Mar 2021 Quentin Jodelet, Xin Liu, Tsuyoshi Murata

When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones.

class-incremental learning Incremental Learning +1

Sampling methods for efficient training of graph convolutional networks: A survey

no code implementations10 Mar 2021 Xin Liu, Mingyu Yan, Lei Deng, Guoqi Li, Xiaochun Ye, Dongrui Fan

Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.

Higher-order topological superconductors based on weak topological insulators

no code implementations2 Mar 2021 Xun-Jiang Luo, Xiao-Hong Pan, Xin Liu

High-order topological phases host robust boundary states at the boundary of the boundary, which can be interpreted from their boundary topology.

Superconductivity Mesoscale and Nanoscale Physics Materials Science

DST: Data Selection and joint Training for Learning with Noisy Labels

no code implementations1 Mar 2021 Yi Wei, Xue Mei, Xin Liu, Pengxiang Xu

In this paper, we propose a Data Selection and joint Training (DST) method to automatically select training samples with accurate annotations.

Learning with noisy labels

An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints

no code implementations NeurIPS 2021 Xin Liu, Bin Li, Pengyi Shi, Lei Ying

Thus, the overall computational complexity of our algorithm is similar to that of the linear UCB for unconstrained stochastic linear bandits.

Learning adaptive differential evolution algorithm from optimization experiences by policy gradient

no code implementations6 Feb 2021 Jianyong Sun, Xin Liu, Thomas Bäck, Zongben Xu

A reinforcement learning algorithm, named policy gradient, is applied to learn an agent (i. e. parameter controller) that can provide the control parameters of a proposed differential evolution adaptively during the search procedure.

Stochastic Optimization

Spectrum Sharing for 6G Integrated Satellite-Terrestrial Communication Networks Based on NOMA and Cognitive Radio

no code implementations27 Jan 2021 Xin Liu, Kwok-Yan Lam, Feng Li, Jun Zhao, Li Wang

ISTCN aims to provide high speed and pervasive network services by integrating broadband terrestrial mobile networks with satellite communication networks.


SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices

no code implementations20 Jan 2021 Xin Liu, Yuang Li, Josh Fromm, Yuntao Wang, Ziheng Jiang, Alex Mariakakis, Shwetak Patel

In this work, we demonstrate state-of-the-art latency and accuracy for on-device super-resolution using a novel hybrid architecture called SplitSR and a novel lightweight residual block called SplitSRBlock.


Generalized Image Reconstruction over T-Algebra

1 code implementation17 Jan 2021 Liang Liao, Xuechun Zhang, Xinqiang Wang, Sen Lin, Xin Liu

We also show in our experiments that the performance of TPCA increases when the order of compounded pixels increases.

Data Compression Dimensionality Reduction +1

Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans

2 code implementations14 Jan 2021 Xin He, Shihao Wang, Xiaowen Chu, Shaohuai Shi, Jiangping Tang, Xin Liu, Chenggang Yan, Jiyong Zhang, Guiguang Ding

The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy.

Medical Diagnosis Neural Architecture Search

An Unsupervised Learning Method with Convolutional Auto-Encoder for Vessel Trajectory Similarity Computation

no code implementations10 Jan 2021 Maohan Liang, Ryan Wen Liu, Shichen Li, Zhe Xiao, Xin Liu, Feng Lu

Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner.

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

no code implementations7 Jan 2021 Sungkwon An, Jeonghoon Kim, Myungjoo Kang, Shahbaz Razaei, Xin Liu

Specifically, we employ orthogonal low-rank embedding in the latent space to disentangle the features in the latent space using mutual class information.

Image Reconstruction

MedWriter: Knowledge-Aware Medical Text Generation

no code implementations COLING 2020 Youcheng Pan, Qingcai Chen, Weihua Peng, Xiaolong Wang, Baotian Hu, Xin Liu, Junying Chen, Wenxiu Zhou

To exploit the domain knowledge to guarantee the correctness of generated text has been a hot topic in recent years, especially for high professional domains such as medical.

Text Generation

Multi-task MR Imaging with Iterative Teacher Forcing and Re-weighted Deep Learning

no code implementations27 Nov 2020 Kehan Qi, Yu Gong, Xinfeng Liu, Xin Liu, Hairong Zheng, Shanshan Wang

Noises, artifacts, and loss of information caused by the magnetic resonance (MR) reconstruction may compromise the final performance of the downstream applications.

Soft-Median Choice: An Automatic Feature Smoothing Method for Sound Event Detection

no code implementations25 Nov 2020 Fengnian Zhao, Ruwei Li, Xin Liu, Liwen Xu

In Sound Event Detection (SED) systems, the lengths of median filters for post-processing have never been optimized during training due to several problems.

Event Detection Sound Event Detection

Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning

no code implementations8 Nov 2020 Nader Bouacida, Jiahui Hou, Hui Zang, Xin Liu

With more regulations tackling users' privacy-sensitive data protection in recent years, access to such data has become increasingly restricted and controversial.

BIG-bench Machine Learning Federated Learning

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

1 code implementation28 Oct 2020 Jun Ma, Yao Zhang, Song Gu, Cheng Zhu, Cheng Ge, Yichi Zhang, Xingle An, Congcong Wang, Qiyuan Wang, Xin Liu, Shucheng Cao, Qi Zhang, Shangqing Liu, Yunpeng Wang, Yuhui Li, Jian He, Xiaoping Yang

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets.

Continual Learning Pancreas Segmentation

Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility

no code implementations28 Oct 2020 Yuanjie Li, Esha Datta, Jiaxin Ding, Ness Shroff, Xin Liu

The demand for seamless Internet access under extreme user mobility, such as on high-speed trains and vehicles, has become a norm rather than an exception.

Thompson Sampling

Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars

no code implementations24 Oct 2020 Daniel McDuff, Javier Hernandez, Erroll Wood, Xin Liu, Tadas Baltrusaitis

Non-contact physiological measurement has the potential to provide low-cost, non-invasive health monitoring.

POND: Pessimistic-Optimistic oNline Dispatching

no code implementations20 Oct 2020 Xin Liu, Bin Li, Pengyi Shi, Lei Ying

This paper considers constrained online dispatching with unknown arrival, reward and constraint distributions.

WeightAlign: Normalizing Activations by Weight Alignment

no code implementations14 Oct 2020 Xiangwei Shi, Yunqiang Li, Xin Liu, Jan van Gemert

Such methods are less stable than BN as they critically depend on the statistics of a single input sample.

Domain Adaptation Semantic Segmentation

MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement

no code implementations5 Oct 2020 Xin Liu, Ziheng Jiang, Josh Fromm, Xuhai Xu, Shwetak Patel, Daniel McDuff

There are large individual differences in physiological processes, making designing personalized health sensing algorithms challenging.


ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference

no code implementations19 Sep 2020 Zhihang Yuan, Xin Liu, Bingzhe Wu, Guangyu Sun

The inference of a input sample can exit from early stage if the prediction of the stage is confident enough.

Candidate Periodically Variable Quasars from the Dark Energy Survey and the Sloan Digital Sky Survey

no code implementations27 Aug 2020 Yu-Ching Chen, Xin Liu, Wei-Ting Liao, A. Miguel Holgado, Hengxiao Guo, Robert A. Gruendl, Eric Morganson, Yue Shen, Kaiwen Zhang, Tim M. C. Abbott, Michel Aguena, Sahar Allam, Santiago Avila, Emmanuel Bertin, Sunayana Bhargava, David Brooks, David L. Burke, Aurelio Carnero Rosell, Daniela Carollo, Matias Carrasco Kind, Jorge Carretero, Matteo Costanzi, Luiz N. da Costa, Tamara M. Davis, Juan De Vicente, Shantanu Desai, H. Thomas Diehl, Peter Doel, Spencer Everett, Brenna Flaugher, Douglas Friedel, Joshua Frieman, Juan García-Bellido, Enrique Gaztanaga, Karl Glazebrook, Daniel Gruen, Gaston Gutierrez, Samuel R. Hinton, Devon L. Hollowood, David J. James, Alex G. Kim, Kyler Kuehn, Nikolay Kuropatkin, Geraint F. Lewis, Christopher Lidman, Marcos Lima, Marcio A. G. Maia, Marisa March, Jennifer L. Marshall, Felipe Menanteau, Ramon Miquel, Antonella Palmese, Francisco Paz-Chinchón, Andrés A. Plazas, Eusebio Sanchez, Michael Schubnell, Santiago Serrano, Ignacio Sevilla-Noarbe, Mathew Smith, Eric Suchyta, Molly E. C. Swanson, Gregory Tarle, Brad E. Tucker, Tamas Norbert Varga, Alistair R. Walker

We present a systematic search for periodic light curves in 625 spectroscopically confirmed quasars with a median redshift of 1. 8 in a 4. 6 deg$^2$ overlapping region of the Dark Energy Survey Supernova (DES-SN) fields and the Sloan Digital Sky Survey Stripe 82 (SDSS-S82).

High Energy Astrophysical Phenomena Astrophysics of Galaxies

A Variational Approach to Unsupervised Sentiment Analysis

no code implementations21 Aug 2020 Ziqian Zeng, Wenxuan Zhou, Xin Liu, Zizheng Lin, Yangqin Song, Michael David Kuo, Wan Hang Keith Chiu

Our objective function is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment classifier.

Sentiment Analysis

2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework

no code implementations10 Aug 2020 Haoyu Chen, Zitong Yu, Xin Liu, Wei Peng, Yoon Lee, Guoying Zhao

To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems.

Action Recognition Optical Flow Estimation

Graph Convolutional Networks for Graphs Containing Missing Features

2 code implementations9 Jul 2020 Hibiki Taguchi, Xin Liu, Tsuyoshi Murata

Notably, our approach does not increase the computational complexity of GCN and it is consistent with GCN when the features are complete.

Graph Learning Imputation +2

Deep Low-rank Prior in Dynamic MR Imaging

no code implementations22 Jun 2020 Ziwen Ke, Wenqi Huang, Jing Cheng, Zhuoxu Cui, Sen Jia, Haifeng Wang, Xin Liu, Hairong Zheng, Leslie Ying, Yanjie Zhu, Dong Liang

The deep learning methods have achieved attractive performance in dynamic MR cine imaging.

An Opportunistic Bandit Approach for User Interface Experimentation

no code implementations21 Jun 2020 Nader Bouacida, Amit Pande, Xin Liu

In fact, we model user interface experimentation as an opportunistic bandit problem, in which the cost of exploration varies under a factor extracted from customer features.

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

3 code implementations NeurIPS 2020 Xin Liu, Josh Fromm, Shwetak Patel, Daniel McDuff

Telehealth and remote health monitoring have become increasingly important during the SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on healthcare practices.

Photoplethysmography (PPG) heart rate estimation

Contextual Bandits with Side-Observations

no code implementations6 Jun 2020 Rahul Singh, Fang Liu, Xin Liu, Ness Shroff

We show that this asymptotically optimal regret is upper-bounded as $O\left(|\chi(\mathcal{G})|\log T\right)$, where $|\chi(\mathcal{G})|$ is the domination number of $\mathcal{G}$.

Multi-Armed Bandits

BWCNN: Blink to Word, a Real-Time Convolutional Neural Network Approach

no code implementations1 Jun 2020 Albara Ah Ramli, Rex Liu, Rahul Krishnamoorthy, Vishal I B, Xiaoxiao Wang, Ilias Tagkopoulos, Xin Liu

The system uses a Convolutional Neural Network (CNN) to find the blinking pattern, which is defined as a series of Open and Closed states.

On the Difficulty of Membership Inference Attacks

1 code implementation CVPR 2021 Shahbaz Rezaei, Xin Liu

Recent studies propose membership inference (MI) attacks on deep models, where the goal is to infer if a sample has been used in the training process.

Image Classification Inference Attack

MMFashion: An Open-Source Toolbox for Visual Fashion Analysis

3 code implementations18 May 2020 Xin Liu, Jiancheng Li, Jiaqi Wang, Ziwei Liu

This toolbox supports a wide spectrum of fashion analysis tasks, including Fashion Attribute Prediction, Fashion Recognition and Retrieval, Fashion Landmark Detection, Fashion Parsing and Segmentation and Fashion Compatibility and Recommendation.


On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification

1 code implementation27 Apr 2020 Xin Liu, Jiefu Ou, Yangqiu Song, Xin Jiang

Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at both the text span level and the sentence level.

Discourse Parsing General Classification +2

Decomposing Word Embedding with the Capsule Network

no code implementations7 Apr 2020 Xin Liu, Qingcai Chen, Yan Liu, Joanna Siebert, Baotian Hu, Xiang-Ping Wu, Buzhou Tang

We propose a Capsule network-based method to Decompose the unsupervised word Embedding of an ambiguous word into context specific Sense embedding, called CapsDecE2S.

Word Embeddings Word Sense Disambiguation

Learning Diverse Fashion Collocation by Neural Graph Filtering

no code implementations11 Mar 2020 Xin Liu, Yongbin Sun, Ziwei Liu, Dahua Lin

To facilitate a comprehensive study on diverse fashion collocation, we reorganize Amazon Fashion dataset with carefully designed evaluation protocols.

Recommendation Systems

XGPT: Cross-modal Generative Pre-Training for Image Captioning

no code implementations3 Mar 2020 Qiaolin Xia, Haoyang Huang, Nan Duan, Dong-dong Zhang, Lei Ji, Zhifang Sui, Edward Cui, Taroon Bharti, Xin Liu, Ming Zhou

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly.

Data Augmentation Denoising +7

Neural Subgraph Isomorphism Counting

1 code implementation25 Dec 2019 Xin Liu, Haojie Pan, Mutian He, Yangqiu Song, Xin Jiang, Lifeng Shang

In this paper, we study a new graph learning problem: learning to count subgraph isomorphisms.

Domain Adaptation Graph Learning +3

Security of Deep Learning Methodologies: Challenges and Opportunities

no code implementations8 Dec 2019 Shahbaz Rezaei, Xin Liu

Despite the plethora of studies about security vulnerabilities and defenses of deep learning models, security aspects of deep learning methodologies, such as transfer learning, have been rarely studied.

Transfer Learning

IPO: Interior-point Policy Optimization under Constraints

no code implementations21 Oct 2019 Yongshuai Liu, Jiaxin Ding, Xin Liu

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints.

reinforcement-learning reinforcement Learning

Cross Domain Image Matching in Presence of Outliers

no code implementations8 Sep 2019 Xin Liu, Seyran Khademi, Jan C. van Gemert

Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap.

Domain Adaptation Outlier Detection

Hyper-Path-Based Representation Learning for Hyper-Networks

1 code implementation24 Aug 2019 Jie Huang, Xin Liu, Yangqiu Song

Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks.

Link Prediction Representation Learning

A Novel Kalman Filter Based Shilling Attack Detection Algorithm

no code implementations18 Aug 2019 Xin Liu, Yingyuan Xiao, Xu Jiao, Wenguang Zheng, Zihao Ling

Collaborative filtering has been widely used in recommendation systems to recommend items that users might like.

Collaborative Filtering Recommendation Systems

hood2vec: Identifying Similar Urban Areas Using Mobility Networks

no code implementations17 Jul 2019 Xin Liu, Konstantinos Pelechrinis, Alexandros Labrinidis

Hence, in this paper, we introduce an approach, namely hood2vec, to identify the similarity between urban areas through learning a node embedding of the mobility network captured through Foursquare check-ins.

Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling

no code implementations4 Jul 2019 Zi Long, Lianzhi Tan, Shengping Zhou, Chaoyang He, Xin Liu

Indicators of Compromise (IOCs) are artifacts observed on a network or in an operating system that can be utilized to indicate a computer intrusion and detect cyber-attacks in an early stage.

Multitask Learning for Network Traffic Classification

1 code implementation12 Jun 2019 Shahbaz Rezaei, Xin Liu

We show that with a large amount of easily obtainable data samples for bandwidth and duration prediction tasks, and only a few data samples for the traffic classification task, one can achieve high accuracy.

Classification General Classification +3

DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution

1 code implementation11 Jun 2019 Shan-Shan Wang, Huitao Cheng, Leslie Ying, Taohui Xiao, Ziwen Ke, Xin Liu, Hairong Zheng, Dong Liang

This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network.

Image Reconstruction

Super-Resolved Image Perceptual Quality Improvement via Multi-Feature Discriminators

no code implementations24 Apr 2019 Xuan Zhu, Yue Cheng, Jinye Peng, Rongzhi Wang, Mingnan Le, Xin Liu

However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images.

Image Super-Resolution

Relation Discovery with Out-of-Relation Knowledge Base as Supervision

1 code implementation NAACL 2019 Yan Liang, Xin Liu, Jianwen Zhang, Yangqiu Song

In this paper, we study the problem of how to use out-of-relation knowledge bases to supervise the discovery of unseen relations, where out-of-relation means that relations to discover from the text corpus and those in knowledge bases are not overlapped.

A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer Learning

1 code implementation ICLR 2020 Shahbaz Rezaei, Xin Liu

Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications.

Face Recognition Image Classification +3

DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators

no code implementations20 Feb 2019 Yu Xing, Shuang Liang, Lingzhi Sui, Xijie Jia, Jiantao Qiu, Xin Liu, Yushun Wang, Yu Wang, Yi Shan

On the Xilinx ZU2 @330 MHz and ZU9 @330 MHz, we achieve equivalently state-of-the-art performance on our benchmarks by na\"ive implementations without optimizations, and the throughput is further improved up to 1. 26x by leveraging heterogeneous optimizations in DNNVM.

AdaLinUCB: Opportunistic Learning for Contextual Bandits

no code implementations20 Feb 2019 Xueying Guo, Xiaoxiao Wang, Xin Liu

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations.

Multi-Armed Bandits

Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era

no code implementations1 Feb 2019 Gabrielle Allen, Igor Andreoni, Etienne Bachelet, G. Bruce Berriman, Federica B. Bianco, Rahul Biswas, Matias Carrasco Kind, Kyle Chard, Minsik Cho, Philip S. Cowperthwaite, Zachariah B. Etienne, Daniel George, Tom Gibbs, Matthew Graham, William Gropp, Anushri Gupta, Roland Haas, E. A. Huerta, Elise Jennings, Daniel S. Katz, Asad Khan, Volodymyr Kindratenko, William T. C. Kramer, Xin Liu, Ashish Mahabal, Kenton McHenry, J. M. Miller, M. S. Neubauer, Steve Oberlin, Alexander R. Olivas Jr, Shawn Rosofsky, Milton Ruiz, Aaron Saxton, Bernard Schutz, Alex Schwing, Ed Seidel, Stuart L. Shapiro, Hongyu Shen, Yue Shen, Brigitta M. Sipőcz, Lunan Sun, John Towns, Antonios Tsokaros, Wei Wei, Jack Wells, Timothy J. Williams, JinJun Xiong, Zhizhen Zhao

We discuss key aspects to realize this endeavor, namely (i) the design and exploitation of scalable and computationally efficient AI algorithms for Multi-Messenger Astrophysics; (ii) cyberinfrastructure requirements to numerically simulate astrophysical sources, and to process and interpret Multi-Messenger Astrophysics data; (iii) management of gravitational wave detections and triggers to enable electromagnetic and astro-particle follow-ups; (iv) a vision to harness future developments of machine and deep learning and cyberinfrastructure resources to cope with the scale of discovery in the Big Data Era; (v) and the need to build a community that brings domain experts together with data scientists on equal footing to maximize and accelerate discovery in the nascent field of Multi-Messenger Astrophysics.

Astronomy Management