Search Results for author: Yan Liu

Found 142 papers, 39 papers with code

MPII: Multi-Level Mutual Promotion for Inference and Interpretation

1 code implementation ACL 2022 Yan Liu, Sanyuan Chen, Yazheng Yang, Qi Dai

In this paper, we propose a multi-level Mutual Promotion mechanism for self-evolved Inference and sentence-level Interpretation (MPII).

Uncovering and Categorizing Social Biases in Text-to-SQL

no code implementations25 May 2023 Yan Liu, Yan Gao, Zhe Su, Xiaokang Chen, Elliott Ash, Jian-Guang Lou

In this work, we aim to uncover and categorize social biases in Text-to-SQL models.


WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

1 code implementation3 Apr 2023 Lianghui Zhu, Yingyue Li, Jiemin Fang, Yan Liu, Hao Xin, Wenyu Liu, Xinggang Wang

Thus a novel weight-based method is proposed to end-to-end estimate the importance of attention heads, while the self-attention maps are adaptively fused for high-quality CAM results that tend to have more complete objects.

Weakly-supervised Learning Weakly supervised Semantic Segmentation +1

Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders

no code implementations4 Mar 2023 Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, Yan Liu

Causal analysis for time series data, in particular estimating individualized treatment effect (ITE), is a key task in many real-world applications, such as finance, retail, healthcare, etc.

Causal Inference Irregular Time Series +1

A novel efficient Multi-view traffic-related object detection framework

no code implementations23 Feb 2023 Kun Yang, Jing Liu, Dingkang Yang, Hanqi Wang, Peng Sun, Yanni Zhang, Yan Liu, Liang Song

With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception.

Model Selection object-detection +1

Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios

no code implementations21 Feb 2023 Yan Liu, Xiaokang Chen, Qi Dai

However, current works pursuing sentence-level explanations rely heavily on annotated training data, which limits the development of interpretability to only a few tasks.

Explanation Generation Natural Language Inference

Estimating Treatment Effects in Continuous Time with Hidden Confounders

no code implementations19 Feb 2023 Defu Cao, James Enouen, Yan Liu

Estimating treatment effects plays a crucial role in causal inference, having many real-world applications like policy analysis and decision making.

Causal Inference Decision Making +2

Personalized Interpretable Classification

no code implementations6 Feb 2023 Zengyou He, Yifan Tang, Lianyu Hu, Mudi Jiang, Yan Liu

In addition to the problem formulation on this new issue, we present a greedy algorithm called PIC (Personalized Interpretable Classifier) to identify a personalized rule for each individual test sample.


DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift

no code implementations17 Nov 2022 Defu Cao, Yousef El-Laham, Loc Trinh, Svitlana Vyetrenko, Yan Liu

Using the proposed synthetic dataset, we provide a holistic analysis on the forecasting performance of three different state-of-the-art forecasting methods.

Benchmarking Time Series Analysis

D$^3$ETR: Decoder Distillation for Detection Transformer

no code implementations17 Nov 2022 Xiaokang Chen, Jiahui Chen, Yan Liu, Gang Zeng

Specifically, Adaptive Matching applies bipartite matching to adaptively match the outputs of the teacher and the student in each decoder layer, while Fixed Matching fixes the correspondence between the outputs of the teacher and the student with the same object queries, with the teacher's fixed object queries fed to the decoder of the student as an auxiliary group.

Knowledge Distillation

Significance-Based Categorical Data Clustering

1 code implementation8 Nov 2022 Lianyu Hu, Mudi Jiang, Yan Liu, Zengyou He

As a by-product, we can further calculate an empirical $p$-value to assess the statistical significance of a set of clusters and develop an improved gap statistic for estimating the cluster number.


Energy System Digitization in the Era of AI: A Three-Layered Approach towards Carbon Neutrality

no code implementations2 Nov 2022 Le Xie, Tong Huang, Xiangtian Zheng, Yan Liu, Mengdi Wang, Vijay Vittal, P. R. Kumar, Srinivas Shakkottai, Yi Cui

The transition towards carbon-neutral electricity is one of the biggest game changers in addressing climate change since it addresses the dual challenges of removing carbon emissions from the two largest sectors of emitters: electricity and transportation.

Decision Making

Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media

no code implementations14 Oct 2022 Yizhou Zhang, Defu Cao, Yan Liu

To address these issues, in this paper, we build up a causal framework that model the causal effect of misinformation from the perspective of temporal point process.


Transition to Adulthood for Young People with Intellectual or Developmental Disabilities: Emotion Detection and Topic Modeling

1 code implementation21 Sep 2022 Yan Liu, Maria Laricheva, Chiyu Zhang, Patrick Boutet, GuanYu Chen, Terence Tracey, Giuseppe Carenini, Richard Young

This study is to explore how to use natural language processing (NLP) methods, especially unsupervised machine learning, to assist psychologists to analyze emotions and sentiments and to use topic modeling to identify common issues and challenges that young people with IDD and their families have.

Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection

no code implementations19 Sep 2022 James Enouen, Yan Liu

There is currently a large gap in performance between the statistically rigorous methods like linear regression or additive splines and the powerful deep methods using neural networks.

Automated Utterance Labeling of Conversations Using Natural Language Processing

1 code implementation12 Aug 2022 Maria Laricheva, Chiyu Zhang, Yan Liu, GuanYu Chen, Terence Tracey, Richard Young, Giuseppe Carenini

Conversational data is essential in psychology because it can help researchers understand individuals cognitive processes, emotions, and behaviors.

Domain Adaptation

SsaA: A Self-supervised auto-Annotation System for Online Visual Inspection and Manufacturing Automation

no code implementations8 Aug 2022 Jiawei Li, Bolin Jiang, Yan Liu, Chengxiao Luo, Naiqi Li, Bin Chen

To make a step forward, this paper outlines an automatic annotation system called SsaA, working in a self-supervised learning manner, for continuously making the online visual inspection in the manufacturing automation scenarios.

Self-Supervised Learning

I-SEA: Importance Sampling and Expected Alignment-Based Deep Distance Metric Learning for Time Series Analysis and Embedding

1 code implementation Proceedings of the AAAI Conference on Artificial Intelligence 2022 Sirisha Rambhatla, Zhengping Che, Yan Liu

To this end, we develop an Importance Sampling based distance metric -- I-SEA -- which enjoys the properties of a metric while consistently achieving superior performance for machine learning tasks such as classification and representation learning.

Density Estimation Metric Learning +2

Policy Learning under Endogeneity Using Instrumental Variables

no code implementations20 Jun 2022 Yan Liu

To this end, we incorporate the marginal treatment effects (MTE) when identifying treatment effect parameters and consider encouragement rules that affect social welfare through treatment take-up when designing policies.

MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos

1 code implementation IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 Bruce X.B. Yu, Yan Liu, Xiang Zhang, Sheng-hua Zhong, Keith C.C. Chan

Upon aggregating the results of multiple modalities, our method is found to outperform state-of-the-art approaches on six evaluation protocols of the five datasets; thus, the proposed MMNet can effectively capture mutually complementary features in different RGB-D video modalities and provide more discriminative features for HAR.

 Ranked #1 on Action Recognition In Videos on PKU-MMD (using extra training data)

Action Classification Action Recognition In Videos +2

When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning

no code implementations31 Mar 2022 Chuizheng Meng, Sungyong Seo, Defu Cao, Sam Griesemer, Yan Liu

Physics-informed machine learning (PIML), referring to the combination of prior knowledge of physics, which is the high level abstraction of natural phenomenons and human behaviours in the long history, with data-driven machine learning models, has emerged as an effective way to mitigate the shortage of training data, to increase models' generalizability and to ensure the physical plausibility of results.

BIG-bench Machine Learning Physics-informed machine learning

Construction of Large-Scale Misinformation Labeled Datasets from Social Media Discourse using Label Refinement

1 code implementation24 Feb 2022 Karishma Sharma, Emilio Ferrara, Yan Liu

Malicious accounts spreading misinformation has led to widespread false and misleading narratives in recent times, especially during the COVID-19 pandemic, and social media platforms struggle to eliminate these contents rapidly.

Fact Checking Misinformation

On the Importance of Building High-quality Training Datasets for Neural Code Search

1 code implementation14 Feb 2022 Zhensu Sun, Yan Liu, Xiaoning Du, Li Li

The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived.

Code Search Retrieval

Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfer

1 code implementation21 Jan 2022 Zhejing Hu, Yan Liu, Gong Chen, Yongxu Liu

User preference music transfer (UPMT) is a new problem in music style transfer that can be applied to many scenarios but remains understudied.

Music Style Transfer Style Transfer

Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision

no code implementations9 Jan 2022 Yan Liu, Qingyong Hu, Yinjie Lei, Kai Xu, Jonathan Li, Yulan Guo

In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.

Semantic Segmentation

Forecasting Loss of Signal in Optical Networks with Machine Learning

1 code implementation8 Jan 2022 Wenjie Du, David Cote, Chris Barber, Yan Liu

Furthermore, we show that it is possible to forecast LOS from all facility types and all networks with a single model, whereas fine-tuning for a particular facility or network only brings modest improvements.

BIG-bench Machine Learning Classification on Time Series with Missing Data

Two-dimensional flow field measurement of sediment-laden flow based on ultrasound image velocimetry

no code implementations29 Nov 2021 Weiliang Tao, Yan Liu, Zhimin Ma, Wenbin Hu

This paper proposes a novel particle image velocimetry (PIV) technique to generate an instantaneous two-dimensional velocity field for sediment-laden fluid based on the optical flow algorithm of ultrasound imaging.

Optical Flow Estimation

Optimization of Grant-Free NOMA with Multiple Configured-Grants for mURLLC

no code implementations17 Nov 2021 Yan Liu, Yansha Deng, Maged Elkashlan, Arumugam Nallanathan, George K. Karagiannidis

To support these requirements, the third generation partnership project (3GPP) has introduced enhanced grant-free (GF) transmission in the uplink (UL), with multiple active configured-grants (CGs) for URLLC UEs.

Large-Scale Hyperspectral Image Clustering Using Contrastive Learning

1 code implementation15 Nov 2021 Yaoming Cai, Zijia Zhang, Yan Liu, Pedram Ghamisi, Kun Li, Xiaobo Liu, Zhihua Cai

Specifically, we exploit a symmetric twin neural network comprised of a projection head with a dimensionality of the cluster number to conduct dual contrastive learning from a spectral-spatial augmentation pool.

Clustering Contrastive Learning +2

Unsupervised PET Reconstruction from a Bayesian Perspective

no code implementations29 Oct 2021 Chenyu Shen, Wenjun Xia, Hongwei Ye, Mingzheng Hou, Hu Chen, Yan Liu, Jiliu Zhou, Yi Zhang

Positron emission tomography (PET) reconstruction has become an ill-posed inverse problem due to low-count projection data, and a robust algorithm is urgently required to improve imaging quality.

Denoising Image Restoration

VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media

no code implementations NeurIPS 2021 Yizhou Zhang, Karishma Sharma, Yan Liu

Specifically, when modeling the observed data from social media with neural temporal point process, we jointly learn a Gibbs-like distribution of group assignment based on how consistent an assignment is to (1) the account embedding space and (2) the prior knowledge.

Misinformation Variational Inference

Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity

1 code implementation NeurIPS 2021 Yan Liu, Zhijie Zhang, Li Niu, Junjie Chen, Liqing Zhang

Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories.

object-detection Object Detection +2

A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Grids

1 code implementation12 Oct 2021 Xiangtian Zheng, Nan Xu, Loc Trinh, Dongqi Wu, Tong Huang, S. Sivaranjani, Yan Liu, Le Xie

The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change.

Time Series Analysis

AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation

no code implementations11 Oct 2021 Nuo Li, Bin Guo, Yan Liu, Lina Yao, Jiaqi Liu, Zhiwen Yu

On the one hand, we model the rich correlations between the users' diverse behaviors (e. g., answer, follow, vote) to obtain the individual-level behavior interaction.

Community Question Answering

Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition

no code implementations14 Sep 2021 Chuan-Fei Zhang, Yan Liu, Tian-Hao Zhang, Song-Lu Chen, Feng Chen, Xu-Cheng Yin

To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition

no code implementations7 Sep 2021 Zhi Zhang, Sheng-hua Zhong, Yan Liu

Data augmentation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting.

Data Augmentation Electroencephalogram (EEG) +2

MeDiaQA: A Question Answering Dataset on Medical Dialogues

no code implementations18 Aug 2021 Huqun Suri, Qi Zhang, Wenhua Huo, Yan Liu, Chunsheng Guan

In this paper, we introduce MeDiaQA, a novel question answering(QA) dataset, which constructed on real online Medical Dialogues.

Multiple-choice Question Answering

Characterizing Online Engagement with Disinformation and Conspiracies in the 2020 U.S. Presidential Election

no code implementations17 Jul 2021 Karishma Sharma, Emilio Ferrara, Yan Liu

Identifying and characterizing disinformation in political discourse on social media is critical to ensure the integrity of elections and democratic processes around the world.

Phoneme-aware and Channel-wise Attentive Learning for Text DependentSpeaker Verification

no code implementations25 Jun 2021 Yan Liu, Zheng Li, Lin Li, Qingyang Hong

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV).

Multi-Task Learning Text-Dependent Speaker Verification

COVID-19 Vaccine Misinformation Campaigns and Social Media Narratives

no code implementations15 Jun 2021 Karishma Sharma, Yizhou Zhang, Yan Liu

In this work, we investigate misinformation communities and narratives that can contribute to COVID-19 vaccine hesitancy.


Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling

1 code implementation9 Jun 2021 Chuizheng Meng, Sirisha Rambhatla, Yan Liu

Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues.

Federated Learning Spatio-Temporal Forecasting

One Network to Solve Them All: A Sequential Multi-Task Joint Learning Network Framework for MR Imaging Pipeline

no code implementations14 May 2021 Zhiwen Wang, Wenjun Xia, Zexin Lu, Yongqiang Huang, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Magnetic resonance imaging (MRI) acquisition, reconstruction, and segmentation are usually processed independently in the conventional practice of MRI workflow.

An Examination of Fairness of AI Models for Deepfake Detection

no code implementations2 May 2021 Loc Trinh, Yan Liu

Recent studies have demonstrated that deep learning models can discriminate based on protected classes like race and gender.

DeepFake Detection Face Swapping +1

IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction

no code implementations3 Apr 2021 Tao Wang, Wenjun Xia, Zexin Lu, Huaiqiang Sun, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods.

Computed Tomography (CT) Disentanglement +1

Interpretable Artificial Intelligence through the Lens of Feature Interaction

no code implementations1 Mar 2021 Michael Tsang, James Enouen, Yan Liu

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations.


DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction

1 code implementation16 Feb 2021 Tao Wang, Wenjun Xia, Yongqiang Huang, Huaiqiang Sun, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT.

Computed Tomography (CT) Metal Artifact Reduction

MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset

no code implementations12 Feb 2021 Chuizheng Meng, Loc Trinh, Nan Xu, Yan Liu

The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications.

Fairness Feature Importance +1

Modeling Treatment Effect Modification in Multidrug-Resistant Tuberculosis in an Individual Patient Data Meta-Analysis

no code implementations11 Jan 2021 Yan Liu, Mireille Schnitzer, Guanbo Wang, Edward Kennedy, Piret Viiklepp, Mario H. Vargas, Giovanni Sotgiu, Dick Menzies, Andrea Benedetti

We propose a marginal structural model (MSM) for effect modification by different patient characteristics and co-medications in a meta-analysis of observational IPD.


An Examination of Preference-based Reinforcement Learning for Treatment Recommendation

no code implementations1 Jan 2021 Nan Xu, Nitin Kamra, Yan Liu

Treatment recommendation is a complex multi-faceted problem with many conflicting objectives, e. g., optimizing the survival rate (or expected lifetime), mitigating negative impacts, reducing financial expenses and time costs, avoiding over-treatment, etc.

reinforcement-learning Reinforcement Learning (RL)

Time Series Counterfactual Inference with Hidden Confounders

no code implementations1 Jan 2021 Guangyu Li, Jiahao Chen, Samuel A Assefa, Yan Liu

We present augmented counterfactual ordinary differential equations (ACODEs), a new approach to counterfactual inference on time series data with a focus on healthcare applications.

Counterfactual Inference Gaussian Processes +1

Weakly Supervised Scene Graph Grounding

no code implementations1 Jan 2021 Yizhou Zhang, Zhaoheng Zheng, Yan Liu

Recent researches have achieved substantial advances in learning structured representations from images.

Differentiable Approximations for Multi-resource Spatial Coverage Problems

no code implementations1 Jan 2021 Nitin Kamra, Yan Liu

Resource allocation for coverage of physical spaces is a challenging problem in robotic surveillance, mobile sensor networks and security domains.

Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation

1 code implementation22 Dec 2020 Liye Mei, Yalan Yu, Yueyun Weng, Xiaopeng Guo, Yan Liu, Du Wang, Sheng Liu, Fuling Zhou, Cheng Lei

Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis.

Towards Accurate Spatiotemporal COVID-19 Risk Scores using High Resolution Real-World Mobility Data

1 code implementation14 Dec 2020 Sirisha Rambhatla, Sepanta Zeighami, Kameron Shahabi, Cyrus Shahabi, Yan Liu

As countries look towards re-opening of economic activities amidst the ongoing COVID-19 pandemic, ensuring public health has been challenging.

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

1 code implementation13 Dec 2020 Yi Zhang, Hu Chen, Wenjun Xia, Yang Chen, Baodong Liu, Yan Liu, Huaiqiang Sun, Jiliu Zhou

Compressed sensing (CS) computed tomography has been proven to be important for several clinical applications, such as sparse-view computed tomography (CT), digital tomosynthesis and interior tomography.

Computed Tomography (CT) Image Restoration +1

RACH in Self-Powered NB-IoT Networks: Energy Availability and Performance Evaluation

no code implementations23 Nov 2020 Yan Liu, Yansha Deng, Maged Elkashlan, Arumugam Nallanathan, Jinhong Yuan, Ranjan K. Mallik

In this work, we analyze RACH success probability in a self-powered NB-IoT network taking into account the repeated preamble transmissions and collisions, where each IoT device with data is active when its battery energy is sufficient to support the transmission.

Multi-agent Trajectory Prediction with Fuzzy Query Attention

1 code implementation NeurIPS 2020 Nitin Kamra, Hao Zhu, Dweep Trivedi, Ming Zhang, Yan Liu

Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning.

Decision Making Traffic Prediction +1

Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography

no code implementations27 Oct 2020 Xiang Chen, Wenjun Xia, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs).

Computed Tomography (CT) Image Reconstruction +1

CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels

no code implementations27 Oct 2020 Wenjun Xia, Zexin Lu, Yongqiang Huang, Yan Liu, Hu Chen, Jiliu Zhou, Yi Zhang

Current mainstream of CT reconstruction methods based on deep learning usually needs to fix the scanning geometry and dose level, which will significantly aggravate the training cost and need more training data for clinical application.

Asymptotic Properties of the Maximum Likelihood Estimator in Regime-Switching Models with Time-Varying Transition Probabilities

no code implementations10 Oct 2020 Chaojun Li, Yan Liu

We prove the asymptotic properties of the maximum likelihood estimator (MLE) in time-varying transition probability (TVTP) regime-switching models.

Analysis of Random Access in NB-IoT Networks with Three Coverage Enhancement Groups: A Stochastic Geometry Approach

no code implementations14 Sep 2020 Yan Liu, Yansha Deng, Nan Jiang, Maged Elkashlan, Arumugam Nallanathan

NarrowBand-Internet of Things (NB-IoT) is a new 3GPP radio access technology designed to provide better coverage for Low Power Wide Area (LPWA) networks.

PolSIRD: Modeling Epidemic Spread under Intervention Policies

no code implementations3 Sep 2020 Nitin Kamra, Yizhou Zhang, Sirisha Rambhatla, Chuizheng Meng, Yan Liu

Epidemic spread in a population is traditionally modeled via compartmentalized models which represent the free evolution of disease in absence of any intervention policies.

Network Intrusion Detection Using Wrapper-based Decision Tree for Feature Selection

no code implementations11 Aug 2020 Mubarak Albarka Umar, Chen Zhanfang, Yan Liu

We evaluate the effectiveness of our propose method by comparing it with the baseline models and also with state-of-the-art works.

feature selection Network Intrusion Detection

Network Inference from a Mixture of Diffusion Models for Fake News Mitigation

no code implementations8 Aug 2020 Karishma Sharma, Xinran He, Sungyong Seo, Yan Liu

Users influential in the propagation of true and fake contents are identified using the inferred diffusion dynamics.

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

no code implementations ECCV 2020 Yan Liu, Lingqiao Liu, Peng Wang, Pingping Zhang, Yinjie Lei

Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain.

Crowd Counting

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

no code implementations29 Jun 2020 Zhenyu Liu, Yaqiang Yao, Yan Liu, Yuening Zhu, Zhenchao Tao, Lei Wang, Yuhong Feng

In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.

Human Activity Recognition

Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes

no code implementations28 Jun 2020 Loc Trinh, Michael Tsang, Sirisha Rambhatla, Yan Liu

In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations.

DeepFake Detection Face Swapping

Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection

1 code implementation ICLR 2020 Michael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, Yan Liu

Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable.

BIG-bench Machine Learning Image Classification +1

Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning

no code implementations15 Jun 2020 Sungyong Seo, Chuizheng Meng, Sirisha Rambhatla, Yan Liu

Although the knowledge of governing partial differential equations (PDE) of data can be helpful for the fast adaptation to few observations, it is mostly infeasible to exactly find the equation for observations in real-world physical systems.


Req2Lib: A Semantic Neural Model for Software Library Recommendation

no code implementations24 May 2020 Zhensu Sun, Yan Liu, Ziming Cheng, Chen Yang, Pengyu Che

In this work, we would like to make recommendations based on requirement descriptions to avoid these problems.

Skeleton Focused Human Activity Recognition in RGB Video

no code implementations29 Apr 2020 Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition.

Human Activity Recognition

Effective Human Activity Recognition Based on Small Datasets

no code implementations29 Apr 2020 Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

To do so, we propose a HAR method that consists of three steps: (i) data transformation involving the generation of new features based on transforming of raw data, (ii) feature extraction involving the learning of a classifier based on the AdaBoost algorithm and the use of training data consisting of the transformed features, and (iii) parameter determination and pattern recognition involving the determination of parameters based on the features generated in (ii) and the use of the parameters as training data for deep learning algorithms to be used to recognize human activities.

Human Activity Recognition

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.

Binary Classification Word Embeddings +1

COVID-19 on Social Media: Analyzing Misinformation in Twitter Conversations

3 code implementations26 Mar 2020 Karishma Sharma, Sungyong Seo, Chuizheng Meng, Sirisha Rambhatla, Yan Liu

The analysis is presented and updated on a publically accessible dashboard (https://usc-melady. github. io/COVID-19-Tweet-Analysis) to track the nature of online discourse and misinformation about COVID-19 on Twitter from March 1 - June 5, 2020.

Fact Checking Misinformation

Towards Using Count-level Weak Supervision for Crowd Counting

no code implementations29 Feb 2020 Yinjie Lei, Yan Liu, Pingping Zhang, Lingqiao Liu

Most existing crowd counting methods require object location-level annotation, i. e., placing a dot at the center of an object.

Crowd Counting

Analyzing Grant-Free Access for URLLC Service

no code implementations18 Feb 2020 Yan Liu, Yansha Deng, Maged Elkashlan, Arumugam Nallanathan, George K. Karagiannidis

Based on this framework, we define the latent access failure probability to characterize URLLC reliability and latency performances.

Deep Reinforcement Learning-Based Beam Tracking for Low-Latency Services in Vehicular Networks

no code implementations13 Feb 2020 Yan Liu, Zhiyuan Jiang, Shunqing Zhang, Shugong Xu

Ultra-Reliable and Low-Latency Communications (URLLC) services in vehicular networks on millimeter-wave bands present a significant challenge, considering the necessity of constantly adjusting the beam directions.

reinforcement-learning Reinforcement Learning (RL)

Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics

1 code implementation ICLR 2020 Sungyong Seo*, Chuizheng Meng*, Yan Liu

Sparsely available data points cause a numerical error on finite differences which hinder to modeling the dynamics of physical systems.

Hybrid Low-order and Higher-order Graph Convolutional Networks

no code implementations2 Aug 2019 FangYuan Lei, Xun Liu, Qingyun Dai, Bingo Wing-Kuen Ling, Huimin Zhao, Yan Liu

With higher-order neighborhood information of graph network, the accuracy of graph representation learning classification can be significantly improved.

General Classification Graph Representation Learning

A simple and effective postprocessing method for image classification

no code implementations19 Jun 2019 Yan Liu, Yun Li, Yunhao Yuan, Jipeng Qiang

Whether it is computer vision, natural language processing or speech recognition, the essence of these applications is to obtain powerful feature representations that make downstream applications completion more efficient.

Classification General Classification +3

Extracting Interpretable Concept-Based Decision Trees from CNNs

no code implementations11 Jun 2019 Conner Chyung, Michael Tsang, Yan Liu

In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree.

Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting

no code implementations27 May 2019 Xu Geng, Xiyu Wu, Lingyu Zhang, Qiang Yang, Yan Liu, Jieping Ye

To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks.

BIG-bench Machine Learning

D$^2$-City: A Large-Scale Dashcam Video Dataset of Diverse Traffic Scenarios

no code implementations3 Apr 2019 Zhengping Che, Guangyu Li, Tracy Li, Bo Jiang, Xuefeng Shi, Xinsheng Zhang, Ying Lu, Guobin Wu, Yan Liu, Jieping Ye

Driving datasets accelerate the development of intelligent driving and related computer vision technologies, while substantial and detailed annotations serve as fuels and powers to boost the efficacy of such datasets to improve learning-based models.

Adaptive Gradient Methods with Dynamic Bound of Learning Rate

5 code implementations ICLR 2019 Liangchen Luo, Yuanhao Xiong, Yan Liu, Xu sun

Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods.

Differentiable Physics-informed Graph Networks

1 code implementation8 Feb 2019 Sungyong Seo, Yan Liu

While physics conveys knowledge of nature built from an interplay between observations and theory, it has been considered less importantly in deep neural networks.

Combating Fake News: A Survey on Identification and Mitigation Techniques

no code implementations18 Jan 2019 Karishma Sharma, Feng Qian, He Jiang, Natali Ruchansky, Ming Zhang, Yan Liu

The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news, and mitigation of its widespread impact on public opinion.


Instance-Based Classification through Hypothesis Testing

no code implementations3 Jan 2019 Zengyou He, Chaohua Sheng, Yan Liu, Quan Zou

After these two steps, we have two p-values for each test instance and the test instance is assigned to the class associated with the smaller p-value.

Binary Classification Classification +2

Can I trust you more? Model-Agnostic Hierarchical Explanations

no code implementations ICLR 2019 Michael Tsang, Youbang Sun, Dongxu Ren, Yan Liu

Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models.

BIG-bench Machine Learning

Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability

no code implementations NeurIPS 2018 Michael Tsang, Hanpeng Liu, Sanjay Purushotham, Pavankumar Murali, Yan Liu

Neural networks are known to model statistical interactions, but they entangle the interactions at intermediate hidden layers for shared representation learning.

Additive models Representation Learning

Skeleton-based Activity Recognition with Local Order Preserving Match of Linear Patches

no code implementations1 Nov 2018 Yaqiang Yao, Yan Liu, Huanhuan Chen

In this paper, we first design an efficient division method to decompose a manifold into ordered continuous maximal linear patches (CMLPs) that denote meaningful action snippets of the action sequence.

Human Activity Recognition

Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series

no code implementations ICML 2018 Zhengping Che, Sanjay Purushotham, Guangyu Li, Bo Jiang, Yan Liu

Multi-Rate Multivariate Time Series (MR-MTS) are the multivariate time series observations which come with various sampling rates and encode multiple temporal dependencies.

Time Series Analysis

DynGEM: Deep Embedding Method for Dynamic Graphs

1 code implementation29 May 2018 Palash Goyal, Nitin Kamra, Xinran He, Yan Liu

The major advantages of DynGEM include: (1) the embedding is stable over time, (2) it can handle growing dynamic graphs, and (3) it has better running time than using static embedding methods on each snapshot of a dynamic graph.

Social and Information Networks

A Modified Sigma-Pi-Sigma Neural Network with Adaptive Choice of Multinomials

no code implementations1 Feb 2018 Feng Li, Yan Liu, Khidir Shaib Mohamed, Wei Wu

We propose in this paper a modified Sigma-Pi-Sigma neural network (MSPSNN) with an adaptive approach to find a better multinomial for a given problem.

Robustness of classification ability of spiking neural networks

no code implementations30 Jan 2018 Jie Yang, Pingping Zhang, Yan Liu

The numerical results show that there is not significant reduction in the classification ability of the network if the input signals are subject to sinusoidal and Gaussian perturbations.

Classification General Classification

Automatically Inferring Data Quality for Spatiotemporal Forecasting

no code implementations ICLR 2018 Sungyong Seo, Arash Mohegh, George Ban-Weiss, Yan Liu

Spatiotemporal forecasting has become an increasingly important prediction task in machine learning and statistics due to its vast applications, such as climate modeling, traffic prediction, video caching predictions, and so on.

Traffic Prediction

Relational Multi-Instance Learning for Concept Annotation from Medical Time Series

no code implementations ICLR 2018 Sanjay Purushotham, Zhengping Che, Bo Jiang, Tanachat Nilanon, Yan Liu

Recent advances in computing technology and sensor design have made it easier to collect longitudinal or time series data from patients, resulting in a gigantic amount of available medical data.

Time Series Analysis

Tensor Regression Meets Gaussian Processes

no code implementations31 Oct 2017 Rose Yu, Guangyu Li, Yan Liu

Low-rank tensor regression, a new model class that learns high-order correlation from data, has recently received considerable attention.

Bayesian Inference Gaussian Processes +1

Deep Generative Dual Memory Network for Continual Learning

no code implementations ICLR 2018 Nitin Kamra, Umang Gupta, Yan Liu

This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data.

Continual Learning Hippocampus

Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets

1 code implementation23 Oct 2017 Sanjay Purushotham, Chuizheng Meng, Zhengping Che, Yan Liu

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications.

Benchmarking BIG-bench Machine Learning +5

Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records

no code implementations6 Sep 2017 Zhengping Che, Yu Cheng, Shuangfei Zhai, Zhaonan Sun, Yan Liu

We use this generative model together with a convolutional neural network (CNN) based prediction model to improve the onset prediction performance.

Detecting Statistical Interactions from Neural Network Weights

no code implementations ICLR 2018 Michael Tsang, Dehua Cheng, Yan Liu

Interpreting neural networks is a crucial and challenging task in machine learning.

CNN based music emotion classification

no code implementations19 Apr 2017 Xin Liu, Qingcai Chen, Xiang-Ping Wu, Yan Liu, Yang Liu

Music emotion recognition (MER) is usually regarded as a multi-label tagging task, and each segment of music can inspire specific emotion tags.

Classification Emotion Classification +3

CSI: A Hybrid Deep Model for Fake News Detection

2 code implementations20 Mar 2017 Natali Ruchansky, Sungyong Seo, Yan Liu

Specifically, we incorporate the behavior of both parties, users and articles, and the group behavior of users who propagate fake news.

Fake News Detection Misinformation

Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding

no code implementations25 Jan 2017 Zhengping Che, Yu Cheng, Zhaonan Sun, Yan Liu

To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts.

SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling

no code implementations NeurIPS 2016 Dehua Cheng, Richard Peng, Yan Liu, Ioakeim Perros

In this paper, we show ways of sampling intermediate steps of alternating minimization algorithms for computing low rank tensor CP decompositions, leading to the sparse alternating least squares (SPALS) method.

Universal dependencies for Uyghur

no code implementations WS 2016 Marhaba Eli, Weinila Mushajiang, Tuergen Yibulayin, Kahaerjiang Abiderexiti, Yan Liu

The Universal Dependencies (UD) Project seeks to build a cross-lingual studies of treebanks, linguistic structures and parsing.

Cross-Lingual Transfer

Learning Influence Functions from Incomplete Observations

no code implementations NeurIPS 2016 Xinran He, Ke Xu, David Kempe, Yan Liu

We establish both proper and improper PAC learnability of influence functions under randomly missing observations.

On Bochner's and Polya's Characterizations of Positive-Definite Kernels and the Respective Random Feature Maps

no code implementations27 Oct 2016 Jie Chen, Dehua Cheng, Yan Liu

A well-known construction of such functions comes from Bochner's characterization, which connects a positive-definite function with a probability distribution.

Gaussian Processes

On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization

no code implementations23 Oct 2016 Yuan Xie, DaCheng Tao, Wensheng Zhang, Lei Zhang, Yan Liu, Yanyun Qu

Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly.

Clustering Multi-view Subspace Clustering

Learning from Multiway Data: Simple and Efficient Tensor Regression

no code implementations8 Jul 2016 Rose Yu, Yan Liu

In this paper, we introduce subsampled tensor projected gradient to solve the problem.

Multi-Task Learning regression

The DARPA Twitter Bot Challenge

no code implementations20 Jan 2016 V. S. Subrahmanian, Amos Azaria, Skylar Durst, Vadim Kagan, Aram Galstyan, Kristina Lerman, Linhong Zhu, Emilio Ferrara, Alessandro Flammini, Filippo Menczer, Andrew Stevens, Alexander Dekhtyar, Shuyang Gao, Tad Hogg, Farshad Kooti, Yan Liu, Onur Varol, Prashant Shiralkar, Vinod Vydiswaran, Qiaozhu Mei, Tim Hwang

A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes.

A Survey on Social Media Anomaly Detection

no code implementations6 Jan 2016 Rose Yu, Huida Qiu, Zhen Wen, Ching-Yung Lin, Yan Liu

In this paper, we present a survey on existing approaches to address this problem.

Anomaly Detection

Distilling Knowledge from Deep Networks with Applications to Healthcare Domain

no code implementations11 Dec 2015 Zhengping Che, Sanjay Purushotham, Robinder Khemani, Yan Liu

Exponential growth in Electronic Healthcare Records (EHR) has resulted in new opportunities and urgent needs for discovery of meaningful data-driven representations and patterns of diseases in Computational Phenotyping research.

Computational Phenotyping Decision Making +3

Weighted Schatten $p$-Norm Minimization for Image Denoising and Background Subtraction

no code implementations3 Dec 2015 Yuan Xie, Shuhang Gu, Yan Liu, WangMeng Zuo, Wensheng Zhang, Lei Zhang

However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications.

Image Denoising

Spectral Sparsification of Random-Walk Matrix Polynomials

no code implementations12 Feb 2015 Dehua Cheng, Yu Cheng, Yan Liu, Richard Peng, Shang-Hua Teng

Our work is particularly motivated by the algorithmic problems for speeding up the classic Newton's method in applications such as computing the inverse square-root of the precision matrix of a Gaussian random field, as well as computing the $q$th-root transition (for $q\geq1$) in a time-reversible Markov model.

Fast Multivariate Spatio-temporal Analysis via Low Rank Tensor Learning

no code implementations NeurIPS 2014 Mohammad Taha Bahadori, Qi (Rose) Yu, Yan Liu

Accurate and efficient analysis of multivariate spatio-temporal data is critical in climatology, geology, and sociology applications.

Clustering Sociology

GLAD: Group Anomaly Detection in Social Media Analysis- Extended Abstract

no code implementations7 Oct 2014 QI, Yu, Xinran He, Yan Liu

Existing group anomaly detection approaches rely on the assumption that the groups are known, which can hardly be true in real world social media applications.

Group Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.