Search Results for author: Xiangnan Kong

Found 31 papers, 8 papers with code

Multi-State Brain Network Discovery

no code implementations4 Nov 2023 Hang Yin, Yao Su, Xinyue Liu, Thomas Hartvigsen, Yanhua Li, Xiangnan Kong

We refer to such brain networks as multi-state, and this mixture can help us understand human behavior.

Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks

no code implementations8 Feb 2023 Thomas Hartvigsen, Jidapa Thadajarassiri, Xiangnan Kong, Elke Rundensteiner

Using this insight, we then propose CAT, a model that classifies multivariate ITS by explicitly seeking highly-relevant portions of an input series' timeline.

Imputation Irregular Time Series +2

ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration

1 code implementation6 Dec 2022 Yao Su, Xin Dai, Lifang He, Xiangnan Kong

Recent research on deformable image registration is mainly focused on improving the registration accuracy using multi-stage alignment methods, where the source image is repeatedly deformed in stages by a same neural network until it is well-aligned with the target image.

Deformable Medical Image Registration Image Registration +1

Stop&Hop: Early Classification of Irregular Time Series

1 code implementation21 Aug 2022 Thomas Hartvigsen, Walter Gerych, Jidapa Thadajarassiri, Xiangnan Kong, Elke Rundensteiner

We bridge this gap and study early classification of irregular time series, a new setting for early classifiers that opens doors to more real-world problems.

Early Classification General Classification +3

One-Shot Learning on Attributed Sequences

no code implementations23 Jan 2022 Zhongfang Zhuang, Xiangnan Kong, Elke Rundensteiner, Aditya Arora, Jihane Zouaoui

In this paper, we study the problem of one-shot learning on attributed sequences, where each instance is composed of a set of attributes (e. g., user profile) and a sequence of categorical items (e. g., clickstream).

Network Intrusion Detection One-Shot Learning

Self-learn to Explain Siamese Networks Robustly

no code implementations15 Sep 2021 Chao Chen, Yifan Shen, Guixiang Ma, Xiangnan Kong, Srinivas Rangarajan, Xi Zhang, Sihong Xie

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.

Face Recognition Fairness +1

Gaussian Mixture Graphical Lasso with Application to Edge Detection in Brain Networks

no code implementations13 Jan 2021 Hang Yin, Xinyue Liu, Xiangnan Kong

Existing works mainly focus on unimodal distributions, where it is usually assumed that the observed activities aregenerated from asingleGaussian distribution (i. e., one graph). However, this assumption is too strong for many real-worldapplications.

Edge Detection

MLAS: Metric Learning on Attributed Sequences

no code implementations8 Nov 2020 Zhongfang Zhuang, Xiangnan Kong, Elke Rundensteiner, Jihane Zouaoui, Aditya Arora

Distance metric learning has attracted much attention in recent years, where the goal is to learn a distance metric based on user feedback.

Attribute Metric Learning

Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?

no code implementations ACL 2020 Cansu Sen, Thomas Hartvigsen, Biao Yin, Xiangnan Kong, Elke Rundensteiner

Motivated by human attention, computational attention mechanisms have been designed to help neural networks adjust their focus on specific parts of the input data.

General Classification text-classification +1

Attributed Sequence Embedding

no code implementations3 Nov 2019 Zhongfang Zhuang, Xiangnan Kong, Elke Rundensteiner, Jihane Zouaoui, Aditya Arora

This problem is core to many important data mining tasks ranging from user behavior analysis to the clustering of gene sequences.


Reducing Computation in Recurrent Networks by Selectively Updating State Neurons

no code implementations25 Sep 2019 Thomas Hartvigsen, Cansu Sen, Xiangnan Kong, Elke Rundensteiner

As a result, even for high-dimensional hidden states, all dimensions are updated at each timestep regardless of the recurrent memory cell.

Adaptive-Halting Policy Network for Early Classification

1 code implementation KDD 2019 Thomas Hartvigsen, Cansu Sen, Xiangnan Kong, Elke Rundensteiner

Early classification of time series is the prediction of the class label of a time series before it is observed in its entirety.

Classification Early Classification +3

Signed Distance-based Deep Memory Recommender

1 code implementation1 May 2019 Thanh Tran, Xinyue Liu, Kyumin Lee, Xiangnan Kong

Personalized recommendation algorithms learn a user's preference for an item by measuring a distance/similarity between them.

Recommendation Systems

Higher-order Graph Convolutional Networks

no code implementations12 Sep 2018 John Boaz Lee, Ryan A. Rossi, Xiangnan Kong, Sungchul Kim, Eunyee Koh, Anup Rao

Experiments show that our proposed method is able to achieve state-of-the-art results on the semi-supervised node classification task.

General Classification Graph Attention +1

TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks

no code implementations22 Aug 2018 Xinyue Liu, Xiangnan Kong, Lei Liu, Kuorong Chiang

To address these issues, we study the problem of syntax-aware sequence generation with GANs, in which a collection of real sequences and a set of pre-defined grammatical rules are given to both discriminator and generator.

Image Generation

Inductive Representation Learning in Large Attributed Graphs

no code implementations25 Oct 2017 Nesreen K. Ahmed, Ryan A. Rossi, Rong Zhou, John Boaz Lee, Xiangnan Kong, Theodore L. Willke, Hoda Eldardiry

To make these methods more generally applicable, we propose a framework for inductive network representation learning based on the notion of attributed random walk that is not tied to node identity and is instead based on learning a function $\Phi : \mathrm{\rm \bf x} \rightarrow w$ that maps a node attribute vector $\mathrm{\rm \bf x}$ to a type $w$.

Anomaly Detection Attribute +2

Deep Graph Attention Model

no code implementations15 Sep 2017 John Boaz Lee, Ryan Rossi, Xiangnan Kong

Graph classification is a problem with practical applications in many different domains.

General Classification Graph Attention +1

Mining Brain Networks using Multiple Side Views for Neurological Disorder Identification

no code implementations19 Aug 2015 Bokai Cao, Xiangnan Kong, Jingyuan Zhang, Philip S. Yu, Ann B. Ragin

In this paper, we study the problem of discriminative subgraph selection using multiple side views and propose a novel solution to find an optimal set of subgraph features for graph classification by exploring a plurality of side views.

feature selection General Classification +1

A review of heterogeneous data mining for brain disorders

no code implementations5 Aug 2015 Bokai Cao, Xiangnan Kong, Philip S. Yu

Brain disorder data poses many unique challenges for data mining research.

DuSK: A Dual Structure-preserving Kernel for Supervised Tensor Learning with Applications to Neuroimages

no code implementations31 Jul 2014 Lifang He, Xiangnan Kong, Philip S. Yu, Ann B. Ragin, Zhifeng Hao, Xiaowei Yang

The dual-tensorial mapping function can map each tensor instance in the input space to another tensor in the feature space while preserving the tensorial structure.

General Classification

Large-Scale Multi-Label Learning with Incomplete Label Assignments

no code implementations6 Jul 2014 Xiangnan Kong, Zhaoming Wu, Li-Jia Li, Ruofei Zhang, Philip S. Yu, Hang Wu, Wei Fan

Unlike prior works, our method can effectively and efficiently consider missing labels and label correlations simultaneously, and is very scalable, that has linear time complexities over the size of the data.

Missing Labels

Multilabel Consensus Classification

no code implementations16 Oct 2013 Sihong Xie, Xiangnan Kong, Jing Gao, Wei Fan, Philip S. Yu

Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time.

Classification General Classification

Predicting Social Links for New Users across Aligned Heterogeneous Social Networks

no code implementations13 Oct 2013 Jiawei Zhang, Xiangnan Kong, Philip S. Yu

We propose a link prediction method called SCAN-PS (Supervised Cross Aligned Networks link prediction with Personalized Sampling), to solve the link prediction problem for new users with information transferred from both the existing active users in the target network and other source networks through aligned accounts.

Link Prediction Transfer Learning

HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks

no code implementations28 Sep 2013 Chuan Shi, Xiangnan Kong, Yue Huang, Philip S. Yu, Bin Wu

Similarity search is an important function in many applications, which usually focuses on measuring the similarity between objects with the same type.

Meta Path-Based Collective Classification in Heterogeneous Information Networks

no code implementations20 May 2013 Xiangnan Kong, Bokai Cao, Philip S. Yu, Ying Ding, David J. Wild

Moreover, by considering different linkage paths in the network, one can capture the subtlety of different types of dependencies among objects.

Classification General Classification

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