Search Results for author: Dongjin Song

Found 19 papers, 5 papers with code

Deep Federated Anomaly Detection for Multivariate Time Series Data

no code implementations9 May 2022 Wei Zhu, Dongjin Song, Yuncong Chen, Wei Cheng, Bo Zong, Takehiko Mizoguchi, Cristian Lumezanu, Haifeng Chen, Jiebo Luo

Specifically, we first design an Exemplar-based Deep Neural network (ExDNN) to learn local time series representations based on their compatibility with an exemplar module which consists of hidden parameters learned to capture varieties of normal patterns on each edge device.

Federated Learning Time Series +1

Ordinal-Quadruplet: Retrieval of Missing Classes in Ordinal Time Series

no code implementations24 Jan 2022 Jurijs Nazarovs, Cristian Lumezanu, Qianying Ren, Yuncong Chen, Takehiko Mizoguchi, Dongjin Song, Haifeng Chen

In this paper, we propose an ordered time series classification framework that is robust against missing classes in the training data, i. e., during testing we can prescribe classes that are missing during training.

Time Series Time Series Classification

Hierarchical Prototype Networks for Continual Graph Representation Learning

no code implementations30 Nov 2021 Xikun Zhang, Dongjin Song, DaCheng Tao

Despite significant advances in graph representation learning, little attention has been paid to the more practical continual learning scenario in which new categories of nodes (e. g., new research areas in citation networks, or new types of products in co-purchasing networks) and their associated edges are continuously emerging, causing catastrophic forgetting on previous categories.

Continual Learning Graph Representation Learning

Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection

no code implementations29 Jul 2021 Xinyang Feng, Dongjin Song, Yuncong Chen, Zhengzhang Chen, Jingchao Ni, Haifeng Chen

Next, a dual discriminator based adversarial training procedure, which jointly considers an image discriminator that can maintain the local consistency at frame-level and a video discriminator that can enforce the global coherence of temporal dynamics, is employed to enhance the future frame prediction.

Anomaly Detection Frame

Hierarchical Prototype Network for Continual Graph Representation Learning

no code implementations NeurIPS 2021 Xikun Zhang, Dongjin Song, DaCheng Tao

The key challenge is to incorporate the feature and topological information of new nodes in a continuous and effective manner such that performance over existing nodes is uninterrupted.

Continual Learning Graph Representation Learning

Unsupervised Document Embedding via Contrastive Augmentation

1 code implementation26 Mar 2021 Dongsheng Luo, Wei Cheng, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Bo Zong, Yanchi Liu, Zhengzhang Chen, Dongjin Song, Haifeng Chen, Xiang Zhang

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner.

Contrastive Learning Data Augmentation +3

Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series

1 code implementation3 Mar 2021 Yinjun Wu, Jingchao Ni, Wei Cheng, Bo Zong, Dongjin Song, Zhengzhang Chen, Yanchi Liu, Xuchao Zhang, Haifeng Chen, Susan Davidson

Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications.

Time Series

The Skill-Action Architecture: Learning Abstract Action Embeddings for Reinforcement Learning

no code implementations1 Jan 2021 Chang Li, Dongjin Song, DaCheng Tao

Derived from a novel discovery that the SMDP option framework has an MDP equivalence, SA hierarchically extracts skills (abstract actions) from primary actions and explicitly encodes these knowledge into skill context vectors (embedding vectors).

Hierarchical Reinforcement Learning reinforcement-learning

TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series

no code implementations4 Oct 2020 Yang Jiao, Kai Yang, Shaoyu Dou, Pan Luo, Sijia Liu, Dongjin Song

To this end, we propose an autonomous representation learning approach for multivariate time series (TimeAutoML) with irregular sampling rates and variable lengths.

Anomaly Detection Hyperparameter Optimization +2

Inductive and Unsupervised Representation Learning on Graph Structured Objects

no code implementations ICLR 2020 Lichen Wang, Bo Zong, Qianqian Ma, Wei Cheng, Jingchao Ni, Wenchao Yu, Yanchi Liu, Dongjin Song, Haifeng Chen, Yun Fu

Inductive and unsupervised graph learning is a critical technique for predictive or information retrieval tasks where label information is difficult to obtain.

Graph Learning Graph Similarity +2

Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

no code implementations18 Dec 2019 Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, Gerard de Melo

In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's reviews pertain only to that single item and are thus topically homogeneous.

Recommendation Systems

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

5 code implementations20 Nov 2018 Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, Nitesh V. Chawla

Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns.

Time Series Unsupervised Anomaly Detection

Learning Deep Network Representations with Adversarially Regularized Autoencoders

1 code implementation ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2018 Wenchao Yu, Cheng Zheng, Wei Cheng, Charu C. Aggarwal, Dongjin Song, Bo Zong, Haifeng Chen, Wei Wang

The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the "semantics" of the original network structure.

Link Prediction Multi-Label Classification +1

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

14 code implementations7 Apr 2017 Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison Cottrell

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades.

Time Series Time Series Prediction

Exemplar-Centered Supervised Shallow Parametric Data Embedding

no code implementations21 Feb 2017 Martin Renqiang Min, Hongyu Guo, Dongjin Song

Our strategy learns a shallow high-order parametric embedding function and compares training/test data only with learned or precomputed exemplars, resulting in a cost function with linear computational complexity for both training and testing.

Dimensionality Reduction General Classification +2

A Shallow High-Order Parametric Approach to Data Visualization and Compression

no code implementations16 Aug 2016 Martin Renqiang Min, Hongyu Guo, Dongjin Song

These exemplars in combination with the feature mapping learned by HOPE effectively capture essential data variations.

Data Visualization General Classification +1

Top Rank Supervised Binary Coding for Visual Search

no code implementations ICCV 2015 Dongjin Song, Wei Liu, Rongrong Ji, David A. Meyer, John R. Smith

In this paper, we propose a novel supervised binary coding approach, namely Top Rank Supervised Binary Coding (Top-RSBC), which explicitly focuses on optimizing the precision of top positions in a Hamming-distance ranking list towards preserving the supervision information.

Image Retrieval online learning

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