Unsupervised Deep Video Hashing with Balanced Rotation

Recently, hashing video contents for fast retrieval has received increasing attention due to the enormous growth of online videos. As the extension of image hashing techniques, traditional video hashing methods mainly focus on seeking the appropriate video features but pay little attention to how the video-specific features can be leveraged to achieve optimal binarization. In this paper, an end-to-end hashing framework, namely Unsupervised Deep Video Hashing (UDVH), is proposed, where feature extraction, balanced code learning and hash function learning are integrated and optimized in a self-taught manner. Particularly, distinguished from previous work, our framework enjoys two novelties: 1) an unsupervised hashing method that integrates the feature clustering and feature binarization, enabling the neighborhood structure to be preserved in the binary space; 2) a smart rotation applied to the video-specific features that are widely spread in the low-dimensional space such that the variance of dimensions can be balanced, thus generating more effective hash codes. Extensive experiments have been performed on two real-world datasets and the results demonstrate its superiority, compared to the state-of-the-art video hashing methods. To bootstrap further developments, the source code will be made publically available.

Download Full-text

TransET: Knowledge Graph Embedding with Entity Types

Electronics ◽

10.3390/electronics10121407 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1407

Author(s):

Peng Wang ◽

Jing Zhou ◽

Yuzhang Liu ◽

Xingchen Zhou

Keyword(s):

Link Prediction ◽

State Of The Art ◽

Score Function ◽

Graph Embedding ◽

Vector Spaces ◽

Knowledge Graph ◽

Semantic Features ◽

Knowledge Graphs ◽

Real World Datasets ◽

Low Dimensional

Knowledge graph embedding aims to embed entities and relations into low-dimensional vector spaces. Most existing methods only focus on triple facts in knowledge graphs. In addition, models based on translation or distance measurement cannot fully represent complex relations. As well-constructed prior knowledge, entity types can be employed to learn the representations of entities and relations. In this paper, we propose a novel knowledge graph embedding model named TransET, which takes advantage of entity types to learn more semantic features. More specifically, circle convolution based on the embeddings of entity and entity types is utilized to map head entity and tail entity to type-specific representations, then translation-based score function is used to learn the presentation triples. We evaluated our model on real-world datasets with two benchmark tasks of link prediction and triple classification. Experimental results demonstrate that it outperforms state-of-the-art models in most cases.

Download Full-text

Season- and Trend-aware Symbolic Approximation for Accurate and Efficient Time Series Matching

Datenbank-Spektrum ◽

10.1007/s13222-021-00389-5 ◽

2021 ◽

Author(s):

Lars Kegel ◽

Claudio Hartmann ◽

Maik Thiele ◽

Wolfgang Lehner

Keyword(s):

Time Series ◽

State Of The Art ◽

Dimensional Space ◽

Symbolic Aggregate Approximation ◽

Current State ◽

Optimal Representation ◽

Symbolic Approximation ◽

Low Dimensional ◽

Deterministic Behavior ◽

Support Time

AbstractProcessing and analyzing time series datasets have become a central issue in many domains requiring data management systems to support time series as a native data type. A core access primitive of time series is matching, which requires efficient algorithms on-top of appropriate representations like the symbolic aggregate approximation (SAX) representing the current state of the art. This technique reduces a time series to a low-dimensional space by segmenting it and discretizing each segment into a small symbolic alphabet. Unfortunately, SAX ignores the deterministic behavior of time series such as cyclical repeating patterns or a trend component affecting all segments, which may lead to a sub-optimal representation accuracy. We therefore introduce a novel season- and a trend-aware symbolic approximation and demonstrate an improved representation accuracy without increasing the memory footprint. Most importantly, our techniques also enable a more efficient time series matching by providing a match up to three orders of magnitude faster than SAX.

Download Full-text

Network Embedding via a Bi-Mode and Deep Neural Network Model

10.20944/preprints201712.0156.v1 ◽

2017 ◽

Author(s):

Yang Fang ◽

Xiang Zhao ◽

Zhen Tan

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Semantic Information ◽

Dimensional Space ◽

Relation Extraction ◽

Network Embedding ◽

Structure Information ◽

Second Mode ◽

Real World Datasets ◽

Low Dimensional

Network Embedding (NE) is an important method to learn the representations of network via a low-dimensional space. Conventional NE models focus on capturing the structure information and semantic information of vertices while neglecting such information for edges. In this work, we propose a novel NE model named BimoNet to capture both the structure and semantic information of edges. BimoNet is composed of two parts, i.e., the bi-mode embedding part and the deep neural network part. For bi-mode embedding part, the first mode named add-mode is used to express the entity-shared features of edges and the second mode named subtract-mode is employed to represent the entity-specific features of edges. These features actually reflect the semantic information. For deep neural network part, we firstly regard the edges in a network as nodes, and the vertices as links, which will not change the overall structure of the whole network. Then we take the nodes' adjacent matrix as the input of the deep neural network as it can obtain similar representations for nodes with similar structure. Afterwards, by jointly optimizing the objective function of these two parts, BimoNet could preserve both the semantic and structure information of edges. In experiments, we evaluate BimoNet on three real-world datasets and task of relation extraction, and BimoNet is demonstrated to outperform state-of-the-art baseline models consistently and significantly.

Download Full-text

Relation Structure-Aware Heterogeneous Information Network Embedding

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33014456 ◽

2019 ◽

Vol 33 ◽

pp. 4456-4463 ◽

Cited By ~ 8

Author(s):

Yuanfu Lu ◽

Chuan Shi ◽

Linmei Hu ◽

Zhiyuan Liu

Keyword(s):

Real World ◽

Dimensional Space ◽

Structural Characteristics ◽

Information Network ◽

Network Embedding ◽

Heterogeneous Information Network ◽

Heterogeneous Information ◽

Real World Datasets ◽

Low Dimensional ◽

Embedding Methods

Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.

Download Full-text

SCDRHA: A scRNA-Seq Data Dimensionality Reduction Algorithm Based on Hierarchical Autoencoder

Frontiers in Genetics ◽

10.3389/fgene.2021.733906 ◽

2021 ◽

Vol 12 ◽

Author(s):

Jianping Zhao ◽

Na Wang ◽

Haiyun Wang ◽

Chunhou Zheng ◽

Yansen Su

Keyword(s):

Dimensionality Reduction ◽

Data Visualization ◽

State Of The Art ◽

Dimensional Space ◽

High Dimensional ◽

Reduction Algorithm ◽

Cell Clustering ◽

Data Dimensionality Reduction ◽

Single Cell Rna Sequencing ◽

Low Dimensional

Dimensionality reduction of high-dimensional data is crucial for single-cell RNA sequencing (scRNA-seq) visualization and clustering. One prominent challenge in scRNA-seq studies comes from the dropout events, which lead to zero-inflated data. To address this issue, in this paper, we propose a scRNA-seq data dimensionality reduction algorithm based on a hierarchical autoencoder, termed SCDRHA. The proposed SCDRHA consists of two core modules, where the first module is a deep count autoencoder (DCA) that is used to denoise data, and the second module is a graph autoencoder that projects the data into a low-dimensional space. Experimental results demonstrate that SCDRHA has better performance than existing state-of-the-art algorithms on dimension reduction and noise reduction in five real scRNA-seq datasets. Besides, SCDRHA can also dramatically improve the performance of data visualization and cell clustering.

Download Full-text

Prediction of Disease-related microRNAs through Integrating Attributes of microRNA Nodes and Multiple Kinds of Connecting Edges

Molecules ◽

10.3390/molecules24173099 ◽

2019 ◽

Vol 24 (17) ◽

pp. 3099 ◽

Cited By ~ 3

Author(s):

Xuan ◽

Li ◽

Zhang ◽

Song

Keyword(s):

State Of The Art ◽

Dimensional Space ◽

Nonnegative Matrix ◽

Superior Performance ◽

Pancreatic Cancers ◽

Node Attribute ◽

Disease Associations ◽

Node Attributes ◽

Novel Method ◽

Low Dimensional

Identifying disease-associated microRNAs (disease miRNAs) contributes to the understanding of disease pathogenesis. Most previous computational biology studies focused on multiple kinds of connecting edges of miRNAs and diseases, including miRNA–miRNA similarities, disease–disease similarities, and miRNA–disease associations. Few methods exploited the node attribute information related to miRNA family and cluster. The previous methods do not completely consider the sparsity of node attributes. Additionally, it is challenging to deeply integrate the node attributes of miRNAs and the similarities and associations related to miRNAs and diseases. In the present study, we propose a novel method, known as MDAPred, based on nonnegative matrix factorization to predict candidate disease miRNAs. MDAPred integrates the node attributes of miRNAs and the related similarities and associations of miRNAs and diseases. Since a miRNA is typically subordinate to a family or a cluster, the node attributes of miRNAs are sparse. Similarly, the data for miRNA and disease similarities are sparse. Projecting the miRNA and disease similarities and miRNA node attributes into a common low-dimensional space contributes to estimating miRNA-disease associations. Simultaneously, the possibility that a miRNA is associated with a disease depends on the miRNA’s neighbour information. Therefore, MDAPred deeply integrates projections of multiple kinds of connecting edges, projections of miRNAs node attributes, and neighbour information of miRNAs. The cross-validation results showed that MDAPred achieved superior performance compared to other state-of-the-art methods for predicting disease-miRNA associations. MDAPred can also retrieve more actual miRNA-disease associations at the top of prediction results, which is very important for biologists. Additionally, case studies of breast, lung, and pancreatic cancers further confirmed the ability of MDAPred to discover potential miRNA–disease associations.

Download Full-text

Bootstrapping Entity Alignment with Knowledge Graph Embedding

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/611 ◽

2018 ◽

Cited By ~ 35

Author(s):

Zequn Sun ◽

Wei Hu ◽

Qingheng Zhang ◽

Yuzhong Qu

Keyword(s):

Performance Improvement ◽

Real World ◽

State Of The Art ◽

Graph Embedding ◽

Training Data ◽

Knowledge Graph ◽

Error Accumulation ◽

Knowledge Graphs ◽

Real World Datasets ◽

Low Dimensional

Embedding-based entity alignment represents different knowledge graphs (KGs) as low-dimensional embeddings and finds entity alignment by measuring the similarities between entity embeddings. Existing approaches have achieved promising results, however, they are still challenged by the lack of enough prior alignment as labeled training data. In this paper, we propose a bootstrapping approach to embedding-based entity alignment. It iteratively labels likely entity alignment as training data for learning alignment-oriented KG embeddings. Furthermore, it employs an alignment editing method to reduce error accumulation during iterations. Our experiments on real-world datasets showed that the proposed approach significantly outperformed the state-of-the-art embedding-based ones for entity alignment. The proposed alignment-oriented KG embedding, bootstrapping process and alignment editing method all contributed to the performance improvement.

Download Full-text

Metric Multidimensional Scaling for Large Single-Cell Data Sets using Neural Networks

10.1101/2021.06.24.449725 ◽

2021 ◽

Author(s):

Stefan Canzar ◽

Van Hoan Do ◽

Slobodan Jelic ◽

Soeren Laue ◽

Domagoj Matijevic ◽

...

Keyword(s):

Multidimensional Scaling ◽

Single Cell ◽

State Of The Art ◽

Dimensional Space ◽

Linear Mapping ◽

Alternative Methods ◽

Dimensional Euclidean Space ◽

Data Sets ◽

Metric Multidimensional Scaling ◽

Low Dimensional

Metric multidimensional scaling is one of the classical methods for embedding data into low-dimensional Euclidean space. It creates the low-dimensional embedding by approximately preserving the pairwise distances between the input points. However, current state-of-the-art approaches only scale to a few thousand data points. For larger data sets such as those occurring in single-cell RNA sequencing experiments, the running time becomes prohibitively large and thus alternative methods such as PCA are widely used instead. Here, we propose a neural network based approach for solving the metric multidimensional scaling problem that is orders of magnitude faster than previous state-of-the-art approaches, and hence scales to data sets with up to a few million cells. At the same time, it provides a non-linear mapping between high- and low-dimensional space that can place previously unseen cells in the same embedding.

Download Full-text

Convolutional Gaussian Embeddings for Personalized Recommendation with Uncertainty

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/367 ◽

2019 ◽

Cited By ~ 2

Author(s):

Junyang Jiang ◽

Deqing Yang ◽

Yanghua Xiao ◽

Chenlu Shen

Keyword(s):

State Of The Art ◽

Dimensional Space ◽

Monte Carlo Sampling ◽

Superior Performance ◽

Personalized Recommendation ◽

Latent Features ◽

Benchmark Datasets ◽

Low Dimensional ◽

Uncertain Preferences ◽

Candidate Item

Most of existing embedding based recommendation models use embeddings (vectors) to represent users and items which contain latent features of users and items. Each of such embeddings corresponds to a single fixed point in low-dimensional space, thus fails to precisely represent the users/items with uncertainty which are often observed in recommender systems. Addressing this problem, we propose a unified deep recommendation framework employing Gaussian embeddings, which are proven adaptive to uncertain preferences exhibited by some users, resulting in better user representations and recommendation performance. Furthermore, our framework adopts Monte-Carlo sampling and convolutional neural networks to compute the correlation between the objective user and the candidate item, based on which precise recommendations are achieved. Our extensive experiments on two benchmark datasets not only justify that our proposed Gaussian embeddings capture the uncertainty of users very well, but also demonstrate its superior performance over the state-of-the-art recommendation models.

Download Full-text

Distributed Collaborative Feature Selection Based on Intermediate Representation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/575 ◽

2019 ◽

Cited By ~ 1

Author(s):

Xiucai Ye ◽

Hongmin Li ◽

Akira Imakura ◽

Tetsuya Sakurai

Keyword(s):

Feature Selection ◽

Dimensional Space ◽

Original Data ◽

Intermediate Representation ◽

Selection Methods ◽

Dimensionality Reduction Technique ◽

Selection For ◽

Real World Datasets ◽

Low Dimensional ◽

Row Sparsity

Feature selection is an efficient dimensionality reduction technique for artificial intelligence and machine learning. Many feature selection methods learn the data structure to select the most discriminative features for distinguishing different classes. However, the data is sometimes distributed in multiple parties and sharing the original data is difficult due to the privacy requirement. As a result, the data in one party may be lack of useful information to learn the most discriminative features. In this paper, we propose a novel distributed method which allows collaborative feature selection for multiple parties without revealing their original data. In the proposed method, each party finds the intermediate representations from the original data, and shares the intermediate representations for collaborative feature selection. Based on the shared intermediate representations, the original data from multiple parties are transformed to the same low dimensional space. The feature ranking of the original data is learned by imposing row sparsity on the transformation matrix simultaneously. Experimental results on real-world datasets demonstrate the effectiveness of the proposed method.

Download Full-text