About: DDNE: Discriminative Distance Metric Learning for Network Embedding

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: DDNE: Discriminative Distance Metric Learning for Network Embedding Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	DDNE: Discriminative Distance Metric Learning for Network Embedding
Creator	Li, Jing Li, Xiaoxue Cheng, Jie Li, Yangxi Shang, Yanmin Tong, Lingling Yin, Pengfei
Source	PMC
abstract	Network embedding is a method to learn low-dimensional representations of nodes in networks, which aims to capture and preserve network structure. Most of the existing methods learn network embedding based on distributional similarity hypothesis while ignoring adjacency similarity property, which may cause distance bias problem in the network embedding space. To solve this problem, this paper proposes a unified framework to encode distributional similarity and measure adjacency similarity simultaneously, named DDNE. The proposed DDNE trains a siamese neural network which learns a set of non-linear transforms to project the node pairs into the same low-dimensional space based on their first-order proximity. Meanwhile, a distance constraint is used to make the distance between a pair of adjacent nodes smaller than a threshold and that of each non-adjacent nodes larger than the same threshold, which highlight the adjacency similarity. We conduct extensive experiments on four real-world datasets in three social network analysis tasks, including network reconstruction, attribute prediction and recommendation. The experimental results demonstrate the competitive and superior performance of our approach in generating effective network embedding vectors over baselines.
has issue date	2020-05-26(xsd:dateTime)
bibo:doi	10.1007/978-3-030-50371-0_42
has license	no-cc
sha1sum (hex)	8352290bedbebc51bf4c9eceac528c2e3d023b20
schema:url	https://doi.org/10.1007/978-3-030-50371-0_42
resource representing a document's title	DDNE: Discriminative Distance Metric Learning for Network Embedding
has PubMed Central identifier	PMC7302248
schema:publication	Computational Science - ICCS 2020
resource representing a document's body	covid:8352290bedbebc51bf4c9eceac528c2e3d023b20#body_text
is schema:about of	named entity 'pair' named entity 'aims' named entity 'distance' named entity 'conduct' named entity 'attribute' named entity 'distance' named entity 'Metric' named entity 'Distance' named entity 'Embedding' named entity 'NETWORK STRUCTURE' named entity 'ADJACENCY' named entity 'CAPTURE' named entity 'DISTANCE' named entity 'SIMULTANEOUSLY' named entity 'SMALLER' covid:arg/8352290bedbebc51bf4c9eceac528c2e3d023b20 named entity 'threshold' named entity 'nodes' named entity 'distance' named entity 'experimental' named entity 'siamese' named entity 'representations' named entity 'problem' named entity 'network' named entity 'network' named entity 'Random Walk' named entity 'score function' named entity 'first-order' named entity 'cosine similarity' named entity 'hidden layers' named entity 'auto-encoder' named entity 'vector' named entity 'feature space' named entity 'network structure' named entity 'vector' named entity 'CNN' named entity 'representation learning' named entity 'vectors' named entity 'distributed representation' named entity 'residual network' named entity 'deep learning' named entity 'probability' named entity 'first-order' named entity 'vectors' named entity 'adjacency relation' named entity 'citation network' named entity 'constellation' named entity 'neural network models' named entity 'adjacency relation' named entity '2.0' named entity 'Distance Metric' named entity 'network structure' named entity 'word embedding' named entity 'data set' named entity 'non-linear' named entity 'proximity' named entity 'nodes' named entity 'demonstrate' named entity 'encode' named entity 'real-world' named entity 'non-adjacent' named entity 'neural network' named entity 'Discriminative' named entity 'existing' named entity 'vector' named entity 'DBLP' named entity 'biased random walk' named entity 'metric learning' named entity 'topology' named entity 'network structure' named entity 'neural network' named entity 'vector' named entity 'objective functions' named entity 'matrix factorization' named entity 'neural network' named entity 'low-dimensional' named entity 'DBLP'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software