Network representation learning: models, methods and applications

Mohan, Anuraj; Pramod, K Varshney

doi:10.1007/s42452-019-1044-9

Cited by 11 publications

(8 citation statements)

References 115 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a machine learning paradigm, incremental learning takes place whenever a change in an information network is detected, which means the need to adjust what was learned by the current model in accordance with the new arrived or removed data. 68 In incremental learning, there is not sufficient training data as they appear over time, which means a partial update in the learning model. Recent incremental learning methods include matrix factorization models (e.g., ISVD, 69 IRMF 70 ), metapath-based models (e.g., metapath2vec, 71 LIME 72 ), and GNN model.…”

Section: Design Of Incremental Multi-view Embeddingmentioning

confidence: 99%

“…Aiming to solve the above challenges, incremental learning 68 is applied, as a solution to help autonomic managers ignore obsolete knowledge (e.g., useless management policies) and equip the BSKG with updated knowledge (e.g., newly added management policies, latest QoS levels, new substituting services, etc.). Next, we start by modeling the captured changes on the managed BSKG.…”

Section: Big Service Knowledge Graphmentioning

confidence: 99%

See 1 more Smart Citation

Autonomic computing and incremental learning for the management of big services

Ghedass

Charrada

2023

Softw Pract Exp

View full text Add to dashboard Cite

Recent years have witnessed the emergence of big services, as a large‐scale big data‐centric service model, that resulted from the synergy between powerful computing paradigms (big data processing, service and cloud computing, Internet of Things, etc.). Big services are seen as a heterogeneous combination of physical and virtualized domain‐specific resources, with a huge volume of data and complex functionalities, all encapsulated and offered as services. This complexity of big services (composition units' heterogeneity, cross‐domain orientation, data massiveness), coupled with other environmental factors (cloud dynamicity, providers' policies, customer requirements) makes their management tasks beyond humans' capability. Therefore, endowing big service ecosystems with self‐adaptive behavior is a natural solution. To achieve this goal, this article models big services as autonomic computing systems, and structures their behavioral aspects (functional behavior, quality of service/data levels, management policies) as a multi‐view knowledge graph. To infer useful knowledge (e.g., conflicts between policies) for the autonomic big service's management tasks, we process the big service's knowledge graph (BSKG) via a graph neural network‐based graph embedding model. This latter is reinforced by an incremental learning method, that helps capturing the big services' frequent changes (e.g., QoS deviations, service failures, new policies), and drives autonomic managers to continuously update and enrich their knowledge w.r.t. the managed big service's current state. Finally, a flexible decision mechanism explores the BSKG structure and the latent knowledge, to locate and trigger the appropriate management policies, according to the big service's produced events.

show abstract

Section: Design Of Incremental Multi-view Embeddingmentioning

confidence: 99%

Section: Big Service Knowledge Graphmentioning

confidence: 99%

Autonomic computing and incremental learning for the management of big services

Ghedass

Charrada

2023

Softw Pract Exp

View full text Add to dashboard Cite

show abstract

“…There have been various studies for learning representations of networks and entities in the networks (e.g., nodes, edges, substructures, etc.) [28][29][30]. Also, there have been various network embedding methods [31][32][33][34] that exhibited the state-of-the-art performance.…”

Section: The Character Network Is a Representation Of Relationships Bmentioning

confidence: 99%

Learning Hierarchical Representations of Stories by Using Multi-Layered Structures in Narrative Multimedia

Lee

Jung

Kim

2020

Sensors

View full text Add to dashboard Cite

Narrative works (e.g., novels and movies) consist of various utterances (e.g., scenes and episodes) with multi-layered structures. However, the existing studies aimed to embed only stories in a narrative work. By covering other granularity levels, we can easily compare narrative utterances that are coarser (e.g., movie series) or finer (e.g., scenes) than a narrative work. We apply the multi-layered structures on learning hierarchical representations of the narrative utterances. To represent coarser utterances, we consider adjacency and appearance of finer utterances in the coarser ones. For the movies, we suppose a four-layered structure (character roles ∈ characters ∈ scenes ∈ movies) and propose three learning methods bridging the layers: Char2Vec, Scene2Vec, and Hierarchical Story2Vec. Char2Vec represents a character by using dynamic changes in the character’s roles. To find the character roles, we use substructures of character networks (i.e., dynamic social networks of characters). A scene describes an event. Interactions between characters in the scene are designed to describe the event. Scene2Vec learns representations of a scene from interactions between characters in the scene. A story is a series of events. Meanings of the story are affected by order of the events as well as their content. Hierarchical Story2Vec uses sequential order of scenes to represent stories. The proposed model has been evaluated by estimating the similarity between narrative utterances in real movies.

show abstract

“…Network representation learning aims to learn the representations of network nodes so that these learned representations can be expressed as latent, informative, and low-dimensional vectors while preserving the network topology, node features, labels, and other auxiliary information [24,31]. These generated vectors can support a wide range of downstream tasks most effectively, such as node classification [15,21,42], link prediction [4,48] and recommendation [43].…”

Section: Introductionmentioning

confidence: 99%

A novel message passing neural network based on neighborhood expansion

Xue

Jin

Apasiba³

2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Most message passing neural networks (MPNNs) are widely used for assortative network representation learning under the assumption of homophily between connected nodes. However, this fundamental assumption is inconsistent with the heterophily of disassortative networks (DNs) in many real-world applications. Therefore, we propose a novel MPNN called NEDA based on neighborhood expansion for disassortative network representation learning (DNRL). Specifically, our NEDA first performs neighborhood expansion to seek more informative nodes for aggregation and then performs data augmentation to speed up the optimization process of a set of parameter matrices at the maximum available training data with minimal computational cost. To evaluate the performance of NEDA comprehensively, we perform several experiments on benchmark disassortative network datasets with variable sizes, where the results demonstrate the effectiveness of our NEDA model. The code is publicly available at https://github.com/xueyanfeng/NEDA.

show abstract

Network representation learning: models, methods and applications

Cited by 11 publications

References 115 publications

Autonomic computing and incremental learning for the management of big services

Autonomic computing and incremental learning for the management of big services

Learning Hierarchical Representations of Stories by Using Multi-Layered Structures in Narrative Multimedia

A novel message passing neural network based on neighborhood expansion

Contact Info

Product

Resources

About