Space-Invariant Projection in Streaming Network Embedding
Not on the map. Why?
Abstract (arXiv)
Newly arriving nodes in dynamics networks would gradually make the node embedding space drifted and the retraining of node embedding and downstream models indispensable. An exact threshold size of these new nodes, below which the node embedding space will be predicatively maintained, however, is rarely considered in either theory or experiment. From the view of matrix perturbation theory, a threshold of the maximum number of new nodes that keep the node embedding space approximately equivalent is analytically provided and empirically validated. It is therefore theoretically guaranteed that as the size of newly arriving nodes is below this threshold, embeddings of these new nodes can be quickly derived from embeddings of original nodes. A generation framework, Space-Invariant Projection (SIP), is accordingly proposed to enables arbitrary static MF-based embedding schemes to embed new nodes in dynamics networks fast. The time complexity of SIP is linear with the network size. By combining SIP with four state-of-the-art MF-based schemes, we show that SIP exhibits not only wide adaptability but also strong empirical performance in terms of efficiency and efficacy on the node classification task in three real datasets.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 76 references that are in the map. First posted on arXiv 11 Mar 2023.
Builds on
29 of 76 references.
References · 29
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2015LINE: Large-scale Information Network Embeddingcited by 582
- 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 198
- 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
- 2018DynGEM: Deep Embedding Method for Dynamic Graphscited by 102
- 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
- 2018dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learningcited by 88
- 2020Knowledge Graph Embedding for Link Prediction: A Comparative Analysiscited by 85
- 2020Streaming Graph Neural Networks via Continual Learningcited by 64
17 more
- 2021A Survey on Embedding Dynamic Graphscited by 60
- 2021Dynamic Network Embedding Surveycited by 44
- 2017Attributed Network Embedding for Learning in a Dynamic Environmentcited by 39
- 2018dynnode2vec: Scalable Dynamic Network Embeddingcited by 32
- 2018Billion-scale Network Embedding with Iterative Random Projectioncited by 25
- 2014Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorizationcited by 21
- 2017TIMERS: Error-Bounded SVD Restart on Dynamic Networkscited by 19
- 2021Network Representation Learning: From Preprocessing, Feature Extraction to Node Embeddingcited by 19
- 2022SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendationcited by 16
- 2019Efficient Representation Learning Using Random Walks for Dynamic Graphscited by 9
- 2022Robust Knowledge Adaptation for Dynamic Graph Neural Networkscited by 9
- 2018Out-of-sample extension of graph adjacency spectral embeddingcited by 8
- 2020GloDyNE: Global Topology Preserving Dynamic Network Embeddingcited by 8
- 2020Time-aware Graph Embedding: A temporal smoothness and task-oriented approachcited by 6
- 2019Dynamic Network Embedding via Incremental Skip-gram with Negative Samplingcited by 4
- 2020Neural graph embeddings as explicit low-rank matrix factorization for link predictioncited by 4
- 2018A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Gamescited by 3
Built on by
Not cited yet.