Proceedings of the 28th ACM International Conference on Information and Knowledge Management 2019
DOI: 10.1145/3357384.3357879
|View full text |Cite
|
Sign up to set email alerts
|

Fast and Accurate Network Embeddings via Very Sparse Random Projection

Abstract: We present FastRP, a scalable and performant algorithm for learning distributed node representations in a graph. FastRP is over 4,000 times faster than state-of-the-art methods such as DeepWalk and node2vec, while achieving comparable or even better performance as evaluated on several real-world networks on various downstream tasks. We observe that most network embedding methods consist of two components: construct a node similarity matrix and then apply dimension reduction techniques to this matrix. We show t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
22
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
3

Relationship

1
7

Authors

Journals

citations
Cited by 56 publications
(22 citation statements)
references
References 30 publications
(42 reference statements)
0
22
0
Order By: Relevance
“…Recently, sketching-based techniques have been explored for generating node embeddings of large networks. Chen et al [36] proposed an algorithm for computing node embedding of large networks using very sparse random projections [37]. FREDE [38] generates linear space embedding of nodes using deterministic matrix sketching [39], and InstantEmbedding [40] computes node embedding using local PageRank computation.…”
Section: Related Workmentioning
confidence: 99%
“…Recently, sketching-based techniques have been explored for generating node embeddings of large networks. Chen et al [36] proposed an algorithm for computing node embedding of large networks using very sparse random projections [37]. FREDE [38] generates linear space embedding of nodes using deterministic matrix sketching [39], and InstantEmbedding [40] computes node embedding using local PageRank computation.…”
Section: Related Workmentioning
confidence: 99%
“…It then obtains an updated embedding vector of 𝑠 by the following three steps: 1) It first updates the estimate vector 𝒑 𝑡 𝑠 and 𝒓 𝑡 𝑠 from Line 2 to Line 9; 2) It then calls the forward local push method to obtain the updated estimations, 𝒑 𝑡 𝑠 ; 3) We then use the hash kernel projection step to get an updated embedding. This projection step is from InstantEmbedding where two universal hash functions are defined as ℎ 𝑑 : N → [𝑑] and ℎ sgn : N → {±1} 6 . Then the hash kernel based on these two hash functions is defined as 𝐻 ℎ sgn ,ℎ 𝑑 (𝒙) : R 𝑛 → R 𝑑 where each entity 𝑖 is 𝑗 ∈ℎ −1 𝑑 (𝑖) 𝑥 𝑗 ℎ sgn ( 𝑗).…”
Section: Dynamic Graph Embedding For Single Batchmentioning
confidence: 99%
“…Then the hash kernel based on these two hash functions is defined as 𝐻 ℎ sgn ,ℎ 𝑑 (𝒙) : R 𝑛 → R 𝑑 where each entity 𝑖 is 𝑗 ∈ℎ −1 𝑑 (𝑖) 𝑥 𝑗 ℎ sgn ( 𝑗). Different from random projection used in RandNE [47] and FastRP [6], hash functions has O (1) memory cost while random projection based method has O (𝑑𝑛) if the Gaussian matrix is used. Furthermore, hash kernel keeps unbiased estimator for the inner product [42].…”
Section: Dynamic Graph Embedding For Single Batchmentioning
confidence: 99%
“…There are several variants of random projection techniques for manifold and network learning [14,20]. Recently, RandNE [34] and FastRP [3] are proposed to capture high-order structure information of homogeneous network by Gaussian random projection and sparse random projection, respectively. However, these methods ignore the heterogeneity and attributes of nodes and relations, and thus cannot capture the rich semantics on AMHENs.…”
Section: Related Workmentioning
confidence: 99%
“…The product attributes include the price, sales-rank, brand, category, etc. AMiner dataset 3 contains three types of nodes: author, paper and conference. The domain of papers is considered as the class label.…”
Section: Experiments 51 Datasetsmentioning
confidence: 99%