Please enable JavaScript.
Coggle requires JavaScript to display documents.
Node Embeddings <3 (Ideas, Nice to Haves (Performance on Adversarial…
Node Embeddings <3
Ideas, Nice to Haves
-
-
-
-
Interpretable Non-Linear (Deep Learning based) models [1], [2]
-
-
-
Dynamic, Temporal Graphs [2]
Discover, not pre decide Candidate Subgraphs [2]
-
use multiple neighbours by taking 2,1,0 everywhere and use loss function from stanford paper
-
Literature
Factorization Based
-
Laplacian Eigenmaps [1], [2]
Earliest, DEC(zi,zj)=||zi-zj||^2), L=SUM(DEC(zi,zj)*sg(vi,vj)))
-
-
Graph Factorization (GF) [1], [2]
HOPE, GF, GraRep are inner product based -> DEC(zi,zj)=ziTzj
Proximity measure Aij
GraRep [1],[2]
HOPE, GF, GraRep are inner product based -> DEC(zi,zj)=ziTzj
Proximity measure Aij, Aij^2, ..., Aij^k
HOPE [1],[2]
HOPE, GF, GraRep are inner product based -> DEC(zi,zj)=ziTzj
general Proximity measure
Random Walk Based
DeepWalk [1], [2]
direct encoding, decoder based on inner product, approximate loss with hierarchical softmax to compute norm. factor, binary tree structure for acceleration
Node2Vec [1], [2]
direct encoding, decoder based on inner product approximate loss with negative sampling
Hierarchical Representation Learning for Networks (HARP) [1], [2]
graph preprocessing, collapse related nodes into supernodes, then other Random Walk based method
Walklets [1]
Combine idea of explicit modelling (Fact. Based) and random walks, Modifies DeepWalk by skipping nodes, Performed in different skip lengths, analogous to factorizing Ak in GraRep, Results are used to train similar to DeepWalk
-
Other
LINE
Two encoder-decoder objectives that optim "first order" and "second order" graph proximity respectively
use decoder based on sigmoid
- proximity sg(vi,vj)=Aij
- proximity two hop adjacency neighborhoods
-
-
-
-
-
-
-
-