DeepWalk: Online Learning of Social Representations thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

DeepWalk: Online Learning of Social Representations

Published on Oct 07, 20144311 Views

We present DeepWalk, a novel approach for learning latent representations of vertices in a network. These latent representations encode social relations in a continuous vector space, which is easily e

Related categories

Chapter list

DeepWalk: Online Learning of Social Representations00:00
Outline - 100:11
Features From Graphs00:16
What is a Graph Representation?01:08
DeepWalk01:34
Visual Example01:47
Advantages of DeepWalk02:17
Outline - 202:46
Language Modeling02:49
World of Word Embeddings03:29
Word Frequency in Natural Language03:50
Connection: Power Laws04:03
Vertex Frequency in SFG04:11
The Cool Idea04:46
Outline - 304:54
Deep Learning for Networks - 104:55
Deep Learning for Networks - 205:10
Random Walks05:12
Deep Learning for Networks - 305:25
Deep Learning for Networks - 405:27
Deep Learning for Networks - 506:10
Hierarchical Softmax06:12
Learning07:22
Deep Learning for Networks - 607:47
Outline - 407:48
Attribute Prediction07:51
Baselines08:30
Results: BlogCatalog09:01
Results: Flickr09:44
Results: YouTube10:05
Parallelization10:28
Outline - 511:05
Variants / Future Work11:07
Take-away11:57
Thanks!12:07