en
0.25
0.5
0.75
1.25
1.5
1.75
2
Learning Recommendations in Social Media Systems By Weighting Multiple Relations
Published on Oct 03, 20112825 Views
We address the problem of item recommendation in social media sharing systems. We adopt a multi-relational framework capable to integrate different entity types available in the social media system an
Related categories
Chapter list
Learning Recommendations in Social Media Systems By Weighting Multiple Relations00:00
Outline (1)00:30
Social media sharing01:37
Image tagging and tag recommendation03:03
Flickr world06:09
Flickr example07:21
Tag recommendation08:25
Prior Art09:47
Outline (2)10:46
Relational graph10:48
Outline (3)11:37
Random walk model11:38
Relational random walk model13:30
Outline (4)15:07
Relational weight learning15:09
Loss function16:29
Optimization problem17:36
Hessian matrix18:27
Outline (5)19:17
Evaluation19:22
Flickr dataset20:30
Experiment setting22:12
Alternative loss functions24:03
Tag recommendation (1)24:39
Tag recommendation (2)25:53
Resetting coefficient effect27:03
Impact of iteration number27:52
Lessons learned (Conclusion)28:44
Thank you!33:09