The 18th European Conference on Machine Learning (ECML) and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD)

Random k-Labelsets: An Ensemble Method for Multilabel Classification

author: Grigorios Tsoumakas, Aristotle University of Thessaloniki

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Random k-Labelsets: An Ensemble Approach for Multilabel Classification
0:09	What is Multilabel Classification?
0:48	Examples of Multilabel Data (1)
0:57	Examples of Multilabel Data (2)
1:12	Examples of Multilabel Data (3)
1:19	Examples of Multilabel Data (4)
1:21	Examples of Multilabel Data (5)
1:24	Examples of Multilabel Data (6)
1:32	Examples of Multilabel Data (7)
1:53	Examples of Multilabel Data (8)
2:00	A Categorization of Multilabel Classification Methods (1)
2:45	A Categorization of Multilabel Classification Methods (2)
2:56	Binary Relevance (BR)
3:32	Label Powerset (LP)
4:30	The RAKEL Algorithm
5:47	Ensemble Production
7:13	Ensemble Combination
8:00	Computational Complexity
9:19	Evaluation Measures
10:12	Example-based Measures
10:37	Label-based Measures
11:12	Datasets
13:06	Methods, algorithms and evaluation
13:54	Results for t=0.5 (1)
14:47	Results for t=0.5 (2)
15:04	Results across all t values (1)
15:34	Results across all t values (2)
16:09	Results after parameter selection (1)
16:57	Results after parameter selection (2)
17:35	Results for t=0.5 (1)
18:25	Results for t=0.5 (2)
18:51	Results for t=0.5 (1)
19:03	Results for t=0.5 (2)
19:17	Results across all t values (1)
19:32	Results across all t values (2)
19:38	Results after parameter selection (1)
19:56	Results after parameter selection (2)
20:10	Results for t=0.5 (1)
20:37	Results for t=0.5 (2)
20:43	Results across all t values (1)
20:59	Results across all t values (2)
21:04	Results after parameter selection (1)
21:22	Results after parameter selection (2)
21:39	Recap, Take Away and Future Work
23:18	http://mlkd.csd.auth.gr/multilabel.html
24:00	Thank you for your attention!

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.