0.25
0.5
0.75
1.25
1.5
1.75
2
Mining All Non-Derivable Frequent Itemsets
Published on Oct 29, 20123194 Views
All frequent itemset mining algorithms rely heavily on the monotonicity principle for pruning. This principle allows for excluding candidate itemsets from the expensive counting phase. In this paper,
Related categories
Chapter list
Mining All Non‐Derivable Frequent Itemset00:00
Outline - 100:08
Association Rules01:12
Situtation Early 2000´s - 102:39
Situtation Early 2000´s - 203:19
Situtation Early 2000´s - 304:50
Condensed Representations - 106:29
Condensed Representations - 207:44
Outline - 208:24
200208:37
Redundancies - 108:53
Redundancies - 209:55
Redundancies - 311:25
Goal13:59
Outline - 315:17
The Inclusion - Exclusion Principle15:35
Deduction Rules via Inclusion - Exclusion - 119:01
Deduction Rules via Inclusion - Exclusion - 220:24
Complete Set for sup(abc)20:48
Example: Deduction Rules - 122:06
Example: Deduction Rules - 222:23
Example: Deduction Rules - 322:25
Example: Deduction Rules - 422:32
Example: Deduction Rules - 522:33
Main Theorem23:25
Example: Completeness - 125:18
Example: Completeness - 225:42
Example: Completeness - 325:51
Derivable Itemsets - 126:17
Derivable Itemsets - 226:55
Example: Derivable Itemsets - 127:10
Example: Derivable Itemsets - 227:34
Example: Derivable Itemsets - 327:41
Derivable Itemsets - 328:16
Algorithm31:22
Optimization32:38
Quick Inclusion - Exclusion - 133:15
Quick Inclusion - Exclusion - 234:25
Quick Inclusion - Exclusion - 336:17
Evaluation - Empirically37:04
Comparison - 138:04
Comparison - 240:13
Comparison - 340:23
Influence of Rule Depth41:13
Evaluation41:54
Outline - 442:59
Illustrative Example: Tiles - 144:01
Illustrative Example: Tiles - 245:14
Illustrative Example: Tiles - 346:50
Statistical Approach47:35
Model 1: Swap Randomization48:08
MaxEntropy Based Models49:01
Minimal Description Length - 150:28
Minimal Description Length - 252:13
Conclusion - 152:30
Conclusion - 253:22
Future?53:37