Difference between revisions of "MyMediaLite/Workshop projects"
Jump to navigation
Jump to search
Zeno Gantner (talk | contribs) (Created page with "Some projects you could work on. == Visualization == * [https://github.com/zenogantner/MyMediaLite/issues/45 evaluation graphs] * dataset visualization == Input Formats == * SQ...") |
Zeno Gantner (talk | contribs) |
||
| Line 13: | Line 13: | ||
== Algorithms == | == Algorithms == | ||
| + | * [http://en.wikipedia.org/wiki/Dice%27s_coefficient Dice's coefficient] | ||
| + | * [http://en.wikipedia.org/wiki/Tversky_index Tyversky index] | ||
* [https://github.com/zenogantner/MyMediaLite/issues/222 Jaccard index for binary feedback data] | * [https://github.com/zenogantner/MyMediaLite/issues/222 Jaccard index for binary feedback data] | ||
| − | * | + | * similarity based on the [[Euclidean distance]] |
| − | * | + | * [https://github.com/zenogantner/MyMediaLite/issues/68 factor-based similarity] |
| − | * fold-in for WRMF | + | * [https://github.com/zenogantner/MyMediaLite/issues/269 fold-in for WRMF] |
| − | |||
* [https://github.com/zenogantner/MyMediaLite/issues/120 BPR-kNN] | * [https://github.com/zenogantner/MyMediaLite/issues/120 BPR-kNN] | ||
* [https://github.com/zenogantner/MyMediaLite/issues/43 determine the learn rate for SGD] | * [https://github.com/zenogantner/MyMediaLite/issues/43 determine the learn rate for SGD] | ||
| + | * [https://github.com/zenogantner/MyMediaLite/issues/207 SGD learning for WRMF] | ||
* [https://github.com/zenogantner/MyMediaLite/issues/82 ALS-based matrix factorization] | * [https://github.com/zenogantner/MyMediaLite/issues/82 ALS-based matrix factorization] | ||
* [https://github.com/zenogantner/MyMediaLite/issues/135 k-means clustering of users and/or items] | * [https://github.com/zenogantner/MyMediaLite/issues/135 k-means clustering of users and/or items] | ||
Revision as of 17:56, 6 September 2012
Some projects you could work on.
Contents
Visualization
- evaluation graphs
- dataset visualization
Input Formats
- SQLite
Parallelization
- parallel similarity computation
- !!!'naive' parallel learning for BPR-MF
Algorithms
- Dice's coefficient
- Tyversky index
- Jaccard index for binary feedback data
- similarity based on the Euclidean distance
- factor-based similarity
- fold-in for WRMF
- BPR-kNN
- determine the learn rate for SGD
- SGD learning for WRMF
- ALS-based matrix factorization
- k-means clustering of users and/or items
- Eigentaste 5.0
- integrating TrueSkill
- your favorite algorithm
- some algorithm from this year's conference or its workshops
Evaluation
- expected reciprocal rank
- Kendall's Tau
- Spearman rank coefficient
- add fold-in evaluation to the command-line tools
- your favorite missing evaluation protocol or measure
Item Recommendation
Under the Hood
- !!! experiment with Math.Net Numerics matrix data types
Compatibility
- Comparing abstractions and APIs in LensKit, Mahout, and MyMediaLite
- data models and storage
- rating scales
- recommenders
- training and updates
- correlations and similarities
- evaluation protocols
- handling of attributes and relations
- portability and interfacing
