Name
Abstract | ||
|---|---|---|
We propose methods for distributed graph-based multi-task learning that are based on weighted averaging of messages from other machines. Uniform averaging or diminishing stepsize in these methods would yield consensus (single task) learning. We show how simply skewing the averaging weights or controlling the stepsize allows learning different, but related, tasks on the different machines. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Machine Learning | Graph,Multi-task learning,Theoretical computer science,Graph regularization,Artificial intelligence,Machine learning,Mathematics |
DocType | Volume | Citations |
Journal | abs/1802.03830 | 1 |
PageRank | References | Authors |
0.35 | 18 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weiran Wang | 1 | 114 | 9.99 |
| Jialei Wang | 2 | 77 | 10.29 |
| Mladen Kolar | 3 | 202 | 23.44 |
| Nathan Srebro | 4 | 3892 | 349.42 |