shenweichen / DeepCTR-Torch

【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.
https://deepctr-torch.readthedocs.io/en/latest/index.html
Apache License 2.0
2.95k stars 696 forks source link

Add multi-task models: SharedBottom, ESMM, MMOE, PLE #260

Closed shenweichen closed 1 year ago

shenweichen commented 1 year ago
  1. Add multi-task models: SharedBottom, ESMM, MMOE, PLE Closes #229
  2. Bugfix:
    Closes #240 Closes #232
  3. support py3.9 3.10
codecov[bot] commented 1 year ago

Codecov Report

Base: 92.31% // Head: 92.56% // Increases project coverage by +0.25% :tada:

Coverage data is based on head (70aa7ab) compared to base (2cd84f3). Patch coverage: 93.16% of modified lines in pull request are covered.

Additional details and impacted files ```diff @@ Coverage Diff @@ ## master #260 +/- ## ========================================== + Coverage 92.31% 92.56% +0.25% ========================================== Files 30 30 Lines 2069 2274 +205 ========================================== + Hits 1910 2105 +195 - Misses 159 169 +10 ``` | Flag | Coverage Δ | | |---|---|---| | pytest | `92.56% <93.16%> (+0.25%)` | :arrow_up: | Flags with carried forward coverage won't be shown. [Click here](https://docs.codecov.io/docs/carryforward-flags?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#carryforward-flags-in-the-pull-request-comment) to find out more. | [Impacted Files](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6) | Coverage Δ | | |---|---|---| | [deepctr\_torch/models/basemodel.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvYmFzZW1vZGVsLnB5) | `86.45% <87.50%> (+1.35%)` | :arrow_up: | | [deepctr\_torch/models/multitask/esmm.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvbXVsdGl0YXNrL2VzbW0ucHk=) | `90.24% <90.24%> (ø)` | | | [deepctr\_torch/models/multitask/sharedbottom.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvbXVsdGl0YXNrL3NoYXJlZGJvdHRvbS5weQ==) | `91.30% <91.30%> (ø)` | | | [deepctr\_torch/models/multitask/mmoe.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvbXVsdGl0YXNrL21tb2UucHk=) | `92.53% <92.53%> (ø)` | | | [deepctr\_torch/models/multitask/ple.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvbXVsdGl0YXNrL3BsZS5weQ==) | `95.87% <95.87%> (ø)` | | | [deepctr\_torch/models/dcnmix.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvZGNubWl4LnB5) | `86.36% <100.00%> (-2.01%)` | :arrow_down: | | [deepctr\_torch/models/dien.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvZGllbi5weQ==) | `97.23% <100.00%> (ø)` | | | [deepctr\_torch/models/fibinet.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvZmliaW5ldC5weQ==) | `89.79% <100.00%> (ø)` | | | [deepctr\_torch/models/autoint.py](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6#diff-ZGVlcGN0cl90b3JjaC9tb2RlbHMvYXV0b2ludC5weQ==) | `93.87% <0.00%> (-1.96%)` | :arrow_down: | | ... and [5 more](https://codecov.io/gh/shenweichen/DeepCTR-Torch/pull/260/diff?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6) | | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=%E6%B5%85%E6%A2%A6)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.