Theodoros Tsiligkaridis, Huan He, Teddy Koker, Owen Queen, Consuelo Cuevas, M. Zitnik
We lifted 17 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| mims-harvard/Raincoat | canonical | 12 of 17 |
| Function | Status | Where it lives |
|---|---|---|
| EntropyLoss | Ran | mims-harvard/Raincoat/models/loss.py code served (permissive licence) · get_code("0cb7cfb326eed8be") |
| compl_mul1d | Ran | mims-harvard/Raincoat/models/sinkhorn_vis.py code served (permissive licence) · get_code("0e947636863e658a") |
| data_generator | Ran | mims-harvard/Raincoat/dataloader/dataloader.py code served (permissive licence) · get_code("452e418f86055a6e") |
| few_shot_data_generator | Ran | mims-harvard/Raincoat/dataloader/dataloader.py code served (permissive licence) · get_code("e1ca084ee48a2eed") |
| generator_percentage_of_data | Ran | mims-harvard/Raincoat/dataloader/dataloader.py code served (permissive licence) · get_code("576f86eb9d3d208b") |
| get_dev_value | Ran | mims-harvard/Raincoat/algorithms/utils.py code served (permissive licence) · get_code("20778da824d806b5") |
| get_iwcv_value | Ran | mims-harvard/Raincoat/algorithms/utils.py code served (permissive licence) · get_code("e285d60da7bd42cc") |
| jitter | Ran | mims-harvard/Raincoat/models/augmentations.py code served (permissive licence) · get_code("17fb0ac3baafb100") |
| open_entropy | Ran | mims-harvard/Raincoat/models/loss.py code served (permissive licence) · get_code("62e430d298d27ab3") |
| ova_loss | Ran | mims-harvard/Raincoat/models/loss.py code served (permissive licence) · get_code("dff3864912382b7a") |
| scaling | Ran | mims-harvard/Raincoat/models/augmentations.py code served (permissive licence) · get_code("62ae42ac3fdc85c6") |
| starting_logs | Ran | mims-harvard/Raincoat/algorithms/utils.py code served (permissive licence) · get_code("7c583e1ae26f9263") |
| get_algorithm_class | Not yet run | mims-harvard/Raincoat/algorithms/algorithms.py code served (permissive licence) · get_code("b0bc80b1655a6802") |
| get_backbone_class | Not yet run | mims-harvard/Raincoat/models/models.py code served (permissive licence) · get_code("f8ac075efb28ded9") |
| get_dataset_class | Not yet run | mims-harvard/Raincoat/configs/data_model_configs.py code served (permissive licence) · get_code("8dadd34c7426858e") |
| get_hparams_class | Not yet run | mims-harvard/Raincoat/configs/hparams.py code served (permissive licence) · get_code("87db44cd0a18316c") |
| permutation | Not yet run | mims-harvard/Raincoat/models/augmentations.py code served (permissive licence) · get_code("d09725912eaa13b1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Unsupervised domain adaptation (UDA) enables the transfer of models trained on source domains to unlabeled target domains. However, transferring complex time series models presents challenges due to the dynamic temporal structure variations across domains. This leads to feature shifts in the time and frequency representations. Additionally, the label distributions of tasks in the source and target domains can differ significantly, posing difficulties in addressing label shifts and recognizing labels unique to the target domain. Effectively transferring complex time series models remains a formidable problem. We present RAINCOAT, the first model for both closed-set and universal domain adaptation on complex time series. RAINCOAT addresses feature and label shifts by considering both temporal and frequency features, aligning them across domains, and correcting for misalignments to facilitate the detection of private labels. Additionally, RAINCOAT improves transferability by identifying label shifts in target domains. Our experiments with 5 datasets and 13 state-of-the-art UDA methods demonstrate that RAINCOAT can improve transfer learning performance by up to 16.33% and can handle both closed-set and universal domain adaptation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.03133")
get_code_for_paper("2302.03133")
have("2302.03133")
Connect an agent — have() is free.