Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of pytorch-frame

pytorch-frame - 0.2.5: Python 3.13 and PyTorch 2.6 support

What's Changed

  • Add support for PyTorch 2.6 by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/494
  • Support Python 3.12 and Python 3.13 by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/496
  • Add copy button for code in docs by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/489
  • CI: Consolidate unit test CI workflows by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/493
  • CI: Add concurrency to workflows triggered on PRs by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/495
  • Let pre-commit fix formatting issue in master by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/498
  • Automate package build and release by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/497
  • Fix auto-merging bot PRs by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/501
  • lint: switch pyupgrade to Ruff's rule UP by @Borda in https://github.com/pyg-team/pytorch-frame/pull/499
  • Prepare 0.2.5 release by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/502

New Contributors

  • @Borda made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/499

Full Changelog: https://github.com/pyg-team/pytorch-frame/compare/0.2.4...0.2.5

- Python
Published by akihironitta over 1 year ago

pytorch-frame - PyTorch Frame 0.2.4

What's Changed

  • fix multicategorical stype inference and add test case by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/420
  • coorectly infer boolean stypes by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/421
  • support xgboost early stopping by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/424
  • Update testing torch version by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/428
  • Update Excelformer benchmark results on small binary and regression tasks by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/427
  • update xgboost numbers by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/425
  • Update excelformer benchmark results by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/431
  • Remove CUDA synchronizations by slicing input tensor with int instead of CUDA tensors in nn.LinearEmbeddingEncoder by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/432
  • Don't put assertions on N/A imputation correctness by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/433
  • Don't create the same tensor every iteration in N/A handling by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/434
  • chore: Update pre-commit by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/435
  • Add benchmark results for large-scale multiclass classification task by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/436
  • Fixed warning and added safe globals by @NeelKondapalli in https://github.com/pyg-team/pytorch-frame/pull/423
  • fix error in xgboost by @puririshi98 in https://github.com/pyg-team/pytorch-frame/pull/443
  • Add is_floating_point() to multi tensors by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/445
  • Fix size mismatch error when CatToNumTransform sees only a subset of labels at test time by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/446
  • add pytorch tabular benchmark by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/398
  • Compare more models across frame and tabular by @wsad1 in https://github.com/pyg-team/pytorch-frame/pull/444
  • Add benchmark result from ExcelFormer on a large-scale multi-class classification task by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/447
  • Fail torch.load(weights=True) gracefully by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/448
  • Fix offset in LinearEmbeddingEncoder by @toenshoff in https://github.com/pyg-team/pytorch-frame/pull/455
  • Fix docs build in CI by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/456
  • Removing the deprecated categorical_feature parameter from lightgbm.train(...) function calls. by @drivanov in https://github.com/pyg-team/pytorch-frame/pull/454
  • Tighten assert condition in graph break tests by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/458
  • Update pytorchtabularbenchmark.py by @wsad1 in https://github.com/pyg-team/pytorch-frame/pull/457
  • Drop support for Python 3.8 by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/462
  • [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in https://github.com/pyg-team/pytorch-frame/pull/461
  • Update benchmark numbers by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/411
  • Add support for PyTorch 2.5 by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/464
  • Allow empty TensorFrame with non-zero number of rows by @rusty1s in https://github.com/pyg-team/pytorch-frame/pull/466
  • Support index select for empty TensorFrame by @rusty1s in https://github.com/pyg-team/pytorch-frame/pull/467
  • Consistent PyPI name pytorch-frame by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/468
  • Raise a friendly message when a str is provided to TensorFrame(col_names_dict) instead of a list[str] by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/469
  • Update README.md by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/471
  • Materialize train test by @HoustonJ2013 in https://github.com/pyg-team/pytorch-frame/pull/472
  • Add an example of training a tabular model on multiple GPUs by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/474
  • Support pin_memory() in Multi{Embedding,Nested}Tensor and TensorFrame by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/437
  • Run MultiNestedTensor tests on both CPU and GPU by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/476
  • Optimize the Trompt example to reduce training time by ~30% by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/477
  • Add dependabot and auto-merge PRs by dependabot once CI passes by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/478
  • Bump tj-actions/changed-files from 41 to 45 by @dependabot in https://github.com/pyg-team/pytorch-frame/pull/479
  • Bump codecov/codecov-action from 2 to 5 by @dependabot in https://github.com/pyg-team/pytorch-frame/pull/481
  • Bump dangoslen/changelog-enforcer from 2 to 3 by @dependabot in https://github.com/pyg-team/pytorch-frame/pull/480
  • Bump actions/labeler from 4 to 5 by @dependabot in https://github.com/pyg-team/pytorch-frame/pull/482
  • [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in https://github.com/pyg-team/pytorch-frame/pull/483
  • Update .pre-commit-config.yaml weekly by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/484
  • Fix documentation build by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/486
  • Label bot PRs skip-changelog by @akihironitta in https://github.com/pyg-team/pytorch-frame/pull/487
  • [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in https://github.com/pyg-team/pytorch-frame/pull/485
  • update version to 0.2.4 by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/488

New Contributors

  • @NeelKondapalli made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/423
  • @puririshi98 made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/443
  • @wsad1 made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/444
  • @HoustonJ2013 made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/472

Full Changelog: https://github.com/pyg-team/pytorch-frame/compare/0.2.3...0.2.4

- Python
Published by weihua916 over 1 year ago

pytorch-frame - PyTorch Frame 0.2.3

What's Changed

  • Fix test_trompt.py by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/373
  • Add torchmetrics to pyproject.py full dependencies by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/374
  • Add light-weight MLP by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/372
  • Handle label imbalance in binary classification tasks on text benchmark by @vid-koci in https://github.com/pyg-team/pytorch-frame/pull/376
  • Fix MLP normalization argument by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/377
  • Add retry to get OpenAI embeddings by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/378
  • Make DataFrameTextBenchmark script pos_weight optional by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/379
  • Fix text dataset stats and benchmark materialize return by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/380
  • Add citation by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/383
  • [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in https://github.com/pyg-team/pytorch-frame/pull/382
  • Update RAEDME by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/384
  • Fix README image size by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/385
  • Add PyTorch Frame paper link to readme by @zechengz in https://github.com/pyg-team/pytorch-frame/pull/386
  • Make sure binary classification FakeDataset has both pos/neg labels by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/392
  • Update the key implementation and corresponding compatibility for ExcelFormer by @jyansir in https://github.com/pyg-team/pytorch-frame/pull/391
  • Better error message for CatToNumTransform by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/394
  • Fix split_by_sep in multicategorical stype by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/395
  • add support for autoinfer bool type by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/399
  • Add R2 metric by @rishabh-ranjan in https://github.com/pyg-team/pytorch-frame/pull/403
  • [FutureWarn] Fix FutureWarning in CategoricalTensorMapper. by @drivanov in https://github.com/pyg-team/pytorch-frame/pull/401
  • fix readme link by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/407
  • update benchmark by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/400
  • Add MovieLens 1M dataset by @xnuohz in https://github.com/pyg-team/pytorch-frame/pull/397
  • Fixing Bug in Version Handling. by @drivanov in https://github.com/pyg-team/pytorch-frame/pull/410
  • update benchmark numbers by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/408
  • [UserWarning] Fixing UserWarnings in two tests. by @drivanov in https://github.com/pyg-team/pytorch-frame/pull/409
  • fix embedding script by @yiweny in https://github.com/pyg-team/pytorch-frame/pull/412
  • Allow column indexing with custom stypes by @rusty1s in https://github.com/pyg-team/pytorch-frame/pull/413
  • [pre-commit.ci] pre-commit suggestions by @pre-commit-ci in https://github.com/pyg-team/pytorch-frame/pull/414
  • Fix ExcelFormer Example Link by @crunai in https://github.com/pyg-team/pytorch-frame/pull/415
  • Towards supporting MultiCategorical encoder for target in torchframe by @XinweiHe in https://github.com/pyg-team/pytorch-frame/pull/417
  • Update to version 0.2.3 by @weihua916 in https://github.com/pyg-team/pytorch-frame/pull/418

New Contributors

  • @jyansir made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/391
  • @rishabh-ranjan made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/403
  • @drivanov made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/401
  • @crunai made their first contribution in https://github.com/pyg-team/pytorch-frame/pull/415

Full Changelog: https://github.com/pyg-team/pytorch-frame/compare/0.2.2...0.2.3

- Python
Published by weihua916 almost 2 years ago

pytorch-frame - PyTorch Frame 0.2.2

This release introduces image_embedded stype to handle image columns, fixes bugs on MultiNestedTensor indexing, and makes efficiency improvements in terms of missing value imputation and categorical column encoders.

Added

  • Avoided for-loop in EmbeddingEncoder (#366)
  • Added image_embedded and one tabular image dataset (#344)
  • Added benchmarking suite for encoders (#360)
  • Added dataframe text benchmark script (#354, #367)
  • Added DataFrameTextBenchmark dataset (#349)
  • Added support for empty TensorFrame (#339)

Changed

  • Changed a workflow of Encoder's na_forward method resulting in performance boost (#364)
  • Removed ReLU applied in FCResidualBlock (#368)

Fixed

  • Fixed bug in empty MultiNestedTensor handling (#369)
  • Fixed the split of DataFrameTextBenchmark (#358)
  • Fixed empty MultiNestedTensor col indexing (#355)

- Python
Published by weihua916 about 2 years ago

pytorch-frame - PyTorch Frame 0.2.1

This PR makes the following fixes and extensions to 0.2.0.

Added - Support more stypes in LinearModelEncoder (https://github.com/pyg-team/pytorch-frame/pull/325) - Added stype_encoder_dict to some models (https://github.com/pyg-team/pytorch-frame/pull/319) - Added HuggingFaceDatasetDict (https://github.com/pyg-team/pytorch-frame/pull/287)

Changed - Supported decoder embedding model in examples/transformers_text.py (https://github.com/pyg-team/pytorch-frame/pull/333) - Removed implicit clones in StypeEncoder (https://github.com/pyg-team/pytorch-frame/pull/286)

Fixed - Fixed TimestampEncoder not applying CyclicEncoder to cyclic features (https://github.com/pyg-team/pytorch-frame/pull/311) - Fixed NaN masking in multicateogrical stype (https://github.com/pyg-team/pytorch-frame/pull/307)

- Python
Published by weihua916 over 2 years ago

pytorch-frame - PyTorch Frame 0.2.0

We are excited to announce the second release of PyTorch Frame 🐶

PyTorch Frame 0.2.0 is the cumulation of work from many contributors from and outside Kumo who have worked on features and bug-fixes for a total of over 120 commits since torch-frame==0.1.0.

PyTorch Frame is featured in the Relational Deep Learning paper and used as the encoding layer for PyG.

Kumo is also hiring interns working on cool deep learning projects. If you are interested, feel free to apply through this link.

If you have any questions or would like to contribute to PyTorch Frame, feel free to send a question at our slack channel.

Highlights

Support for multicategorical, timestamp,text_tokenized and embedding stypes

We have added support for four more semantic types. Adding the new stypes allows for more flexibility to encode raw data. To understand how to specify different semantic types for your data, you can take a look at the tutorial. We also added many new StypeEncoder for the different new semantic types.

Integration with Large Language Models

We now support two types of integration with LLMs--embedding and fine-tuning.

You can use any embeddings generated by LLMs with PyTorch Frame, either by directly feeding the embeddings as raw data of embedding stype or using text as raw data of text_embedded stype and specifying the text_embedder for each column. Here is an example of how you can use PyTorch Frame with text embeddings generated by OpenAI, Cohere, VoyageAI and HuggingFace transformers.

text_tokenized enables users to fine-tune Large Language Models on text columns, along with other types of raw tabular data, on any downstream task. In this example, we fine-tuned both the full distilbert-base-uncased model and with LoRA.

More Benchmarks

We added more benchmark results in the benchmark section. LightGBM is included in the list of GBDTs that we compare with the deep learning models. We did initial experiments on various LLMs as well.

Breaking Changes

  • text_tokenized_cfg and text_embedder_cfg are renamed to col_to_text_tokenized_cfg and col_to_text_embedder_cfg respectively (#257). This allows users to specify different embedders, tokenizers for different text columns.
  • Now Trompt outputs 2-dim embeddings in forward.

Features

  • We now support the following new encoders: LinearEmbeddingEncoder for embedding stype, TimestampEncoder for timestamp stype and MultiCategoricalEmbeddingEncoder for multicategorical stype.

  • LightGBM is added to GDBTs module.

  • Auto-inference of stypes from raw DataFrame columns is supported through infer_df_stype function. However, the correctness of the inference is not guaranteed and we suggest you to double-check.

Bugfixes

We fixed the in_channels calculation of ResNet(#220) and improved the overall user experience on handling dirty data (#171 #234 #264).

Full Changelog

Full Changelog: https://github.com/pyg-team/pytorch-frame/compare/0.1.0...0.2.0

- Python
Published by yiweny over 2 years ago

pytorch-frame - PyTorch Frame 0.1.0

We are excited to announce the initial release of PyTorch Frame 🎉🎉🎉

PyTorch Frame is a deep learning extension for PyTorch, designed for heterogeneous tabular data with different column types, including numerical, categorical, time, text, and images.

To get started, please refer to: - our README.md for the overview of PyTorch Frame, - "Introduction by Example" tutorial and its code at examples/tutorial.py to get started with using PyTorch Frame, and - "Modular Design of Deep Tabular Models" tutorial in our documentation and the existing implementations in torch_frame/nn/models/ directory to create your own PyTorch Frame model for tabular data.

Highlights

Models, datasets and examples

In our initial release, we introduce 6 models, 9 feature encoders, 5 table convolution layers, 3 decoders, and 14 datasets.

Benchmarks

With our initial set of models and datasets under torch_frame.nn and torch_frame.datasets, we benchmarked their performance on binary classification and regression tasks. The row denotes the model names and the column denotes the dataset idx. In each cell, we include the mean and standard deviation of the model performance, as well as the total time spent, including Optuna-based hyper-parameter search and final model training.

[!NOTE]
- For the latest benchmark scripts and results, see benchmark/ directory. - For which column number denoting dataset idx corresponds to which dataset, see the torch.datasets.DataFrameBenchmark dataset docs

Benchmark on small-scale binary classification tasks

Metric: ROC-AUC, higher the better.

| | dataset0 | dataset1 | dataset2 | dataset3 | dataset4 | dataset5 | dataset6 | dataset7 | dataset8 | dataset9 | dataset10 | dataset11 | dataset12 | dataset13 | |:--------------------|:-----------------------|:------------------------|:-------------------------|:----------------------|:------------------------|:-----------------------|:----------------------|:-----------------------|:-----------------------|:-----------------------|:----------------------|:------------------------|:------------------------|:------------------------| | XGBoost | 0.931±0.000 (41s) | 1.000±0.000 (4s) | 0.935±0.000 (16s) | 0.946±0.000 (26s) | 0.881±0.000 (10s) | 0.951±0.000 (16s) | 0.862±0.000 (26s) | 0.780±0.000 (11s) | 0.983±0.000 (584s) | 0.763±0.000 (240s) | 0.795±0.000 (11s) | 0.950±0.000 (479s) | 0.999±0.000 (148s) | 0.926±0.000 (3042s) | | CatBoost | 0.930±0.000 (152s) | 1.000±0.000 (9s) | 0.938±0.000 (164s) | 0.924±0.000 (29s) | 0.881±0.000 (27s) | 0.963±0.000 (48s) | 0.861±0.000 (12s) | 0.772±0.000 (10s) | 0.930±0.000 (91s) | 0.628±0.000 (10s) | 0.796±0.000 (15s) | 0.948±0.000 (46s) | 0.998±0.000 (38s) | 0.926±0.000 (115s) | | Trompt | 0.919±0.000 (9627s) | 1.000±0.000 (5341s) | 0.945±0.000 (14679s) | 0.942±0.001 (2752s) | 0.881±0.001 (2640s) | 0.964±0.001 (5173s) | 0.855±0.002 (4249s) | 0.778±0.002 (8789s) | 0.933±0.001 (9353s) | 0.686±0.008 (3105s) | 0.793±0.002 (8255s) | 0.952±0.001 (4876s) | 1.000±0.000 (3558s) | 0.916±0.001 (30002s) | | ResNet | 0.917±0.000 (615s) | 1.000±0.000 (71s) | 0.937±0.001 (787s) | 0.938±0.002 (230s) | 0.865±0.001 (183s) | 0.960±0.001 (349s) | 0.828±0.001 (248s) | 0.768±0.002 (205s) | 0.925±0.002 (958s) | 0.665±0.006 (140s) | 0.794±0.002 (76s) | 0.946±0.002 (145s) | 1.000±0.000 (93s) | 0.911±0.001 (880s) | | FTTransformerBucket | 0.915±0.001 (690s) | 0.999±0.001 (354s) | 0.936±0.002 (1705s) | 0.939±0.002 (484s) | 0.876±0.002 (321s) | 0.960±0.001 (746s) | 0.857±0.000 (549s) | 0.771±0.003 (654s) | 0.909±0.002 (1177s) | 0.636±0.012 (244s) | 0.788±0.002 (710s) | 0.950±0.001 (510s) | 0.999±0.000 (634s) | 0.913±0.001 (1164s) | | ExcelFormer | 0.918±0.001 (1587s) | 1.000±0.000 (634s) | 0.939±0.001 (1827s) | 0.939±0.002 (378s) | 0.878±0.003 (251s) | 0.969±0.000 (678s) | 0.833±0.011 (435s) | 0.780±0.002 (938s) | 0.921±0.005 (1131s) | 0.649±0.008 (519s) | 0.794±0.003 (683s) | 0.950±0.001 (405s) | 0.999±0.000 (1169s) | 0.919±0.001 (1798s) | | FTTransformer | 0.918±0.001 (871s) | 1.000±0.000 (571s) | 0.940±0.001 (1371s) | 0.936±0.001 (458s) | 0.874±0.002 (200s) | 0.959±0.001 (622s) | 0.828±0.001 (339s) | 0.773±0.002 (521s) | 0.909±0.002 (1488s) | 0.635±0.011 (392s) | 0.790±0.001 (556s) | 0.949±0.002 (374s) | 1.000±0.000 (713s) | 0.912±0.000 (1855s) | | TabNet | 0.911±0.001 (150s) | 1.000±0.000 (35s) | 0.931±0.005 (254s) | 0.937±0.003 (125s) | 0.864±0.002 (52s) | 0.944±0.001 (116s) | 0.828±0.001 (79s) | 0.771±0.005 (93s) | 0.913±0.005 (177s) | 0.606±0.014 (65s) | 0.790±0.003 (41s) | 0.936±0.003 (104s) | 1.000±0.000 (64s) | 0.910±0.001 (294s) | | TabTransformer | 0.910±0.001 (2044s) | 1.000±0.000 (1321s) | 0.928±0.001 (2519s) | 0.918±0.003 (134s) | 0.829±0.002 (64s) | 0.928±0.001 (105s) | 0.816±0.002 (99s) | 0.757±0.003 (645s) | 0.885±0.001 (1167s) | 0.652±0.006 (282s) | 0.780±0.002 (112s) | 0.937±0.001 (117s) | 0.996±0.000 (76s) | 0.905±0.001 (2283s) |

Benchmark on small-scale regression tasks

Metric: RMSE, lower the better.

| | dataset0 | dataset1 | dataset2 | dataset3 | dataset4 | dataset5 | dataset6 | dataset7 | dataset8 | dataset9 | dataset10 | dataset11 | dataset_12 | |:--------------------|:-----------------------|:------------------------|:------------------------|:-------------------------|:------------------------|:-----------------------|:-----------------------|:-----------------------|:------------------------|:------------------------|:-----------------------|:---------------------|:------------------------| | XGBoost | 0.247±0.000 (516s) | 0.077±0.000 (14s) | 0.167±0.000 (423s) | 1.119±0.000 (1063s) | 0.328±0.000 (2044s) | 1.024±0.000 (47s) | 0.292±0.000 (844s) | 0.606±0.000 (1765s) | 0.876±0.000 (2288s) | 0.023±0.000 (1170s) | 0.697±0.000 (248s) | 0.865±0.000 (8s) | 0.435±0.000 (22s) | | CatBoost | 0.265±0.000 (116s) | 0.062±0.000 (129s) | 0.128±0.000 (97s) | 0.336±0.000 (103s) | 0.346±0.000 (110s) | 0.443±0.000 (97s) | 0.375±0.000 (46s) | 0.273±0.000 (693s) | 0.881±0.000 (660s) | 0.040±0.000 (80s) | 0.756±0.000 (44s) | 0.876±0.000 (110s) | 0.439±0.000 (101s) | | Trompt | 0.261±0.003 (8390s) | 0.015±0.005 (3792s) | 0.118±0.001 (3836s) | 0.262±0.001 (10037s) | 0.323±0.001 (9255s) | 0.418±0.003 (9071s) | 0.329±0.009 (2977s) | 0.312±0.002 (21967s) | OOM | 0.008±0.001 (1889s) | 0.779±0.006 (775s) | 0.874±0.004 (3723s) | 0.424±0.005 (3185s) | | ResNet | 0.288±0.006 (220s) | 0.018±0.003 (187s) | 0.124±0.001 (135s) | 0.268±0.001 (330s) | 0.335±0.001 (471s) | 0.434±0.004 (345s) | 0.325±0.012 (178s) | 0.324±0.004 (365s) | 0.895±0.005 (142s) | 0.036±0.002 (172s) | 0.794±0.006 (120s) | 0.875±0.004 (122s) | 0.468±0.004 (303s) | | FTTransformerBucket | 0.325±0.008 (619s) | 0.096±0.005 (290s) | 0.360±0.354 (332s) | 0.284±0.005 (768s) | 0.342±0.004 (757s) | 0.441±0.003 (835s) | 0.345±0.007 (191s) | 0.339±0.003 (3321s) | OOM | 0.105±0.011 (199s) | 0.807±0.010 (156s) | 0.885±0.008 (820s) | 0.468±0.006 (706s) | | ExcelFormer | 0.302±0.003 (703s) | 0.099±0.003 (490s) | 0.145±0.003 (587s) | 0.382±0.011 (504s) | 0.344±0.002 (1096s) | 0.411±0.005 (469s) | 0.359±0.016 (207s) | 0.336±0.008 (5522s) | OOM | 0.192±0.014 (317s) | 0.794±0.005 (189s) | 0.890±0.003 (1186s) | 0.445±0.005 (550s) | | FTTransformer | 0.335±0.010 (338s) | 0.161±0.022 (370s) | 0.140±0.002 (244s) | 0.277±0.004 (516s) | 0.335±0.003 (973s) | 0.445±0.003 (599s) | 0.361±0.018 (286s) | 0.345±0.005 (2443s) | OOM | 0.106±0.012 (150s) | 0.826±0.005 (121s) | 0.896±0.007 (832s) | 0.461±0.003 (647s) | | TabNet | 0.279±0.003 (68s) | 0.224±0.016 (53s) | 0.141±0.010 (34s) | 0.275±0.002 (61s) | 0.348±0.003 (110s) | 0.451±0.007 (82s) | 0.355±0.030 (49s) | 0.332±0.004 (168s) | 0.992±0.182 (53s) | 0.015±0.002 (57s) | 0.805±0.014 (27s) | 0.885±0.013 (46s) | 0.544±0.011 (112s) | | TabTransformer | 0.624±0.003 (1225s) | 0.229±0.003 (1200s) | 0.369±0.005 (52s) | 0.340±0.004 (163s) | 0.388±0.002 (1137s) | 0.539±0.003 (100s) | 0.619±0.005 (73s) | 0.351±0.001 (125s) | 0.893±0.005 (389s) | 0.431±0.001 (489s) | 0.819±0.002 (52s) | 0.886±0.005 (46s) | 0.545±0.004 (95s) |

Full Changelog

Full Changelog: https://github.com/pyg-team/pytorch-frame/compare/5b5525f...0.1.0

- Python
Published by akihironitta over 2 years ago