Metadata-Version: 2.1
Name: SupCL-Seq
Version: 0.0.1
Summary: Supervised Contrastive Learning for Downstream Optimized Sequence representations
Home-page: https://github.com/hooman650/SupCL-Seq
Author: Hooman
Author-email: hooman650@yahoo.com
License: UNKNOWN
Project-URL: Bug Tracker, https://github.com/hooman650/SupCL-Seq/issues
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# SupCL-Seq :book:
Supervised Contrastive Learning for Downstream Optimized Sequence representations (**SupCS-Seq**) extends the supervised contrastive learning from computer vision to the optimization of sequence representations in NLP. By altering the dropout mask probability in standard Transformer architectures (e.g. *BERT_base*), for every representation (anchor), we generate augmented altered views. A supervised contrastive loss is then utilized to maximize the system’s capability of pulling together similar samples (e.g. anchors and their altered views) and pushing apart the samples belonging to the other classes. Despite its simplicity, SupCL-Seq leads to large gains in many sequence classification tasks on the GLUE benchmark compared to a standard *BERT_base*, including 6% absolute improvement on CoLA, 5.4% on MRPC, 4.7% on RTE and 2.6% on STS-B.

This package can be easily run on almost all of the transformer models in [`Huggingface`](https://huggingface.co/) :hugs: that contain an encoder including but not limited to:

1. [ALBERT](https://huggingface.co/transformers/model_doc/albert.html)
2. [BERT](https://huggingface.co/transformers/model_doc/bert.html)
3. [BigBird](https://huggingface.co/transformers/model_doc/bigbird.html)
4. [RoBerta](https://huggingface.co/transformers/model_doc/roberta.html)
5. And many more!


## Installation
Simply follow:

```bash
$ pip install SupCL-Seq
```

## Usage
The package builds on the [`trainer`](https://huggingface.co/transformers/main_classes/trainer.html) from [`Huggingface`](https://huggingface.co/):hugs:. Therefore, its use is exactly similar to [`trainer`](https://huggingface.co/transformers/main_classes/trainer.html).

```python
from SupCL_Seq import SupCsTrainer

SupCL_trainer = SupCsTrainer.SupCsTrainer(
            w_drop_out=[0.0,0.05,0.2],      # Number of views and their associated mask drop-out probabilities [Optional]
            temperature= 0.05,              # Temeprature for the contrastive loss function [Optional]
            def_drop_out=0.1,               # Default drop out of the transformer, this is usually 0.1 [Optional]
            pooling_strategy='mean',        # Strategy used to extract embeddings can be from `mean` or `pooling` [Optional]
            model = model,                  # model
            args = CL_args,                 # Arguments from `TrainingArguments` [Optional]
            train_dataset=train_dataset,    # Train dataloader
            tokenizer=tokenizer,            # Tokenizer
            compute_metrics=compute_metrics # If you need a customized evaluation [Optional]
        )

```




