microsoft / microsoft/dp-transformers

`DataCollatorForPrivateCausalLanguageModeling` hardcoded to `mlm=False`

Open
#42 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
149
Forks
33
Avg merge
22h 6m
Merged PRs (30d)
1

Description

Why is the mlm parameter hardcoded to False in DataCollatorForPrivateCausalLanguageModeling's implementation?
I intend to use the DPCallback for Masked Language Modeling.
Is it unsafe to turn it to True?

dp_utils.py#L99

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with src/dp_transformers/dp_utils.py#L99 and trace how DataCollatorForPrivateCausalLanguageModeling is used with DPCallback. Determine whether enabling masked language modeling is compatible with the differential-privacy flow or intentionally restricted. Done means documenting the decision and, if supported, defining the behavior and coverage needed for mlm=True.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning, security
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.