mozilla / mozilla/bugbug

Try overweighting model errors when training

Open
#5,878 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
570
Forks
351
Avg merge
2d 13h
Merged PRs (30d)
65

Description

We currently consider all examples the same, without overweighting anything. We might want to try overweighting cases where the model made an error (e.g. identifying a bug as accessibility which was not actually accessibility).

Contributor guide

Open the contributing guide

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

The issue names no files, tests, or training entry point. Start by locating the training pipeline and how model errors are identified, then clarify which errors should receive extra weight. Done should include an implemented weighting approach and evidence from training or evaluation that it improves classification.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning, python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.