Accenture / Accenture/AmpliGraph
Add support for L4 optimizer
Open
Nobody has claimed this yet.
enhancement
model
- Dominant language
- Python
- Stars
- 2.2k
- Forks
- 257
- PR merge metrics
- No merged PRs in 30d
Description
Description
Integrate L4 optimizer and allow its use as drop-in replacement for adam, adagrad as optimizer argument in EmbeddingModel constructor.
https://github.com/martius-lab/l4-optimizer
https://arxiv.org/abs/1802.05074v2
Run experiments on FB15k-237 on ComplEx to assess:
- i) predictive power
- ii) training speed
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the EmbeddingModel constructor and its optimizer argument, then review how adam and adagrad are currently selected. Integrate the referenced L4 optimizer as a drop-in option and run the requested FB15k-237 ComplEx experiments; done means predictive power and training speed are assessed against the existing optimizers.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100