google-research/fast-soft-sort
A Google Research library implementing O(n log n) differentiable sorting and ranking operations across JAX, PyTorch, and TensorFlow.
Fast-soft-sort provides soft, differentiable versions of sorting and ranking operations that can be integrated into ML training pipelines. The library exposes functions like soft_sort and soft_rank with a regularization_strength parameter that controls how hard or soft the sorting behavior is, enabling end-to-end gradient-based optimization where ranking metrics need to be minimized. It offers native implementations for TensorFlow, JAX, and PyTorch, making it a utility library for researchers working on ranking losses, learning-to-rank models, and neural network architectures that depend on ordering operations.
Frequently asked
- What is google-research/fast-soft-sort?
- A Google Research library implementing O(n log n) differentiable sorting and ranking operations across JAX, PyTorch, and TensorFlow.
- Is fast-soft-sort open source?
- Yes — google-research/fast-soft-sort is open source, released under the Apache-2.0 license.
- What language is fast-soft-sort written in?
- google-research/fast-soft-sort is primarily written in Python.
- How popular is fast-soft-sort?
- google-research/fast-soft-sort has 624 stars on GitHub.
- Where can I find fast-soft-sort?
- google-research/fast-soft-sort is on GitHub at https://github.com/google-research/fast-soft-sort.