Unified Implementations of Recurrent Neural Networks in Multiple Deep Learning Frameworks

2025-10-24

AI Summary

Existing RNN variants suffer from fragmented implementations across deep learning frameworks, lacking standardized interfaces and rigorous cross-framework evaluation—leading to poor reproducibility, redundant development, and inefficient experimentation. Method: We introduce the first standardized, multi-framework RNN interface, implemented in open-source libraries: `torchrecurrent` (Python, for PyTorch), `RecurrentLayers.jl`, and `LuxRecurrentLayers.jl` (Julia, for JAX/Flux). These provide unified, semantically consistent implementations of diverse recurrent units—including LSTM, GRU, mGRU, and Delta-RNN—as well as higher-level architectures. Contribution/Results: Our work establishes the first modular, extensible, and framework-agnostic RNN API, enabling flexible customization and seamless model migration across ecosystems. All libraries are MIT-licensed, actively maintained, and rigorously tested. By abstracting framework-specific complexities, they significantly lower implementation overhead and experimental barriers, thereby promoting structural standardization, reproducible research, and collaborative advancement in recurrent modeling.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recurrent neural networks (RNNs) are a cornerstone of sequence modeling across various scientific and industrial applications. Owing to their versatility, numerous RNN variants have been proposed over the past decade, aiming to improve the modeling of long-term dependencies and to address challenges such as vanishing and exploding gradients. However, no central library is available to test these variations, and reimplementing diverse architectures can be time-consuming and error-prone, limiting reproducibility and exploration. Here, we introduce three open-source libraries in Julia and Python that centralize numerous recurrent cell implementations and higher-level recurrent architectures. torchrecurrent, RecurrentLayers.jl, and LuxRecurrentLayers.jl offer a consistent framework for constructing and extending RNN models, providing built-in mechanisms for customization and experimentation. All packages are available under the MIT license and actively maintained on GitHub.

Problem

• Implementing recurrent neural networks consistently across frameworks
• Providing centralized library for diverse RNN variants testing
• Addressing time-consuming error-prone RNN reimplementation challenges

Innovation

• Unified RNN implementations across multiple frameworks
• Centralized recurrent cell libraries in Julia and Python
• Consistent architecture with built-in customization mechanisms