torchgfn: A PyTorch GFlowNet library

• URL: http://arxiv.org/abs/2305.14594v3
• Date: Sun, 26 Oct 2025 19:56:42 GMT
• Title: torchgfn: A PyTorch GFlowNet library
• Authors: Joseph D. Viviano, Omar G. Younis, Sanghyeok Choi, Victor Schmidt, Yoshua Bengio, Salem Lahlou,
• Abstract summary: We present torchgfn, a PyTorch library that aims to address this need.<n>Its core contribution is a modular and decoupled architecture which treats environments, neural network modules, and training objectives as interchangeable components.<n>This provides users with a simple yet powerful API to facilitate rapid prototyping and novel research.
• Score: 44.94532429787822
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The growing popularity of generative flow networks (GFlowNets or GFNs) from a range of researchers with diverse backgrounds and areas of expertise necessitates a library that facilitates the testing of new features (e.g., training losses and training policies) against standard benchmark implementations, or on a set of common environments. We present torchgfn, a PyTorch library that aims to address this need. Its core contribution is a modular and decoupled architecture which treats environments, neural network modules, and training objectives as interchangeable components. This provides users with a simple yet powerful API to facilitate rapid prototyping and novel research. Multiple examples are provided, replicating and unifying published results. The library is available on GitHub (https://github.com/GFNOrg/torchgfn) and on pypi (https://pypi.org/project/torchgfn/).

Related papers

• gfnx: Fast and Scalable Library for Generative Flow Networks in JAX [12.748861864193623]
  We present gfnx, a package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX.<n>gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlowNets.<n>Across different tasks, gfnx achieves significant wall-clock speedups compared to Pytorch-based benchmarks.
  arXiv  Detail & Related papers  (2025-11-20T17:44:45Z)
• ByzFL: Research Framework for Robust Federated Learning [11.23722364748134]
  We present ByzFL, an open-source library for developing and robust benchmarking learning (FL) algorithms.<n>ByzFL provides a unified framework that includes implementations of state-of-the-art robust aggregators.<n>The library enables systematic experimentation via a single-based configuration file and includes built-in utilities for result visualization.
  arXiv  Detail & Related papers  (2025-05-30T17:08:15Z)
• PyPulse: A Python Library for Biosignal Imputation [58.35269251730328]
  We introduce PyPulse, a Python package for imputation of biosignals in both clinical and wearable sensor settings.<n>PyPulse's framework provides a modular and extendable framework with high ease-of-use for a broad userbase, including non-machine-learning bioresearchers.<n>We released PyPulse under the MIT License on Github and PyPI.
  arXiv  Detail & Related papers  (2024-12-09T11:00:55Z)
• Comgra: A Tool for Analyzing and Debugging Neural Networks [35.89730807984949]
  We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations of a model and organizes it in a GUI. It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network.
  arXiv  Detail & Related papers  (2024-07-31T14:57:23Z)
• Benchmarking Predictive Coding Networks -- Made Simple [48.652114040426625]
  We tackle the problems of efficiency and scalability for predictive coding networks (PCNs) in machine learning. We propose a library, called PCX, that focuses on performance and simplicity, and use it to implement a large set of standard benchmarks. We perform extensive tests on such benchmarks using both existing algorithms for PCNs, as well as adaptations of other methods popular in the bio-plausible deep learning community.
  arXiv  Detail & Related papers  (2024-07-01T10:33:44Z)
• Local Search GFlowNets [85.0053493167887]
  Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their rewards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue.
  arXiv  Detail & Related papers  (2023-10-04T10:27:17Z)
• BayesDLL: Bayesian Deep Learning Library [29.624531252627484]
  We release a new Bayesian neural network library for PyTorch for large-scale deep networks. Our library implements mainstream inference algorithms: variational inference, MC-dropout, approximate-gradient MCMC, and Laplace approximation.
  arXiv  Detail & Related papers  (2023-09-22T15:27:54Z)
• SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval [92.27387459751309]
  We provide SPRINT, a unified Python toolkit for evaluating neural sparse retrieval. We establish strong and reproducible zero-shot sparse retrieval baselines across the well-acknowledged benchmark, BEIR. We show that SPLADEv2 produces sparse representations with a majority of tokens outside of the original query and document.
  arXiv  Detail & Related papers  (2023-07-19T22:48:02Z)
• PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs [20.832917829426098]
  PyTorch Geometric Signed Directed (PyGSD) is a software package for signed and directed networks. PyGSD consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions. As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks.
  arXiv  Detail & Related papers  (2022-02-22T10:25:59Z)
• TyXe: Pyro-based Bayesian neural nets for Pytorch [12.343312954353639]
  We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likelihood specification. In contrast to existing packages TyXe does not implement any layer classes, and instead relies on architectures defined in generic Pytorch code.
  arXiv  Detail & Related papers  (2021-10-01T09:04:26Z)
• Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning [83.02597612195966]
  solo-learn is a library of self-supervised methods for visual representation learning. Implemented in Python, using Pytorch and Pytorch lightning, the library fits both research and industry needs.
  arXiv  Detail & Related papers  (2021-08-03T22:19:55Z)
• Efficient Graph Deep Learning in TensorFlow with tf_geometric [53.237754811019464]
  We introduce tf_geometric, an efficient and friendly library for graph deep learning. tf_geometric provides kernel libraries for building Graph Neural Networks (GNNs) as well as implementations of popular GNNs. The kernel libraries consist of infrastructures for building efficient GNNs, including graph data structures, graph map-reduce framework, graph mini-batch strategy, etc.
  arXiv  Detail & Related papers  (2021-01-27T17:16:36Z)
• TensorX: Extensible API for Neural Network Model Design and Deployment [0.0]
  TensorFlowX is a Python library for prototyping, design, and deployment of complex neural network models in computation. A special emphasis is put on ease of use, performance, and API consistency.
  arXiv  Detail & Related papers  (2020-12-29T00:15:38Z)
• torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models [19.024035785367044]
  We design and implement a ready-to-use library in PyTorch for performing micro-batch pipeline parallelism with checkpointing proposed by GPipe. We show that each component is necessary to fully benefit from pipeline parallelism in such environment, and demonstrate the efficiency of the library.
  arXiv  Detail & Related papers  (2020-04-21T11:27:00Z)
• Torch-Struct: Deep Structured Prediction Library [138.5262350501951]
  We introduce Torch-Struct, a library for structured prediction. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API.
  arXiv  Detail & Related papers  (2020-02-03T16:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.