• TensorFlow

  • Referenced in 629 articles [sw15170]
  • graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated ... purposes of conducting machine learning and deep neural networks research, but the system is general...
  • DeepWalk

  • Referenced in 63 articles [sw39604]
  • feature learning (or deep learning) from sequences of words to graphs. DeepWalk uses local information...
  • DGL

  • Referenced in 11 articles [sw33907]
  • research in the emerging field of deep graph learning requires new tools to support tensor ... present the design principles and implementation of Deep Graph Library (DGL). DGL distills the computational ... operations suitable for extensive parallelization. By advocating graph as the central programming abstraction ... leverage the existing components across multiple deep learning frameworks. Our evaluation shows that DGL significantly...
  • subgraph2vec

  • Referenced in 4 articles [sw36496]
  • inspired by recent advancements in Deep Learning and Graph Kernels. These latent representations encode semantic ... statistical models for tasks such as graph classification, clustering, link prediction and community detection. subgraph2vec ... information obtained from neighbourhoods of nodes to learn their latent representations in an unsupervised fashion ... used for building a deep learning variant of Weisfeiler-Lehman graph kernel. Our experiments...
  • PyG

  • Referenced in 4 articles [sw41050]
  • upon PyTorch to easily write and train Graph Neural Networks (GNNs) for a wide range ... consists of various methods for deep learning on graphs and other irregular structures, also known ... geometric deep learning, from a variety of published papers. In addition, it consists of easy ... operating on many small and single giant graphs, multi GPU-support, distributed graph learning...
  • CayleyNets

  • Referenced in 5 articles [sw38090]
  • citation graphs, and functional brain networks, in combination with resounding success of deep learning ... spectral domain convolutional architecture for deep learning on graphs. The core ingredient of our model...
  • MXNet

  • Referenced in 36 articles [sw20940]
  • MXNet is a deep learning framework designed for both efficiency and flexibility. It allows ... imperative operations on the fly. A graph optimization layer on top of that makes symbolic ... MXNet is also more than a deep learning project. It is also a collection...
  • DIG

  • Referenced in 1 article [sw37858]
  • Turnkey Library for Diving into Graph Deep Learning Research. Although there exist several libraries ... deep learning on graphs, they are aiming at implementing basic operations for graph deep learning ... consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into ... self-supervised learning on graphs, explainability of graph neural networks, and deep learning...
  • CogDL

  • Referenced in 2 articles [sw37740]
  • CogDL: An Extensive Toolkit for Deep Learning on Graphs. Graph representation learning aims to learn ... dimensional node embeddings for graphs. It is used in several real-world applications such ... extensive research toolkit for deep learning on graphs that allows researchers and developers to easily...
  • DGL-LifeSci

  • Referenced in 1 article [sw39641]
  • Learning on Graphs in Life Science. Graph neural networks (GNNs) constitute a class of deep ... requires graph data pre-processing and modeling in addition to programming and deep learning. Here ... open-source package for deep learning on graphs in life science. DGL-LifeSci ... without any background in programming and deep learning. We test the command-line interfaces using...
  • RLgraph

  • Referenced in 2 articles [sw31155]
  • RLgraph: Modular Computation Graphs for Deep Reinforcement Learning. Reinforcement learning (RL) tasks are challenging ... separation of logical component composition, backend graph definition, and distributed execution. To this ... designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms ... yield high performance across different deep learning frameworks and distributed backends...
  • PyTorch Geometric

  • Referenced in 1 article [sw39158]
  • consists of various methods for deep learning on graphs and other irregular structures, also known ... geometric deep learning, from a variety of published papers. In addition, it consists ... loader for many small and single giant graphs, a large number of common benchmark datasets...
  • Chainer

  • Referenced in 15 articles [sw26707]
  • learning. Chainer is a Python-based deep learning framework aiming at flexibility. It provides automatic ... define-by-run approach (a.k.a. dynamic computational graphs) as well as object-oriented high-level...
  • RNAglib

  • Referenced in 1 article [sw39986]
  • machine learning pipelines and graph-based deep learning models suited for this representation. RNAglib also ... utilities to model RNA with 2.5D graphs, such as drawing tools, comparison functions...
  • ONNX

  • Referenced in 6 articles [sw30961]
  • models, both deep learning and traditional ML. It defines an extensible computation graph model...
  • ProGraML

  • Referenced in 1 article [sw32379]
  • ProGraML: Graph-based Deep Learning for Program Optimization and Analysis. The increasing complexity of computing ... ever more accurate and aggressive optimizations. Machine learning offers significant benefits for constructing optimization heuristics ... about this representation. We introduce ProGraML - Program Graphs for Machine Learning - a novel graph-based...
  • DeepTMA

  • Referenced in 1 article [sw33597]
  • novel framework combining graph-based deep learning and Network Calculus (NC) models. The framework learns...
  • CNTK

  • Referenced in 9 articles [sw21056]
  • Toolkit (https://cntk.ai), is a unified deep-learning toolkit that describes neural networks ... series of computational steps via a directed graph. In this directed graph, leaf nodes represent...
  • OpenGraphGym

  • Referenced in 1 article [sw38102]
  • environment incorporates a basic deep reinforcement learning method, and several graph embeddings to capture graph...
  • nGraph-HE

  • Referenced in 1 article [sw38100]
  • nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data. Homomorphic encryption ... increasing concerns about data privacy in deep learning (DL). However, building DL models that operate ... engineering. DL frameworks and recent advances in graph compilers have greatly accelerated the training...