# Deep Learning with Dynamic Computation Graphs

arXiv: https://arxiv.org/abs/1702.02181 · HTML: https://mlsanity.com/paper/1702.02181/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2017.

## Built on by (most cited first, 15 of 15)

- [VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesis](https://mlsanity.com/paper/2307.03592/) (2023)
- [The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment](https://mlsanity.com/paper/2302.06117/) (2023)
- [TOD: GPU-accelerated Outlier Detection via Tensor Operations](https://mlsanity.com/paper/2110.14007/) (2021)
- [Deep Learning-based Sentiment Classification: A Comparative Survey](https://mlsanity.com/paper/2312.17253/) (2023)
- [SoD2: Statically Optimizing Dynamic Deep Neural Network](https://mlsanity.com/paper/2403.00176/) (2024)
- [InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs](https://mlsanity.com/paper/2502.08807/) (2025)
- [REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving](https://mlsanity.com/paper/2506.01374/) (2025)
- [Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey](https://mlsanity.com/paper/2510.00078/) (2025)
- [Unsupervised Learning of Explainable Parse Trees for Improved Generalisation](https://mlsanity.com/paper/2104.04998/) (2021)
- [Computational Complexity Evaluation of Neural Network Applications in Signal Processing](https://mlsanity.com/paper/2206.12191/) (2022)
- [ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines](https://mlsanity.com/paper/2302.03851/) (2023)
- [ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time](https://mlsanity.com/paper/2305.10611/) (2023)
- [Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs](https://mlsanity.com/paper/2605.29453/) (2026)
- [Recursive Function Definitions in Static Dataflow Graphs and their Implementation in TensorFlow](https://mlsanity.com/paper/2410.20225/) (2024)
- [Recursive Variational Autoencoders for 3D Blood Vessel Generative Modeling](https://mlsanity.com/paper/2506.14914/) (2025)

## Abstract (arXiv)

Neural networks that compute over graph structures are a natural fit for problems in a variety of domains, including natural language (parse trees) and cheminformatics (molecular graphs). However, since the computation graph has a different shape and size for every input, such networks do not directly support batched training or inference. They are also difficult to implement in popular deep learning libraries, which are based on static data-flow graphs. We introduce a technique called dynamic batching, which not only batches together operations between different input graphs of dissimilar shape, but also between different nodes within a single input graph. The technique allows us to create static graphs, using popular libraries, that emulate dynamic computation graphs of arbitrary shape and size. We further present a high-level library of compositional blocks that simplifies the creation of dynamic graph models. Using the library, we demonstrate concise and batch-wise parallel implementations for a variety of models from the literature.