# AdaNet: Adaptive Structural Learning of Artificial Neural Networks

arXiv: https://arxiv.org/abs/1607.01097 · HTML: https://mlsanity.com/paper/1607.01097/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2016.

## Built on by (most cited first, 30 of 54)

- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts](https://mlsanity.com/paper/2211.05272/) (2022)
- [GradMax: Growing Neural Networks using Gradient Information](https://mlsanity.com/paper/2201.05125/) (2022)
- [Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent](https://mlsanity.com/paper/2402.13717/) (2024)
- [FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation](https://mlsanity.com/paper/2505.20353/) (2025)
- [Whither AutoML? Understanding the Role of Automation in Machine Learning Workflows](https://mlsanity.com/paper/2101.04834/) (2021)
- [Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective](https://mlsanity.com/paper/2112.14531/) (2021)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation](https://mlsanity.com/paper/2112.06632/) (2021)
- [Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019](https://mlsanity.com/paper/2201.03801/) (2022)
- [Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data](https://mlsanity.com/paper/2502.10381/) (2025)
- [Lifelong Mixture of Variational Autoencoders](https://mlsanity.com/paper/2107.04694/) (2021)
- [AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation](https://mlsanity.com/paper/2203.06558/) (2022)
- [Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey](https://mlsanity.com/paper/2101.10181/) (2021)
- [Continual Learning on the Edge with TensorFlow Lite](https://mlsanity.com/paper/2105.01946/) (2021)
- [Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features](https://mlsanity.com/paper/2110.13413/) (2021)
- [Numerical Computation of Partial Differential Equations by Hidden-Layer Concatenated Extreme Learning Machine](https://mlsanity.com/paper/2204.11375/) (2022)
- [Improved Balanced Classification with Theoretically Grounded Loss Functions](https://mlsanity.com/paper/2512.23947/) (2025)
- [A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms](https://mlsanity.com/paper/2211.12386/) (2022)
- [Boosted Dynamic Neural Networks](https://mlsanity.com/paper/2211.16726/) (2022)
- [Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process](https://mlsanity.com/paper/2108.12278/) (2021)
- [Neural Ensemble Search via Bayesian Sampling](https://mlsanity.com/paper/2109.02533/) (2021)
- [Task Selection for AutoML System Evaluation](https://mlsanity.com/paper/2208.12754/) (2022)
- [Self-Activating Neural Ensembles for Continual Reinforcement Learning](https://mlsanity.com/paper/2301.00141/) (2022)
- [Towards continual task learning in artificial neural networks: current approaches and insights from neuroscience](https://mlsanity.com/paper/2112.14146/) (2021)
- [MobilityDL: A Review of Deep Learning From Trajectory Data](https://mlsanity.com/paper/2402.00732/) (2024)
- [Local Critic Training for Model-Parallel Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.01963/) (2021)
- [DOC3-Deep One Class Classification using Contradictions](https://mlsanity.com/paper/2105.07636/) (2021)
- [Continual Domain Adversarial Adaptation via Double-Head Discriminators](https://mlsanity.com/paper/2402.03588/) (2024)
- [Random Feature Representation Boosting](https://mlsanity.com/paper/2501.18283/) (2025)

## Abstract (arXiv)

We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including data-dependent generalization guarantees that we prove and discuss in detail. We report the results of large-scale experiments with one of our algorithms on several binary classification tasks extracted from the CIFAR-10 dataset. The results demonstrate that our algorithm can automatically learn network structures with very competitive performance accuracies when compared with those achieved for neural networks found by standard approaches.