# Adaptive Stochastic Weight Averaging

arXiv: https://arxiv.org/abs/2406.19092 · HTML: https://mlsanity.com/paper/2406.19092/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Essentially No Barriers in Neural Network Energy Landscape](https://mlsanity.com/paper/1803.00885/) (2018)
- [Complex Query Answering with Neural Link Predictors](https://mlsanity.com/paper/2011.03459/) (2020)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [An empirical analysis of dropout in piecewise linear networks](https://mlsanity.com/paper/1312.6197/) (2013)
- [Convolutional Hypercomplex Embeddings for Link Prediction](https://mlsanity.com/paper/2106.15230/) (2021)
- [Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings](https://mlsanity.com/paper/2104.05003/) (2021)
- [LitCQD: Multi-Hop Reasoning in Incomplete Knowledge Graphs with Numeric Literals](https://mlsanity.com/paper/2304.14742/) (2023)

## Built on by (most cited first, 4 of 4)

- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning](https://mlsanity.com/paper/2507.04790/) (2025)
- [DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation](https://mlsanity.com/paper/2506.23104/) (2025)
- [Boosting Active Learning with Knowledge Transfer](https://mlsanity.com/paper/2509.15805/) (2025)

## Abstract (arXiv)

Ensemble models often improve generalization performances in challenging tasks. Yet, traditional techniques based on prediction averaging incur three well-known disadvantages: the computational overhead of training multiple models, increased latency, and memory requirements at test time. To address these issues, the Stochastic Weight Averaging (SWA) technique maintains a running average of model parameters from a specific epoch onward. Despite its potential benefits, maintaining a running average of parameters can hinder generalization, as an underlying running model begins to overfit. Conversely, an inadequately chosen starting point can render SWA more susceptible to underfitting compared to an underlying running model. In this work, we propose Adaptive Stochastic Weight Averaging (ASWA) technique that updates a running average of model parameters, only when generalization performance is improved on the validation dataset. Hence, ASWA can be seen as a combination of SWA with the early stopping technique, where the former accepts all updates on a parameter ensemble model and the latter rejects any update on an underlying running model. We conducted extensive experiments ranging from image classification to multi-hop reasoning over knowledge graphs. Our experiments over 11 benchmark datasets with 7 baseline models suggest that ASWA leads to a statistically better generalization across models and datasets