# KATO: Knowledge Alignment and Transfer for Transistor Sizing of Different Design and Technology

arXiv: https://arxiv.org/abs/2404.14433 · HTML: https://mlsanity.com/paper/2404.14433/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Builds on (most cited first, 4 of 4)

- [GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning](https://mlsanity.com/paper/2005.00406/) (2020)
- [Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2204.05944/) (2022)
- [Differentiable Compositional Kernel Learning for Gaussian Processes](https://mlsanity.com/paper/1806.04326/) (2018)
- [An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble](https://mlsanity.com/paper/2106.15412/) (2021)

## Built on by (most cited first, 2 of 2)

- [AMSNet: Netlist Dataset for AMS Circuits](https://mlsanity.com/paper/2405.09045/) (2024)
- [Finding the Needle in a Haystack: Test-Time Analog Circuit Representation Adaptation for Bayesian Optimization](https://mlsanity.com/paper/2608.12687/) (2026)

## Abstract (arXiv)

Automatic transistor sizing in circuit design continues to be a formidable challenge. Despite that Bayesian optimization (BO) has achieved significant success, it is circuit-specific, limiting the accumulation and transfer of design knowledge for broader applications. This paper proposes (1) efficient automatic kernel construction, (2) the first transfer learning across different circuits and technology nodes for BO, and (3) a selective transfer learning scheme to ensure only useful knowledge is utilized. These three novel components are integrated into BO with Multi-objective Acquisition Ensemble (MACE) to form Knowledge Alignment and Transfer Optimization (KATO) to deliver state-of-the-art performance: up to 2x simulation reduction and 1.2x design improvement over the baselines.