# Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

arXiv: https://arxiv.org/abs/2004.11262 · HTML: https://mlsanity.com/paper/2004.11262/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey](https://mlsanity.com/paper/2106.02154/) (2021)
- [Unsupervised Domain Adaptation for Constraining Star Formation Histories](https://mlsanity.com/paper/2112.14072/) (2021)
- [Best-Effort Adaptation](https://mlsanity.com/paper/2305.05816/) (2023)
- [Fighting Money Laundering with Statistics and Machine Learning](https://mlsanity.com/paper/2201.04207/) (2022)
- [Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classification](https://mlsanity.com/paper/2207.11577/) (2022)
- [DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation](https://mlsanity.com/paper/2409.08946/) (2024)
- [Efficient Online Processing with Deep Neural Networks](https://mlsanity.com/paper/2306.13474/) (2023)
- [GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging](https://mlsanity.com/paper/2606.13919/) (2026)

## Abstract (arXiv)

Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding in which the domain labels are incorporated into the structure of the intrinsic and penalty graphs. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding. Moreover, we highlight some generalisation and reproducibility issues related to the experimental setup commonly used to demonstrate the few-shot learning capabilities of these methods. To assess and compare Supervised Domain Adaptation methods accurately, we propose a rectified evaluation protocol, and report updated benchmarks on the standard datasets Office31 (Amazon, DSLR, and Webcam), Digits (MNIST, USPS, SVHN, and MNIST-M) and VisDA (Synthetic, Real).