Domain Adaptation on Graphs by Learning Aligned Graph Bases

Pilanci, Mehmet; Vural, Elif

doi:10.1109/tkde.2020.2984212

Cited by 45 publications

(12 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This shows that shifting the size of GCN layers to predict the brain graphs with a different resolution from the base one is not sufficient for getting an accurate prediction. Thereby, as a future research direction, we will include a domain alignment component in our architecture which will boost the prediction of brain graphs with different resolutions [26,27].…”

Section: Resultsmentioning

confidence: 99%

A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint

Bessadok¹,

Nebli²,

Mahjoub³

et al. 2021

Preprint

View full text Add to dashboard Cite

Charting the baby connectome evolution trajectory during the first year after birth plays a vital role in understanding dynamic connectivity development of baby brains. Such analysis requires acquisition of longitudinal connectomic datasets. However, both neonatal and postnatal scans are rarely acquired due to various difficulties. A small body of works has focused on predicting baby brain evolution trajectory from a neonatal brain connectome derived from a single modality. Although promising, large training datasets are essential to boost model learning and to generalize to a multi-trajectory prediction from different modalities (i.e., functional and morphological connectomes). Here, we unprecedentedly explore the question: "Can we design a few-shot learningbased framework for predicting brain graph trajectories across different modalities?" To this aim, we propose a Graph Multi-Trajectory Evolution Network (GmTE-Net), which adopts a teacher-student paradigm where the teacher network learns on pure neonatal brain graphs and the student network learns on simulated brain graphs given a set of different timepoints. To the best of our knowledge, this is the first teacherstudent architecture tailored for brain graph multi-trajectory growth prediction that is based on few-shot learning and generalized to graph neural networks (GNNs). To boost the performance of the student network, we introduce a local topology-aware distillation loss that forces

show abstract

Section: Resultsmentioning

confidence: 99%

A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint

Bessadok¹,

Nebli²,

Mahjoub³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Usually they focus on adaptation between two domains where data points themselves are graphs. For example, (Pilancı & Vural, 2019;Pilanci & Vural, 2020) use frequency analysis to align the data graphs between the source domain and the target domains, and (Alam et al, 2018;Ding et al, 2018) perform label propagation on the data graph.…”

Section: Domain Adaptation Related Tomentioning

confidence: 99%

Graph-Relational Domain Adaptation

Zhang¹,

he²,

Lee³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing domain adaptation methods tend to treat every domain equally and align them all perfectly. Such uniform alignment ignores topological structures among different domains; therefore it may be beneficial for nearby domains, but not necessarily for distant domains. In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency, e.g., a graph of states in the US with each state as a domain and each edge indicating adjacency, thereby allowing domains to align flexibly based on the graph structure. We generalize the existing adversarial learning framework with a novel graph discriminator using encodingconditioned graph embeddings. Theoretical analysis shows that at equilibrium, our method recovers classic domain adaptation when the graph is a clique, and achieves non-trivial alignment for other types of graphs. Empirical results show that our approach successfully generalizes uniform alignment, naturally incorporates domain information represented by graphs, and improves upon existing domain adaptation methods on both synthetic and real-world datasets 1 .

show abstract

“…However, these works mainly focus on the node classification, by simply replacing the feature extractor with the graph convolutional network, without taking the property of the graph-structured data into account. Recently, Elif et al [40], [41] handle graph domain adaptation via learning aligned graph bases. In this paper, we not only focus on the challenging graph classification task but also well utilize the property of graph-structured data via the generation process of graph-structured data.…”

Section: Graph Domain Adaptationmentioning

confidence: 99%

Graph Domain Adaptation: A Generative View

Cai,

Wu,

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, current graph domain adaptation methods are generally adopted from traditional domain adaptation tasks, and the properties of graph-structured data are not well utilized. For example, the observed social networks on different platforms are controlled not only by the different crowd or communities but also by the domain-specific policies and the background noise. Based on these properties in graph-structured data, we first assume that the graph-structured data generation process is controlled by three independent types of latent variables, i.e., the semantic latent variables, the domain latent variables, and the random latent variables. Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules. Extensive experimental results on two real-world datasets in the graph classification task reveal that our method not only significantly outperforms the traditional domain adaptation methods and the disentangled-based domain adaptation methods but also outperforms the state-of-the-art graph domain adaptation algorithms.

show abstract

Domain Adaptation on Graphs by Learning Aligned Graph Bases

Cited by 45 publications

References 50 publications

A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint

A Few-shot Learning Graph Multi-Trajectory Evolution Network for Forecasting Multimodal Baby Connectivity Development from a Baseline Timepoint

Graph-Relational Domain Adaptation

Graph Domain Adaptation: A Generative View

Contact Info

Product

Resources

About