Dynamic Transfer Learning across Graphs

by   Haohui Wang, et al.

Transferring knowledge across graphs plays a pivotal role in many high-stake domains, ranging from transportation networks to e-commerce networks, from neuroscience to finance. To date, the vast majority of existing works assume both source and target domains are sampled from a universal and stationary distribution. However, many real-world systems are intrinsically dynamic, where the underlying domains are evolving over time. To bridge the gap, we propose to shift the problem to the dynamic setting and ask: given the label-rich source graphs and the label-scarce target graphs observed in previous T timestamps, how can we effectively characterize the evolving domain discrepancy and optimize the generalization performance of the target domain at the incoming T+1 timestamp? To answer the question, for the first time, we propose a generalization bound under the setting of dynamic transfer learning across graphs, which implies the generalization performance is dominated by domain evolution and domain discrepancy between source and target domains. Inspired by the theoretical results, we propose a novel generic framework DyTrans to improve knowledge transferability across dynamic graphs. In particular, we start with a transformer-based temporal encoding module to model temporal information of the evolving domains; then, we further design a dynamic domain unification module to efficiently learn domain-invariant representations across the source and target domains. Finally, extensive experiments on various real-world datasets demonstrate the effectiveness of DyTrans in transferring knowledge from dynamic source domains to dynamic target domains.


page 1

page 2

page 3

page 4


Non-IID Transfer Learning on Graphs

Transfer learning refers to the transfer of knowledge or information fro...

Continuous Transfer Learning with Label-informed Distribution Alignment

Transfer learning has been successfully applied across many high-impact ...

Augmenting Knowledge Transfer across Graphs

Given a resource-rich source graph and a resource-scarce target graph, h...

Quantifying and Improving Transferability in Domain Generalization

Out-of-distribution generalization is one of the key challenges when tra...

A Unified Meta-Learning Framework for Dynamic Transfer Learning

Transfer learning refers to the transfer of knowledge or information fro...

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

Domain generalization aims to improve the generalization capability of m...

Characterizing Long-Tail Categories on Graphs

Long-tail data distributions are prevalent in many real-world networks, ...

Please sign up or login with your details

Forgot password? Click here to reset