Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation
Keywords: Federated Learning, Decentralized Learning, Scene Graph Generation
TL;DR: Benchmark for Semantic Dataset in Federated Learning
Abstract: Federated learning (FL) has recently garnered attention as a decentralized training framework that enables the learning of deep models from locally distributed samples while keeping the data privacy.
Built upon the framework, immense efforts have been made to establish FL benchmarks, which provide rigorous evaluation settings that aim to control data heterogeneity across clients.
Prior efforts have mainly focused on handling relatively simple classification tasks, where each sample is annotated with a one-hot label, such as MNIST, CIFAR, LEAF benchmark, etc.
However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse semantic information from multiple labels, such as Scene Graph Generation / Panoptic Scene Graph Generation (SGG/PSG) with objects, predicates, and relations between objects.
Because the existing benchmark is designed to distribute data in a narrow view of a single semantic, e.g., a one-hot label, managing the complicated $\textit{semantic heterogeneity}$ across clients when formalizing FL benchmarks is non-trivial.
In this paper, we propose a benchmark process to establish an FL benchmark with controllable semantic heterogeneity across clients: two key steps are i) data clustering with semantics and ii) data distributing via controllable semantic heterogeneity across clients.
As a proof of concept, we first construct a federated SGG/PSG benchmark, which demonstrates the efficacy of the existing PSG methods in an FL setting with controllable semantic heterogeneity of scene graphs.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6569
Loading