AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Federated Continual Instruction Tuning

Haiyang Guo, Fanhu Zeng, Fei Zhu, Wenzhuo Liu, Da-Han Wang, Jian Xu, Xu-Yao Zhang, Cheng-Lin Liu

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 13 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use text-encoder identity tokens instead of image features (ablation)DISCO · Hom-FCIT task-related beta=1.0Last accuracy: 56.22 -> 55.63 without (image only)Improved
use text-only identity tokens instead of text and image combined (ablation)DISCO · Hom-FCIT task-related beta=1.0Last accuracy: 56.22 -> 55.96 without (text & image)Improved
softmax-normalised similarity for activation instead of concatenation (ablation)DISCO SSA · Hom-FCIT task-related beta=1.0Last accuracy: 51.74 -> 56.22Improved
softmax-normalised similarity instead of raw cosine similarity (ablation)DISCO SSA · Hom-FCIT task-related beta=1.0Last accuracy: 52.83 -> 56.22Improved
softmax instead of argmax selection of subspace (ablation)DISCO SSA · Hom-FCIT task-related beta=1.0Last accuracy: 55.74 -> 56.22Improved
softmax instead of concatenation (ablation)DISCO SSA · Het-FCIT task-related beta=1.0Last accuracy: 60.36 -> 63.25Improved
LoRA in FFN instead of attention only (ablation)DISCO · Hom-FCIT task-related beta=1.0Last accuracy: 56.03 -> 56.22Improved
LoRA in all linear layers (FFN and attention) instead of FFN only (ablation)DISCO · Hom-FCIT task-related beta=1.0Last accuracy: 56.22 -> 56.30No clear effect
FedAvg instead of FedAdam aggregation (ablation)DISCO · Hom-FCIT task-related beta=1.0Last accuracy: 55.76 -> 56.22Improved
FedAvg instead of FedYogi aggregation (ablation)DISCO · Hom-FCIT task-related beta=1.0Avg accuracy: 73.16 vs 73.03No clear effect
DISCO instead of O-LoRAFederated continual instruction tuning · Hom-FCIT task-related beta=1.0Last accuracy: 49.87 -> 56.22Improved
DISCO instead of FinetuneFederated continual instruction tuning · Het-FCIT task-related beta=1.0Avg accuracy: 54.22 -> 61.99Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy