Research map / Federated learning and privacy / Personalized and heterogeneous FL
DA-DFGAS:Differentiable Federated Graph Neural Architecture Search with Distribution-Aware Attentive Aggregation
Zhaowei Liu, Yihao Jiang, Rufei Gao, Jinglei Liu, Dong Yang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add distribution-aware aggregation (vs data-volume weighting) (ablation) | DA-DFGAS · DBLP | accuracy (%): 58.67 -> 59.36 | Improved |
| add distribution-aware aggregation (vs data-volume weighting) (ablation) | DA-DFGAS · SBM PATTERN | accuracy (%): 86.77 -> 87.35 | Improved |
| add system-heterogeneity handling (FedNova normalization and selection) (ablation) | DA-DFGAS · SBM PATTERN | communication rounds: 144 -> 118 | Improved |
| add proximal regularization to local objective (ablation) | DA-DFGAS · DBLP | communication rounds: 172 -> 97 | Improved |
| add proximal regularization to local objective (ablation) | DA-DFGAS · SBM PATTERN | accuracy (%): 86.31 -> 87.35 | Improved |
| differentiable search instead of RL-based search | federated GNN NAS · SBM PATTERN | search time (h): 1.8 -> 1.2 | Improved |
| add attention mechanism to aggregation | DA-DFGAS · Table 4 datasets | parameters: about 5-10% more parameters | Hurt |
| set similarity scaling factor tau to 1.0 (vs too small or too large) (ablation) | DA-DFGAS · Cora | accuracy | Mixed |
| set architecture smoothing constant T around 60 (ablation) | DA-DFGAS · Cora | accuracy | Mixed |
| use DA-DFGAS aggregation instead of FedProx/FedNova on GCN backbone | FedGNN with fixed GCN backbone · SBM CLUSTER | accuracy (%): 59.67 -> 60.56 | Improved |
| DA-DFGAS vs FED-PUB on DBLP in Table 3 vs Table 5 | DA-DFGAS · DBLP | accuracy (%): 59.36 (Table 3) vs 58.61 (Table 5, GCN backbone) | Mixed |
Closest papers by meaning
- Large Language Models Enhanced Personalized Graph Neural Architecture Search in Federated Learning (AAAI 2025 · similarity 0.90)
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (NeurIPS 2024 · similarity 0.88)
- FedGOG: Federated Graph Out-of-Distribution Generalization with Diffusion Data Exploration and Latent Embedding Decorrelation (AAAI 2025 · similarity 0.87)
- Federated Graph Condensation with Information Bottleneck Principles (AAAI 2025 · similarity 0.87)
- Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective (ICML 2025 · similarity 0.86)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.86)
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.
