We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| inouye-lab/feddg_benchmark | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| Classifier | Ran | inouye-lab/feddg_benchmark/src/models.py pointer only (licence: NONE) · get_code("ce7990d7ad5821ff") |
| euclidean_proj_simplex | Ran | inouye-lab/feddg_benchmark/src/utils.py pointer only (licence: NONE) · get_code("1bae979767591485") |
| init_net | Ran | inouye-lab/feddg_benchmark/src/utils.py pointer only (licence: NONE) · get_code("0183a250efb28437") |
| remove_batch_norm_from_resnet | Ran | inouye-lab/feddg_benchmark/src/models.py pointer only (licence: NONE) · get_code("196cab71d7129d62") |
| code_gpt_py | Not yet run | inouye-lab/feddg_benchmark/src/models.py pointer only (licence: NONE) · get_code("8ac25d5a52bbeae7") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based heterogeneity in clients' local datasets - a realistic Federated DG scenario. Prior Federated DG evaluations are limited in terms of the number or heterogeneity of clients and dataset diversity. To address this gap, we propose an Federated DG benchmark methodology that enables control of the number and heterogeneity of clients and provides metrics for dataset difficulty. We then apply our methodology to evaluate 14 Federated DG methods, which include centralized DG methods adapted to the FL context, FL methods that handle client heterogeneity, and methods designed specifically for Federated DG. Our results suggest that despite some progress, there remain significant performance gaps in Federated DG particularly when evaluating with a large number of clients, high client heterogeneity, or more realistic datasets. Please check our extendable benchmark code here: https://github.com/inouye-lab/FedDG_Benchmark.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2307.04942")
get_code_for_paper("2307.04942")
have("2307.04942")
Connect an agent — have() is free.