We lifted 11 functions out of this paper's own repositories and ran 11 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 |
|---|---|---|
| umd-huang-lab/RealFM | canonical | 11 of 11 |
| Function | Status | Where it lives |
|---|---|---|
| accuracy | Ran | umd-huang-lab/RealFM/simulations.py pointer only (licence: NONE) · get_code("f03dc6c15ee4608e") |
| accuracy | Ran | umd-huang-lab/RealFM/utils/equilibrium.py pointer only (licence: NONE) · get_code("52d9a1efc7975ce6") |
| accuracy_utility | Ran | umd-huang-lab/RealFM/simulations.py pointer only (licence: NONE) · get_code("127afa65a4cb4bf2") |
| accuracy_utility | Ran | umd-huang-lab/RealFM/utils/equilibrium.py pointer only (licence: NONE) · get_code("9ec7e78c352e31a1") |
| accuracy_utility_dx | Ran | umd-huang-lab/RealFM/utils/equilibrium.py pointer only (licence: NONE) · get_code("cbc9e362b3b8cc7f") |
| bootstrapping | Ran | umd-huang-lab/RealFM/plotter.py pointer only (licence: NONE) · get_code("4c29c95890abe0ac") |
| date_string | Ran | umd-huang-lab/RealFM/utils/recorder.py pointer only (licence: NONE) · get_code("955b5a9769de51d2") |
| generate_confidence_interval | Ran | umd-huang-lab/RealFM/plotter.py pointer only (licence: NONE) · get_code("338b3d6cb6ee50a5") |
| non_iid_dirichlet | Ran | umd-huang-lab/RealFM/utils/data_loading.py pointer only (licence: NONE) · get_code("a1fbde5d0872554d") |
| unpack_data | Ran | umd-huang-lab/RealFM/plotter.py pointer only (licence: NONE) · get_code("d41b045c77e331a8") |
| utility | Ran | umd-huang-lab/RealFM/simulations.py pointer only (licence: NONE) · get_code("ee4d2120a78e2a2b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Edge device participation in federating learning (FL) is typically studied through the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in realistic settings, with many encountering the free-rider dilemma. In a step to push FL towards realistic settings, we propose RealFM: the first federated mechanism that (1) realistically models device utility, (2) incentivizes data contribution and device participation, (3) provably removes the free-rider dilemma, and (4) relaxes assumptions on data homogeneity and data sharing. Compared to previous FL mechanisms, RealFM allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices. On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.13681")
get_code_for_paper("2310.13681")
have("2310.13681")
Connect an agent — have() is free.