We lifted 7 functions out of this paper's own repositories and ran 7 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 |
|---|---|---|
| Golden-Slumber/AirFL-2nd | canonical | 7 of 7 |
| Function | Status | Where it lives |
|---|---|---|
| accelerate_gradient | Ran | Golden-Slumber/AirFL-2nd/Utils/CrossEntropy.py code served (permissive licence) · get_code("adf7e835ad1f23b8") |
| accelerate_obj | Ran | Golden-Slumber/AirFL-2nd/Utils/CrossEntropy.py code served (permissive licence) · get_code("303ccb84996fc1ed") |
| conjugate_solver | Ran | Golden-Slumber/AirFL-2nd/Utils/conjugate_gradient_method.py code served (permissive licence) · get_code("d66d67212370a4c8") |
| load_data | Ran | Golden-Slumber/AirFL-2nd/Resources/data_loader.py code served (permissive licence) · get_code("9b67cfbb6604fc07") |
| normalization | Ran | Golden-Slumber/AirFL-2nd/Experiments/cross_entropy_demo.py code served (permissive licence) · get_code("3db4eda73fcaa60d") |
| stable_softmax | Ran | Golden-Slumber/AirFL-2nd/Utils/CrossEntropy.py code served (permissive licence) · get_code("dd326f5698315c6d") |
| svrg_solver | Ran | Golden-Slumber/AirFL-2nd/Utils/conjugate_gradient_method.py code served (permissive licence) · get_code("302d402e510927d3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Federated learning (FL) is a promising learning paradigm that can tackle the increasingly prominent isolated data islands problem while keeping users' data locally with privacy and security guarantees. However, FL could result in task-oriented data traffic flows over wireless networks with limited radio resources. To design communication-efficient FL, most of the existing studies employ the first-order federated optimization approach that has a slow convergence rate. This however results in excessive communication rounds for local model updates between the edge devices and edge server. To address this issue, in this paper, we instead propose a novel over-the-air second-order federated optimization algorithm to simultaneously reduce the communication rounds and enable low-latency global model aggregation. This is achieved by exploiting the waveform superposition property of a multi-access channel to implement the distributed second-order optimization algorithm over wireless networks. The convergence behavior of the proposed algorithm is further characterized, which reveals a linear-quadratic convergence rate with an accumulative error term in each iteration. We thus propose a system optimization approach to minimize the accumulated error gap by joint device selection and beamforming design. Numerical results demonstrate the system and communication efficiency compared with the state-of-the-art approaches.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.15488")
get_code_for_paper("2203.15488")
have("2203.15488")
Connect an agent — have() is free.