We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared to periodically communicating state-of-the-art approaches. Moreover, we derive a communication bound that scales well with the hardness of the serialized learning problem. The reduction in communication comes at almost no cost, as the predictive performance remains virtually unchanged. Indeed, the proposed protocol retains loss bounds of periodically averaging schemes. An extensive empirical evaluation validates major improvement of the trade-off between model performance and communication which could be beneficial for numerous decentralized learning applications, such as autonomous driving, or voice recognition and image classification on mobile phones.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1807.03210")
get_code_for_paper("1807.03210")
have("1807.03210")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1807.03210.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1807.03210)
Connect an agent — have() is free.