Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation

To address this, et al., 2017) and becomes an even more critical our methodology, MetaSend, incorporates a metalearning challenge with large-scale NMT models. The result is depicted multilingual NMT performance over an FL system by the blue thresholds for the cases in Figure 1. A premise doing so, MetaSend considers translation quality for our work is that exchanging complete NMT and communication efficiency as important objectives engines in FL might not be necessary, similar to in multilingual NMT training. We can develop MetaSend, we make three major contributions: some intuition around this through a small We conduct the first research on the communication FL experiment using the well-known FedAVG algorithm efficiency of FL in multilingual NMT, (McMahan et al., 2017). In Figure 1, we perform and study the relationship between translation FL on the UN Corpus dataset (see Section 4 quality and the volume of transmitted parameters for details) distributed across three clients (each in multilingual NMT engines.