Experimental results on both quality estimation of machine translation and cross-lingual semantic textual similarity tasks reveal that our method consistently outperforms the strong baselines using the original multilingual embedding.
We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs.
Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration scales with model dimension, hindering the learning capability significantly.
Federated learning is a distributed machine learning approach in which a single server and multiple clients collaboratively build machine learning models without sharing datasets on clients.
Nowadays, so as to improve services and urban areas livability, multiple smart city initiatives are being carried out throughout the world.
First, to optimize the model architectures for local data, clients tune their own personalized models by comparing to exchanged models and picking the one that yields the best performance.
Since existing methods aim to infer air quality of locations only in monitored cities, they do not assume inferring air quality in unmonitored cities.
Curriculum learning has improved the quality of neural machine translation, where only source-side features are considered in the metrics to determine the difficulty of translation.
That is, our algorithm generates failure patterns when a partial embedding is found unable to become an isomorphic embedding.
The feature extraction model transforms original data and threshold to a Hamming space, in which a deep learning-based regression model is utilized to exploit the incremental property of cardinality w. r. t.