Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding

no code implementations • 19 May 2023 • Mingliang Zhai, Yulin Li, Xiameng Qin, Chen Yi, Qunyi Xie, Chengquan Zhang, Kun Yao, Yuwei Wu, Yunde Jia

Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length.

document understanding

Latency Aware Semi-synchronous Client Selection and Model Aggregation for Wireless Federated Learning

no code implementations • 19 Oct 2022 • Liangkun Yu, Xiang Sun, Rana Albelaihi, Chen Yi

This traditional FL process may suffer from the straggler problem in heterogeneous client settings, where the FL server has to wait for slow clients to upload their local models in each global iteration, thus increasing the overall training time.

Federated Learning