vf5aUZT0Fz@OpenReview

Total: 1

#1 DEPT: Decoupled Embeddings for Pre-training Language Models [PDF85] [Copy] [Kimi135] [REL]

Authors: Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, William Shen, Xinchi Qiu, Dongqi Cai, Yan Gao, Nic Lane

Past works have shown that lexical, syntactical, and semantical differences in heterogeneous data sources can cause challenges such as negative interference or the ``curse of multilinguality''. Because of this, training on such heterogeneous corpora requires extensive and costly efforts to balance data mixtures. We propose a novel pre-training framework to alleviate this curse. Our method, DEPT, decouples embeddings from the transformer body while simultaneously training the latter in multiple contexts without a shared global vocabulary. DEPT: (1) trains robustly and effectively under significant data heterogeneity, (2) reduces token embedding parameters by up to 80% and communication costs by 714x for billion-scale models, (3) enhances transformer body plasticity and generalization, improving average perplexity upward of 15.3-20% and improving performance for downstream fine-tuning in our experiments, and (4) permits training with custom optimized vocabularies per data source. We demonstrate DEPT's potential via the first vocabulary-agnostic federated multilingual pre-training of a billion-scale model, reducing total parameters by 24% versus standard training.

Subject: ICLR.2025 - Oral