Neural Architecture Search for Effective Teacher-Student Knowledge Transfer in Language Models
Trivedi, Aashka, Udagawa, Takuma, Merler, Michele, Panda, Rameswar, El-Kurdi, Yousef, Bhattacharjee, Bishwaranjan
–arXiv.org Artificial Intelligence
Large pretrained language models have achieved state-of-the-art results on a variety of downstream tasks. Knowledge Distillation (KD) into a smaller student model addresses their inefficiency, allowing for deployment in resource-constrained environments. However, KD can be ineffective when the student is manually selected from a set of existing options, since it can be a sub-optimal choice within the space of all possible student architectures. We develop multilingual KD-NAS, the use of Neural Architecture Search (NAS) guided by KD to find the optimal student architecture for task agnostic distillation from a multilingual teacher. In each episode of the search process, a NAS controller predicts a reward based on the distillation loss and latency of inference. The top candidate architectures are then distilled from the teacher on a small proxy set. Finally the architecture(s) with the highest reward is selected, and distilled on the full training corpus. KD-NAS can automatically trade off efficiency and effectiveness, and recommends architectures suitable to various latency budgets. Using our multi-layer hidden state distillation process, our KD-NAS student model achieves a 7x speedup on CPU inference (2x on GPU) compared to a XLM-Roberta Base Teacher, while maintaining 90% performance, and has been deployed in 3 software offerings requiring large throughput, low latency and deployment on CPU.
arXiv.org Artificial Intelligence
Oct-13-2023
- Country:
- Asia > China (0.14)
- North America > Canada (0.14)
- Genre:
- Research Report (0.64)
- Industry:
- Education (1.00)
- Technology: