Popularity Prediction for Social Media over Arbitrary Time Horizons
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
International Conference on Machine Learning (ICML)
Task-specific fine-tuning on pre-trained transformers has achieved performance breakthroughs in multiple NLP tasks. Yet, as both computation and parameter size grows linearly with the number of sub-tasks, such methods are increasingly difficult to adopt in the real world due to unrealistic memory and computation overhead on computing devices. Previous works on fine-tuning focus on reducing the growing parameter size to save storage cost by parameter sharing. However, compared to storage, the constraint of computation is a more critical issue with the fine-tuning models in modern computing environments; prior works fall short on computation reduction.
To enable efficient fine-tuning, we propose LeTS, a framework that leverages both computation and parameter sharing across multiple tasks. LeTS consists of two principles. First, LeTS decouples the computation dependency in traditional fine-tuning model by proposing a novel neural architecture to reuse the intermediate results computed from the pre-trained model and the input. Furthermore, we leverage differentiable neural architecture search to determine task-specific computation sharing scheme. Second, by treating the final weight parameters as a weight difference added to the pre-trained weight, we propose a novel early stage pruning approach to generate a mask at the beginning of fine-tuning. By combining these two principles, LeTS further reduces the computation demand by exploiting the sparsity feature of weight difference. Extensive experiments show that with 1.4% of extra parameters per task, LeTS reduces the computation by 49.5% on GLUE benchmarks with only 0.2% accuracy loss compared to the full fine-tuning method.
Daniel Haimovich, Dima Karamshuk, Thomas Leeper, Evgeniy Riabenko, Milan Vojnovic
Liqi Yan, Qifan Wang, Yiming Cu, Fuli Feng, Xiaojun Quan, Xiangyu Zhang, Dongfang Liu
Barlas Oğuz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih