no code implementations • 15 Feb 2024 • Shengrui Li, Xueting Han, Jing Bai
Structured pruning, offers an effective means to compress LLMs, thereby reducing storage costs and enhancing inference speed for more efficient utilization.
no code implementations • 16 Jun 2023 • Dongshuo Yin, Xueting Han, Bin Li, Hao Feng, Jing Bai
We provide a gradient backpropagation highway for low-rank adapters which eliminates the need for expensive backpropagation through the frozen pre-trained model, resulting in substantial savings of training memory and training time.
1 code implementation • 13 Jun 2023 • Haozhen Zhang, Xueting Han, Xi Xiao, Jing Bai
To address these issues, we propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs, which learns better graph structures for downstream tasks through adding potential temporal edges.
1 code implementation • 19 Apr 2023 • Shengrui Li, Xueting Han, Jing Bai
AdapterGNN preserves the knowledge of the large pre-trained model and leverages highly expressive adapters for GNNs, which can adapt to downstream tasks effectively with only a few parameters, while also improving the model's generalization ability.
1 code implementation • 19 Jul 2021 • Xueting Han, Zhenhuan Huang, Bang An, Jing Bai
We design an adaptive auxiliary loss weighting model to learn the weights of auxiliary tasks by quantifying the consistency between auxiliary tasks and the target task.