Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize the calibration data and importance estimation metrics in the structured pruning process. Specifically, AdaPruner effectively removes redundant parameters from LLMs by constructing a structured pruning solution space and then employing Bayesian optimization to adaptively search for the optimal calibration data and importance estimation metrics. Experimental results show that the AdaPruner outperforms existing structured pruning methods on a family of LLMs with varying pruning ratios, demonstrating its applicability and robustness. Remarkably, at a 20% pruning ratio, the model pruned with AdaPruner maintains 97% of the performance of the unpruned model.

Federated learning (FL) enables decentralized clients to collaboratively train a global model under the orchestration of a central server without exposing their individual data. However, the iterative exchange of model parameters between the server and clients imposes heavy communication burdens, risks potential privacy leakage, and even precludes collaboration among heterogeneous clients. Distillation-based FL tackles these challenges by exchanging low-dimensional model outputs rather than model parameters, yet it highly relies on a task-relevant auxiliary dataset that is often not available in practice. Data-free FL attempts to overcome this limitation by training a server-side generator to directly synthesize task-specific data samples for knowledge transfer. However, the update rule of the generator requires clients to share on-device models for white-box access, which greatly compromises the advantages of distillation-based FL. This motivates us to explore a data-free and black-box FL framework via Zeroth-order Gradient Estimation (FedZGE), which estimates the gradients after flowing through on-device models in a black-box optimization manner to complete the training of the generator in terms of fidelity, transferability, diversity, and equilibrium, without involving any auxiliary data or sharing any model parameters, thus combining the advantages of both distillation-based FL and data-free FL. Experiments on large-scale image classification datasets and network architectures demonstrate the superiority of FedZGE in terms of data heterogeneity, model heterogeneity, communication efficiency, and privacy protection.

The growing concerns and regulations surrounding the protection of user data privacy have necessitated decentralized training paradigms.To this end, federated learning (FL) is widely studied in user-related natural language processing (NLP).However, it suffers from several critical limitations including extensive communication overhead, inability to handle heterogeneity, and vulnerability to white-box inference attacks.Federated distillation (FD) is proposed to alleviate these limitations, but its performance is faded by confirmation bias.To tackle this issue, we propose Federated Interactive Distillation (FedID), which utilizes a small amount of labeled data retained by the server to further rectify the local models during knowledge transfer.Additionally, based on the GLUE benchmark, we develop a benchmarking framework across multiple tasks with diverse data distributions to contribute to the research of FD in NLP community.Experiments show that our proposed Fe-dID framework achieves the best results in homogeneous and heterogeneous federated scenarios.The code for this paper is available at: https://github.com/maxinge8698/FedID.

The billions, and sometimes even trillions, of parameters involved in pre-trained language models significantly hamper their deployment in resource-constrained devices and real-time applications. Knowledge distillation (KD) can transfer knowledge from the original model (i.e., teacher) into a compact model (i.e., student) to achieve model compression. However, previous KD methods have usually frozen the teacher and applied its immutable output feature maps as soft labels to guide the student’s training. Moreover, the goal of the teacher is to achieve the best performance on downstream tasks rather than knowledge transfer. Such a fixed architecture may limit the teacher’s teaching and student’s learning abilities. Herein, a knowledge distillation method with reptile meta-learning is proposed to facilitate the transfer of knowledge from the teacher to the student. The teacher can continuously meta-learn the student’s learning objective to adjust its parameters for maximizing the student’s performance throughout the distillation process. In this way, the teacher learns to teach, produces more suitable soft labels, and transfers more appropriate knowledge to the student, resulting in improved performance. Unlike previous KD using meta-learning, the proposed method only needs to calculate the first-order derivatives to update the teacher, leading to lower computational cost but better convergence. Extensive experiments on the GLUE benchmark show the competitive performance achieved by the proposed method. For reproducibility, the code for this paper is available at: https://github.com/maxinge8698/ReptileDistil.