With the prevalence of pre-trained language models (PLMs) and the pre-training–fine-tuning paradigm, it has been continuously shown that larger models tend to yield better performance. However, as PLMs scale up, fine-tuning and storing all the parameters is prohibitively costly and eventually becomes practically infeasible. This necessitates a new branch of research focusing on the parameter-efficient adaptation of PLMs, which optimizes a small portion of the model parameters while keeping the rest fixed, drastically cutting down computation and storage costs. In general, it demonstrates that large-scale models could be effectively stimulated by the optimization of a few parameters. Despite the various designs, here we discuss and analyse the approaches under a more consistent and accessible term ‘delta-tuning’, where ‘delta’ a mathematical notation often used to denote changes, is borrowed to refer to the portion of parameters that are ‘changed’ during training. We formally describe the problem and propose a unified categorization criterion for existing delta-tuning methods to explore their correlations and differences. We also discuss the theoretical principles underlying the effectiveness of delta-tuning and interpret them from the perspectives of optimization and optimal control. Furthermore, we provide a holistic empirical study on over 100 natural language processing tasks and investigate various aspects of delta-tuning. With comprehensive study and analysis, our research demonstrates the theoretical and practical properties of delta-tuning in the adaptation of PLMs.

Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, Maosong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

To accelerate biomedical research process, deep-learning systems are developed to automatically acquire knowledge about molecule entities by reading large-scale biomedical data. Inspired by humans that learn deep molecule knowledge from versatile reading on both molecule structure and biomedical text information, we propose a knowledgeable machine reading system that bridges both types of information in a unified deep-learning framework for comprehensive biomedical research assistance. We solve the problem that existing machine reading models can only process different types of data separately, and thus achieve a comprehensive and thorough understanding of molecule entities. By grasping meta-knowledge in an unsupervised fashion within and across different information sources, our system can facilitate various real-world biomedical applications, including molecular property prediction, biomedical relation extraction and so on. Experimental results show that our system even surpasses human professionals in the capability of molecular property comprehension, and also reveal its promising potential in facilitating automatic drug discovery and documentation in the future.

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Humans possess an extraordinary ability to create and utilize tools. With the advent of foundation models, artificial intelligence systems have the potential to be equally adept in tool use as humans. This paradigm, which is dubbed as tool learning with foundation models , combines the strengths of tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. This article presents a systematic investigation and comprehensive review of tool learning. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research and formulate a general framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate generalization in tool learning. Finally, we discuss several open problems that require further investigation, such as ensuring trustworthy tool use, enabling tool creation with foundation models, and addressing personalization challenges. Overall, we hope this article could inspire future research in integrating tools with foundation models.

Network representation learning (NRL) aims to learn low-dimensional vectors for vertices in a network. Most existing NRL methods focus on learning representations from local context of vertices (such as their neighbors). Nevertheless, vertices in many complex networks also exhibit significant global patterns widely known as communities. It's intuitive that vertices in the same community tend to connect densely and share common attributes. These patterns are expected to improve NRL and benefit relevant evaluation tasks, such as link prediction and vertex classification. Inspired by the analogy between network representation learning and text modeling, we propose a unified NRL framework by introducing community information of vertices, named as Community-enhanced Network Representation Learning (CNRL). CNRL simultaneously detects community distribution of each vertex and learns embeddings of both vertices and communities. Moreover, the proposed community enhancement mechanism can be applied to various existing NRL models. In experiments, we evaluate our model on vertex classification, link prediction, and community detection using several real-world datasets. The results demonstrate that CNRL significantly and consistently outperforms other state-of-the-art methods while verifying our assumptions on the correlations between vertices and communities