A COMPREHENSIVE SURVEY OF MEMORY UPDATE MECHANISMS FOR CONTINUAL LEARNING ON TEXT DATASETS
Main Article Content
Abstract
Over the last several years, there has been a growing focus on the CL field in the context of machine learning and its goal to create models capable of learning new tasks step by step without loss of prior knowledge. Among these, catastrophic forgetting is especially challenging in real-world settings where the data experience changes over time. To this effect, what has become pivotal for models is mechanisms for memory update to enable the models to learn information as well as update what has been previously learned easily. This survey specifically investigates the memory update strategy in the continual learning setup wherein new categories and domains are continuously added in the text datasets including sentiment analysis, named entity recognition, text classification tasks etc. Moving on, three primary memory update strategies of memory replay, memory consolidation, and parameter isolation are discussed; this paper further addresses certain adaptations of the proposed methods for text-based applications. Memory replay means that part of previous data is stored to be replayed when new tasks are learned while memory consolidation strengthens only significant memories. Parameter isolation helps avoid masking previous tasks or overwriting the parameters when the machine learning algorithm is trained to accomplish new tasks. In this paper, we discuss the latest in these techniques and offer a thorough insight into their use in text datasets such as Amazon Reviews and Yelp Reviews. Further, we outline the primary drawbacks of existing solutions for memory updates such as capacity limitations, domain variation, and continually learning without having access to new task information. In addition, a summary table of literature review identifying the most relevant works within the field is offered. Lastly, we discuss the remaining issues and potential research directions where more focus and development should be given in CL for text data by noting the importance of efficient and adaptive update policies towards the memory.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
References
Liu, An-an, Haochun Lu, Heyu Zhou, Tianbao Li, and Mohan S. Kankanhalli. "Balanced Class-Incremental 3D Object Classification and Retrieval." IEEE Transactions on Knowledge and Data Engineering 36 (2024): 35-48.
Zhu, Jun, Yuanfan Wang, Cheng-Geng Huang, Changqing Shen, and Bojian Chen. "A New Incremental Learning for Bearing Fault Diagnosis Under Noisy Conditions Using Classification and Feature-Level Information." IEEE Transactions on Instrumentation and Measurement 73 (2024): 1-14.
Yan, Jingsong, Piji Li, Haibin Chen, Junhao Zheng, and Qianli Ma. "Does the Order Matter? A Random Generative Way to Learn Label Hierarchy for Hierarchical Text Classification." IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024): 276-285.
Kong, Jun, Jin Wang, and Xuejie Zhang. "Adaptive Ensemble Self-Distillation With Consistent Gradients for Fast Inference of Pretrained Language Models." IEEE/ACM Transactions on Audio, Speech, and Language Processing 32 (2024): 430-442.
Qorich, Mohammed, and Rajae El Ouazzani. "Optimizer Algorithms and Convolutional Neural Networks for Text Classification." IAES International Journal of Artificial Intelligence (IJ-AI) 13 (2024): 451-458.
Luo, Yun, Xiaotian Lin, Zhen Yang, Fandong Meng, Jie Zhou, and Yue Zhang. "Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion." ArXiv abs/2305.12270 (2023).
Song, Yifan, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, and Sujian Li. "InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective." ArXiv abs/2310.06362 (2023)..
Zhang, Duzhen, Wei Cong, Jiahua Dong, Yahan Yu, Xiuyi Chen, Yonggang Zhang, and Zhen Fang. "Continual Named Entity Recognition without Catastrophic Forgetting." ArXiv abs/2310.14541 (2023).
Li, Xingyu, Bo Tang, and Haifeng Li. "AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning." ArXiv abs/2308.03810 (2023).
Wang, Jue, Dajie Dong, L. Shou, Ke Chen, and Gang Chen. "Effective Continual Learning for Text Classification with Lightweight Snapshots." AAAI Conference on Artificial Intelligence (2023): 10122-10130.
Prabhu, Ameya, Zhipeng Cai, P. Dokania, Philip H. S. Torr, V. Koltun, and Ozan Sener. "Online Continual Learning Without the Storage Constraint." ArXiv abs/2305.09253 (2023).
Harun, Md Yousuf, Jhair Gallardo, Tyler L. Hayes, and Christopher Kanan. "How Efficient Are Today’s Continual Learning Algorithms?" 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023): 2431-2436.
Winata, Genta Indra, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, and Daniel Preotiuc-Pietro. "Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning." ArXiv abs/2305.16252 (2023).
Wang, Liyuan, Xingxing Zhang, Qian Li, Mingtian Zhang, Hang Su, Jun Zhu, and Yi Zhong. "Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence." ArXiv abs/2308.14991 (2023).
Liang, Yanyan, and Wu-Jun Li. "Adaptive Plasticity Improvement for Continual Learning." 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023): 7816-7825.
Zhang, Jie, Chen Chen, Weiming Zhuang, and LingJuan Lv. "Addressing Catastrophic Forgetting in Federated Class-Continual Learning." ArXiv abs/2303.06937 (2023).
Wang, Tiancheng, Huaping Liu, Di Guo, and Xi-Ming Sun. "Continual Residual Reservoir Computing for Remaining Useful Life Prediction." IEEE Transactions on Industrial Informatics 20 (2024): 931-940.
Ma, Bingtao, Yang Cong, and Jiahua Dong. "Topology-Aware Graph Convolution Network for Few-Shot Incremental 3-D Object Learning." IEEE Transactions on Systems, Man, and Cybernetics: Systems 54 (2024): 324-337.
Harun, Md Yousuf, Jhair Gallardo, Tyler L. Hayes, and Christopher Kanan. "How Efficient Are Today’s Continual Learning Algorithms?" 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023): 2431-2436.
Jin, Xisen, Arka Sadhu, Junyi Du, and Xiang Ren. "Gradient Based Memory Editing for Task-Free Continual Learning." ArXiv (2020).
Yao, Xuanrong, Xin Wang, Yue Liu, and Wenwu Zhu. "Continual Recognition with Adaptive Memory Update." ACM Transactions on Multimedia Computing, Communications, and Applications (2022).
Javed, Khurram, and Martha White. "Meta-Learning Representations for Continual Learning." ArXiv (2019).
Gao, Yuyang, G. Ascoli, and Liang Zhao. "Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning." Neural Networks 144 (2021): 49-60.
Chen, Xi, Christos Papadimitriou, and Binghui Peng. "Memory Bounds for Continual Learning." 2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS) (2022): 519-530.
Wang, Liyuan, Xingxing Zhang, Qian Li, et al. "Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence." ArXiv (2023).
Wang, Zhen, Liu Liu, Yiqun Duan, et al. "Continual Learning with Lifelong Vision Transformer." 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022): 171-181.
Shi, Yujun, Li Yuan, Yunpeng Chen, and Jiashi Feng. "Continual Learning via Bit-Level Information Preserving." 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 16669-16678.
Graffieti, G., G. Borghi, and D. Maltoni. "Continual Learning in Real-Life Applications." IEEE Robotics and Automation Letters 7 (2022): 6195-6202.