Benchmarking Continual Learning from Cognitive Perspectives

• URL: http://arxiv.org/abs/2312.03309v1
• Date: Wed, 6 Dec 2023 06:27:27 GMT
• Title: Benchmarking Continual Learning from Cognitive Perspectives
• Authors: Xiaoqian Liu, Junge Zhang, Mingyi Zhang, Peipei Yang
• Abstract summary: Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. There is a mismatch between cognitive properties and evaluation methods of continual learning models. We propose to integrate model cognitive capacities and evaluation metrics into a unified evaluation paradigm.
• Score: 14.867136605254975
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning addresses the problem of continuously acquiring and transferring knowledge without catastrophic forgetting of old concepts. While humans achieve continual learning via diverse neurocognitive mechanisms, there is a mismatch between cognitive properties and evaluation methods of continual learning models. First, the measurement of continual learning models mostly relies on evaluation metrics at a micro-level, which cannot characterize cognitive capacities of the model. Second, the measurement is method-specific, emphasizing model strengths in one aspect while obscuring potential weaknesses in other respects. To address these issues, we propose to integrate model cognitive capacities and evaluation metrics into a unified evaluation paradigm. We first characterize model capacities via desiderata derived from cognitive properties supporting human continual learning. The desiderata concern (1) adaptability in varying lengths of task sequence; (2) sensitivity to dynamic task variations; and (3) efficiency in memory usage and training time consumption. Then we design evaluation protocols for each desideratum to assess cognitive capacities of recent continual learning models. Experimental results show that no method we consider has satisfied all the desiderata and is still far away from realizing truly continual learning. Although some methods exhibit some degree of adaptability and efficiency, no method is able to identify task relationships when encountering dynamic task variations, or achieve a trade-off in learning similarities and differences between tasks. Inspired by these results, we discuss possible factors that influence model performance in these desiderata and provide guidance for the improvement of continual learning models.

Related papers

• Mimicking Human Intuition: Cognitive Belief-Driven Q-Learning [5.960184723807347]
  We propose Cognitive Belief-Driven Q-Learning (CBDQ), which integrates subjective belief modeling into the Q-learning framework. CBDQ enhances decision-making accuracy by endowing agents with human-like learning and reasoning capabilities. We evaluate the proposed method on discrete control benchmark tasks in various complicate environments.
  arXiv  Detail & Related papers  (2024-10-02T16:50:29Z)
• Evaluating and Improving Continual Learning in Spoken Language Understanding [58.723320551761525]
  We propose an evaluation methodology that provides a unified evaluation on stability, plasticity, and generalizability in continual learning. By employing the proposed metric, we demonstrate how introducing various knowledge distillations can improve different aspects of these three properties of the SLU model.
  arXiv  Detail & Related papers  (2024-02-16T03:30:27Z)
• Balancing Continual Learning and Fine-tuning for Human Activity Recognition [21.361301806478643]
  Wearable-based Human Activity Recognition (HAR) is a key task in human-centric machine learning. This work explores the adoption and adaptation of CaSSLe, a continual self-supervised learning model. We also investigated the importance of different loss terms and explored the trade-off between knowledge retention and learning from new tasks.
  arXiv  Detail & Related papers  (2024-01-04T13:11:43Z)
• A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems [128.63953314853327]
  "Lifelong Learning" systems are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. We show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems.
  arXiv  Detail & Related papers  (2023-01-18T21:58:54Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• Causal Imitation Learning with Unobserved Confounders [82.22545916247269]
  We study imitation learning when sensory inputs of the learner and the expert differ. We show that imitation could still be feasible by exploiting quantitative knowledge of the expert trajectories.
  arXiv  Detail & Related papers  (2022-08-12T13:29:53Z)
• Dynamic Diagnosis of the Progress and Shortcomings of Student Learning using Machine Learning based on Cognitive, Social, and Emotional Features [0.06999740786886534]
  Student diversity can be challenging as it adds variability in the way in which students learn and progress over time. A single teaching approach is likely to be ineffective and result in students not meeting their potential. This paper discusses a novel methodology based on data analytics and Machine Learning to measure and causally diagnose the progress and shortcomings of student learning.
  arXiv  Detail & Related papers  (2022-04-13T21:14:58Z)
• Behavior Priors for Efficient Reinforcement Learning [97.81587970962232]
  We consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors. We discuss how such latent variable formulations connect to related work on hierarchical reinforcement learning (HRL) and mutual information and curiosity based objectives. We demonstrate the effectiveness of our framework by applying it to a range of simulated continuous control domains.
  arXiv  Detail & Related papers  (2020-10-27T13:17:18Z)
• Understanding the Role of Training Regimes in Continual Learning [51.32945003239048]
  Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. We study the effect of dropout, learning rate decay, and batch size, on forming training regimes that widen the tasks' local minima.
  arXiv  Detail & Related papers  (2020-06-12T06:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.