Implicit Assumptions About Tasks in Continual Learning
cs.LG, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: Accepted to the Workshop on Continual Learning in the Era of Foundation Models and Embodied Agents at NeurIPS 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once.
Terminology
Abstract
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks and presenting them sequentially. Explanations of the resulting measurements take into account factors such as the similarity between segments, the rate at which the data changes and the order of presentation. Each of these factors can be defined in terms of the underlying data, the partition imposed on it, or the learner that encounters it. These levels do not necessarily coincide, and it is usually left implicit which level a reported quantity refers to. We separate these and identify which properties acquire a value at each level. In controlled teacher--student experiments, we demonstrate that partitioning the same underlying trajectory at different levels of granularity, changing the order of presentation, and varying the similarity structure of the underlying data all result in different measured outcomes. We review representative benchmarks to determine which of these properties are stated. Where the underlying data cannot be inspected, as in foundation models built on undisclosed pre-training corpora, its properties are inherited by the model's initial state, and the training applied on top of it can be described.
Sources
- Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
- The Future of Continual Learning in the Era of Foundation Models: Three Key Directions
- The Effect of Task Ordering in Continual Learning
- Position: Modular Memory is the Key to Continual Learning Agents
- Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- The Importance of Being Lazy: Scaling Limits of Continual Learning
- Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
- Simple and Scalable Strategies to Continually Pre-train Large Language Models
- Elastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation
- Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation
- Optimal Task Order for Continual Learning of Multiple Tasks
- Continual Learning Should Move Beyond Incremental Classification
- Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
- The 2025 Foundation Model Transparency Index
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis