Catastrophic Forgetting in the Context of Model Updates
A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline, you can train a new model from scratch (randomly initialized weights) on all existing data. Instead, you can take an existing model and fine-tune (continue to train) it on new data. The former is costly and slow. The latter is cheap and fast, but catastrophic forgetting generally causes the new model to 'forget' how to classify older data well. There are a plethora of complicated techniques to keep models from forgetting their past learnings. Arguably the most basic is to mix in a small amount of past data into the new data during fine-tuning: also known as 'data rehearsal'. In this paper, we compare various methods of limiting catastrophic forgetting and conclude that if you can maintain access to a portion of your past data (or tasks), data rehearsal is ideal in terms of overall accuracy across all time periods, and performs even better when combined with methods like Elastic Weight Consolidation (EWC). Especially when the amount of past data (past 'tasks') is large compared to new data, the cost of updating an existing model is far cheaper and faster than training a new model from scratch.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSimilar Papers 제목 키워드 기반
Learning to Continually Learn
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default te…
Continual LearningLifelong learningMeta-LearningExplaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
Catastrophic forgetting remains a central challenge in continual learning, where models are required to integrate new knowledge over time without losing what they have previously learned. In prior work, we introduced Cob…
Continual LearningOn Learning the Geodesic Path for Incremental Learning
Neural networks notoriously suffer from the problem of catastrophic forgetting, the phenomenon of forgetting the past knowledge when acquiring new knowledge. Overcoming catastrophic forgetting is of significant importanc…
Incremental LearningKnowledge DistillationElastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation
Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation …
Continual LearningKnowledge GraphsLink PredictionMitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
Expanding the linguistic diversity of instruct large language models (LLMs) is crucial for global accessibility but is often hindered by the reliance on costly specialized target language labeled data and catastrophic fo…