RECORD
SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning
Neural and Evolutionary Computing · Submitted 8 Jun 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective replay. It further employs synaptic consolidation by tracking the importance of parameters during the training trajectory and anchoring them to the consolidated parameters in the semantic memory. To the best of our knowledge, our study is the first to employ dual memory experience replay in conjunction with synaptic consolidation that is suitable for general CL whereby the network does not utilize task boundaries or task labels during training or inference. Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. | background 1.00 | 0.04 | 0.04 | asserted 0.78 |
| s2 | Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). | contribution 0.94 | 0.77 | 0.28 | asserted 0.90 |
| s3 | Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective replay. | method 0.99 | 0.83 | 0.08 | asserted 1.00 |
| s4 | It further employs synaptic consolidation by tracking the importance of parameters during the training trajectory and anchoring them to the consolidated parameters in the semantic memory. | method 1.00 | 0.91 | 0.06 | asserted 1.00 |
| s5 | To the best of our knowledge, our study is the first to employ dual memory experience replay in conjunction with synaptic consolidation that is suitable for general CL whereby the network does not utilize task boundaries or task labels during training or inference. | contribution 0.95 | 0.89 | 0.19 | asserted 0.98 |
| s6 | Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs. | result 0.91 | 0.95 | 0.80 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective replay. It further employs synaptic consolidation by tracking the importance of parameters during the training trajectory and anchoring them to the consolidated parameters in the semantic memory. To the best of our knowledge, our study is the first to employ dual memory experience replay in conjunction with synaptic consolidation that is suitable for general CL whereby the network does not utilize task boundaries or task labels during training or inference. Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 5 sentences without a confident label
Cites as background 3 papers
-
Experience Replay (ER) [ref] typically involves storing a subset of samples from previous tasks and mixing them with data from the new task to update the model parameters with an approximate joint distribution and has proven to be effective in reducing catastrophic forgetting under challenging settings [ref] .
Towards Robust Evaluations of Continual Learning · Background · 0.80
-
Experience Replay (ER) [ref] typically involves storing a subset of samples from previous tasks and mixing them with data from the new task to update the model parameters with an approximate joint distribution and has proven to be effective in reducing catastrophic forgetting under challenging settings [ref] .
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference · Background · 0.80
-
CLS theory has further inspired dual memory learning systems [ref] .
DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning · Background · 0.92
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.