Daily Dose of Paper : Sparse Continual Learning on the Edge

 

Sparse Continual Learning on the Edge

NeurIPS 2022 paper.

TLDR

sparclalgo

  • Task-aware dynamic mask TDM : Based on $CWI$, keep only important weights for both current & past tasks.
    ++ consider task transition
  • Dynamic Gradient Masking DGM : Based on $CGI$, select important weights to update,
    only a subset of sparse weight updated to leverage gradient sparcity.

Quick Look

Research Topic

  • Category (General): Continual Learning
  • Category (Specific): Continual Learning, Lottery Ticket Theorem

Paper Summary (What)

  1. Use two types of masks, $M_w$ and $M_g$ based on slightly different importance metrics.
  2. Dynamic Data Removal DDR : remove ‘easy’ examples regarding to loss,
    keep more informative examples in the replay buffer.
  3. $CWI$ for $M_w$
    \(CWI = \text{L1 norm of }W + \text{gradient w.r.t task data } D_t + \text{gradient w.r.t rehearsal buffer} R\)
  4. $CGI$ for $M_g$
    \(CGI = \text{grad w.r.t task data }D_t + \text{gradient w.r.t rehearsal buffer} R\)
  5. Update mask by retaining weights with high $CWI$ or $CGI$ value.

Notable References

Thoughts

Isn’t $CWI$ and $CGI$ are redundant metrics, i.e. not orthogonal enough?
Applying different masks for forward/backward phase is notable.
Somewhat very similar with my idea, but somewhat different from what I thought.

Footnote

아래와 같은 양식을 활용한다.

# 
## Quick Look
- **Authors & Affiliation**: [Authors][Affiliations]
- **Link**: [Paper link]
- **Comments**: [e.g. Published at X / arXiv paper / in review.]
- **TLDR**: [One or at most two line summary]
- **Relevance**: [Score between 1 and 5, stating how relevant this paper is to your work. Usually filled in at the end.]
# Research Topic
- **Category** (General):
- **Category** (Specific):
# Paper Summary (What)
[Summary of the paper - a few sentences with bullet points. What did they do?]

wbjeon2k

Pursuite for Progress.

This work is licensed under a Attribution-NonCommercial 4.0 International license. Attribution-NonCommercial 4.0 International