Papers › Difference-Masking: Choosing What to Mask in Continued Pretraining

Difference-Masking: Choosing What to Mask in Continued Pretraining

23 May 2023arXiv:2305.14577archive 2025-07-28

Alex Wilf, Syeda Nahida Akter, Leena Mathur, Paul Pu Liang, Sheryl Mathew, Mengrou Shou, Eric Nyberg, Louis-Philippe Morency

The self-supervised objective of masking-and-predicting has led to promising performance gains on a variety of downstream tasks. However, while most approaches randomly mask tokens, there is strong intuition that deciding what to mask can substantially improve learning outcomes. We investigate this in continued pretraining setting in which pretrained models continue to pretrain on domain-specific data before performing some downstream task. We introduce Difference-Masking, a masking strategy that automatically chooses what to mask during continued pretraining by considering what makes a task domain different from the pretraining domain. Empirically, we find that Difference-Masking outperforms baselines on continued pretraining settings across four diverse language-only and multimodal video tasks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

abwilf/difference-masking officialmentioned in paperjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Self-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections