Finetune-Informed Pretraining Boosts Downstream Performance
Authors:
- Atik FaysalAFAtik Faysal
- Mohammad RostamiMRMohammad Rostami
- Reihaneh Gh. RoshanRRReihaneh Gh. Roshan
- Nikhil MuralidharNMNikhil Muralidhar
- Huaxia WangHWHuaxia Wang
Preprint
Abstract
Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities uniformly, which can lead to under-optimized representations for the modality that actually matters. We propose Finetune-Informed Pretraining (FIP), a model-agnostic method that biases representation learning toward a designated target modality needed at fine-tuning time. FIP combines higher masking difficulty, stronger loss weighting, and increased decoder capacity for the target modality, without modifying the shared encoder or requiring additional supervision. When applied to masked modeling on constellation diagrams for wireless signals, FIP consistently improves downstream fine-tuned performance with no extra data or compute. FIP is simple to implement, architecture-compatible, and broadly applicable across multimodal masked modeling pipelines.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- An Effective Masked Transformer Model for Automatic Modulation RecognitionIEEE Transactions on Cognitive Communications and Networking, 2025
- MCLHN: Toward Automatic Modulation Classification via Masked Contrastive Learning With Hard NegativesIEEE Transactions on Wireless Communications, 2024
- 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities2024
- MM-Net: A Multi-Modal Approach Toward Automatic Modulation ClassificationIEEE Communications Letters, 2023
- GAF-MAE: A Self-Supervised Automatic Modulation Classification Method Based on Gramian Angular Field and Masked AutoencoderIEEE Transactions on Cognitive Communications and Networking, 2023