DG algorithms face fundamental challenges in FL setups due to the lack of samples/domains in each client's local dataset.

It's important to note that

However, existing contrastive learning methods primarily focus on one single data level, which fails to fully exploit the intricate nature of medical time series.

Surprisingly, we find that most of the studied methods yield similar results.

Specifically, we pose and answer the following questions: Q1. How do the learned spatial and temporal representations vary based on different VSSL pretrain-ing methodologies? How robust are these representations to different distribution shifts?

Diffusion models have recently shown remarkable success in high-quality image generation. Sometimes, however, a pre-trained diffusion model exhibits partial misalignment in the sense that the model can generate good images, but it sometimes outputs undesirable images. If so, we simply need to prevent the generation of the bad images, and we call this task censoring. In this work, we present censored generation with a pre-trained diffusion model using a reward model trained on minimal human feedback. We show that censoring can be accomplished with extreme human feedback efficiency and that labels generated with a mere few minutes of human feedback are sufficient.