Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequences
This addresses the challenge of handling heterogeneous data in scientific fields like astronomy, though it is incremental as it builds on existing self-supervised and diffusion methods.
The paper tackled the problem of representation learning for long, irregular, and multimodal sequences in scientific domains, introducing the Diffusion Autoencoder with Perceivers (daep) which achieved lower reconstruction errors, more discriminative latent spaces, and better preservation of fine-scale structure compared to VAE and maep baselines across astronomical datasets.
Self-supervised learning has become a central strategy for representation learning, but the majority of architectures used for encoding data have only been validated on regularly-sampled inputs such as images, audios. and videos. In many scientific domains, data instead arrive as long, irregular, and multimodal sequences. To extract semantic information from these data, we introduce the Diffusion Autoencoder with Perceivers (daep). daep tokenizes heterogeneous measurements, compresses them with a Perceiver encoder, and reconstructs them with a Perceiver-IO diffusion decoder, enabling scalable learning in diverse data settings. To benchmark the daep architecture, we adapt the masked autoencoder to a Perceiver encoder/decoder design, and establish a strong baseline (maep) in the same architectural family as daep. Across diverse spectroscopic and photometric astronomical datasets, daep achieves lower reconstruction errors, produces more discriminative latent spaces, and better preserves fine-scale structure than both VAE and maep baselines. These results establish daep as an effective framework for scientific domains where data arrives as irregular, heterogeneous sequences.