PairAlign learns compact variable-length token sequences for audio via self-alignment on paired content-preserving views, achieving 55% fewer archive tokens than VQ while preserving edit-distance retrieval at 12.71 tokens/s.
Self-supervised learning from a multi-view perspective
5 Pith papers cite this work, alongside 12 external citations. Polarity classification is still indexing.
5
Pith papers citing it
12
external citations · external index
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 5roles
background 1polarities
background 1representative citing papers
The paper proves statistical consistency of contrastive loss to optimal ranking via an AUC criterion and derives generalization bounds O(1/m + 1/sqrt(n)) for supervised and O(1/sqrt(m) + 1/sqrt(n)) for self-supervised CRL that explain benefits of large negative sets.
DiGGR introduces a self-supervised graph representation learning framework that disentangles latent factors to guide mask modeling and improve representation quality on graph tasks.
Derives novel generalization error bounds for multimodal pairwise metric learning showing that fine-grained modality features reduce hypothesis space complexity via enhanced complementarity.
citing papers explorer
-
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
PairAlign learns compact variable-length token sequences for audio via self-alignment on paired content-preserving views, achieving 55% fewer archive tokens than VQ while preserving edit-distance retrieval at 12.71 tokens/s.
-
Statistical Consistency and Generalization of Contrastive Representation Learning
The paper proves statistical consistency of contrastive loss to optimal ranking via an AUC criterion and derives generalization bounds O(1/m + 1/sqrt(n)) for supervised and O(1/sqrt(m) + 1/sqrt(n)) for self-supervised CRL that explain benefits of large negative sets.
-
Disentangled Generative Graph Representation Learning
DiGGR introduces a self-supervised graph representation learning framework that disentangles latent factors to guide mask modeling and improve representation quality on graph tasks.
-
Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning
Derives novel generalization error bounds for multimodal pairwise metric learning showing that fine-grained modality features reduce hypothesis space complexity via enhanced complementarity.
- SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data