Y. Jin

MKD: Mixup-Based Knowledge Distillation for Mandarin End-to-End Speech Recognition

2022 · Algorithms

Large-scale automatic speech recognition model has achieved impressive performance. However, huge computational resources and massive amount of data are required to train an ASR model. Knowledge distillation is a prevalent model compression method which transfers …

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation …

HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

2025 · arXiv (Cornell University)

Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant …