Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clientsby Shaoyuan Chen, Linlin You,…
Understanding the Gains from Repeated Self-Distillationby Divyansh Pareek, Simon S. Du, Sewoong OhFirst submitted to…
Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillationby Marco Mistretta, Alberto Baldrati, Marco…
Advancing Compressed Video Action Recognition through Progressive Knowledge Distillationby Efstathia Soufleri, Deepak Ravikumar, Kaushik RoyFirst…
MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Modelsby Ying Zhang, Ziheng Yang, Shufan JiFirst submitted…
Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterizationby Hongjun Choi, Jayaraman J. Thiagarajan,…
FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detectionby Rui Cao, Shijie Xue,…
Instance Temperature Knowledge Distillationby Zhengbo Zhang, Yuxi Zhou, Jia Gong, Jun Liu, Zhigang TuFirst submitted…
MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classificationby Tianjun Yao, Jiaqi Sun, Defu…
InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillationby Jinbin Huang, Wenbin He, Liang Gou, Liu…