Portrait de Congshu Zou n'est pas disponible

Congshu Zou

Maîtrise recherche - Concordia
Superviseur⋅e principal⋅e
Eugene Belilovsky
Sujets de recherche
Apprentissage profond
GitHub

Publications

Understanding Permutation Based Model Merging with Feature Visualizations
Congshu Zou
Geraldin Nanfack
Stefan Horoi
Eugene Belilovsky
Linear mode connectivity (LMC) has become a topic of great interest in recent years. It has been empirically demonstrated that popular deep … (voir plus)learning models trained from different initializations exhibit linear model connectivity up to permutation. Based on this, several approaches for finding a permutation of the model's features or weights have been proposed leading to several popular methods for model merging. These methods enable the simple averaging of two models to create a new high-performance model. However, besides accuracy, the properties of these models and their relationships to the representations of the models they derive from are poorly understood. In this work, we study the inner mechanisms behind LMC in model merging through the lens of classic feature visualization methods. Focusing on convolutional neural networks (CNNs) we make several observations that shed light on the underlying mechanisms of model merging by permute and average.
2024-10-10
NeurIPS.cc/2024/Workshop/UniReps (accepté)
openreview.net
openreview.net
Understanding Permutation Based Model Merging with Feature Visualizations
Congshu Zou
Geraldin Nanfack
Stefan Horoi
Eugene Belilovsky
Linear mode connectivity (LMC) has become a topic of great interest in recent years. It has been empirically demonstrated that popular deep … (voir plus)learning models trained from different initializations exhibit linear model connectivity up to permutation. Based on this, several approaches for finding a permutation of the model's features or weights have been proposed leading to several popular methods for model merging. These methods enable the simple averaging of two models to create a new high-performance model. However, besides accuracy, the properties of these models and their relationships to the representations of the models they derive from are poorly understood. In this work, we study the inner mechanisms behind LMC in model merging through the lens of classic feature visualization methods. Focusing on convolutional neural networks (CNNs) we make several observations that shed light on the underlying mechanisms of model merging by permute and average.
2024-10-10
NeurIPS.cc/2024/Workshop/UniReps (accepté)
openreview.net
openreview.net