Timezone: »

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning
Chang Liu · Chenfei Lou · Runzhong Wang · Alan Yuhan Xi · Li Shen · Junchi Yan

Tue Jul 19 11:25 AM -- 11:30 AM (PDT) @ Hall F

Model fusion without accessing training data in machine learning has attracted increasing interest due to the practical resource-saving and data privacy issues. During the training process, the neural weights of each model can be randomly permuted, and we have to align the channels of each layer before fusing them. Regrading the channels as nodes and weights as edges, aligning the channels to maximize weight similarity is a challenging NP-hard assignment problem. Due to its quadratic assignment nature, we formulate the model fusion problem as a graph matching task, considering the second-order similarity of model weights instead of previous work merely formulating model fusion as a linear assignment problem. For the rising problem scale and multi-model consistency issues, we propose an efficient graduated assignment-based model fusion method, dubbed GAMF, which iteratively updates the matchings in a consistency-maintaining manner. We apply GAMF to tackle the compact model ensemble task and federated learning task on MNIST, CIFAR-10, CIFAR-100, and Tiny-Imagenet. The performance shows the efficacy of our GAMF compared to state-of-the-art baselines.

Author Information

Chang Liu (Shanghai Jiao Tong University)
Chenfei Lou (Shanghai Jiao Tong University)
Runzhong Wang (Shanghai Jiao Tong University)
Alan Yuhan Xi (university of wisconsin madison)
Li Shen (JD Explore Academy)
Junchi Yan (Shanghai Jiao Tong University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors