Collaborative Learning via Prediction Consensus

2023

Conference Paper

sf

We consider a collaborative learning setting where the goal of each agent is to improve their own model by leveraging the expertise of collaborators, in addition to their own training data. To facilitate the exchange of expertise among agents, we propose a distillation-based method leveraging shared unlabeled auxiliary data, which is pseudo-labeled by the collective. Central to our method is a trust weighting scheme that serves to adaptively weigh the influence of each collaborator on the pseudo-labels until a consensus on how to label the auxiliary data is reached. We demonstrate empirically that our collaboration scheme is able to significantly boost the performance of individual models in the target domain from which the auxiliary data is sampled. By design, our method adeptly accommodates heterogeneity in model architectures and substantially reduces communication overhead compared to typical collaborative learning methods. At the same time, it can probably mitigate the negative impact of bad models on the collective.

@inproceedings{NEURIPS2023_065e259a,
  title = {Collaborative Learning via Prediction Consensus},
  author = {Fan, Dongyang and Mendler-D\"{u}nner, Celestine and Jaggi, Martin},
  booktitle = {Advances in Neural Information Processing Systems 36 (NeurIPS 2023)},
  publisher = {Curran Associates, Inc.},
  month = dec,
  year = {2023},
  doi = {},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/file/065e259a1d2d955e63b99aac6a3a3081-Paper-Conference.pdf},
  month_numeric = {12}
}