Robust Group Subspace Recovery: A New Approach for Multi-Modality Data Fusion
This work addresses data fusion for unlabeled sensors in applications like audio and magnetic analysis, but it is incremental as it builds on an existing algorithm.
The authors tackled the problem of multi-modality data fusion by extending the Robust Subspace Recovery algorithm to handle different data modalities individually, proposing Robust Group Subspace Recovery (RoGSuRe), which showed competitive performance with state-of-the-art subspace clustering methods on audio and magnetic data.
Robust Subspace Recovery (RoSuRe) algorithm was recently introduced as a principled and numerically efficient algorithm that unfolds underlying Unions of Subspaces (UoS) structure, present in the data. The union of Subspaces (UoS) is capable of identifying more complex trends in data sets than simple linear models. We build on and extend RoSuRe to prospect the structure of different data modalities individually. We propose a novel multi-modal data fusion approach based on group sparsity which we refer to as Robust Group Subspace Recovery (RoGSuRe). Relying on a bi-sparsity pursuit paradigm and non-smooth optimization techniques, the introduced framework learns a new joint representation of the time series from different data modalities, respecting an underlying UoS model. We subsequently integrate the obtained structures to form a unified subspace structure. The proposed approach exploits the structural dependencies between the different modalities data to cluster the associated target objects. The resulting fusion of the unlabeled sensors' data from experiments on audio and magnetic data has shown that our method is competitive with other state of the art subspace clustering methods. The resulting UoS structure is employed to classify newly observed data points, highlighting the abstraction capacity of the proposed method.