Semantic-based Distributed Learning for Diverse and Discriminative Representations
For distributed learning systems, this work addresses the problem of nonstructural embeddings that cause collapsed variability within classes, offering a theoretically grounded solution for both i.i.d. and non-i.i.d. data.
The paper proposes a distributed learning framework that ensures diverse and discriminative representations by reformulating the global optimization function with constraints on representation variance, achieving improved structural embeddings in large-scale distributed scenarios. Experiments on MNIST, CIFAR-10, and CIFAR-100 confirm effectiveness.
In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific approaches often result in nonstructural embeddings, leading to collapsed variability among data samples within the same class, particularly in classification tasks. To address this issue and fully leverage the intrinsic structure of data for downstream applications, we propose a novel distributed learning framework that ensures both diverse and discriminative representations. For independent and identically distributed (i.i.d.) data, we reformulate and decouple the global optimization function by introducing constraints on representation variance. The update rules are then derived and simplified using a primal-dual approach. For non-i.i.d. data distributions, we tackle the problem by clustering and virtually replicating nodes, allowing model updates within each cluster using block coordinate descent. In both cases, the resulting optimal solutions are theoretically proven to maintain discriminative and diverse properties, with a guaranteed convergence for i.i.d. conditions. Additionally, semantic information from representations is shared among nodes, reducing the need for common neural network architectures. Finally, extensive simulations on MNIST, CIFAR-10 and CIFAR-100 confirm the effectiveness of the proposed algorithms in capturing global structural representations.