We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy.

Neural Information Processing Systems http://nips.cc/

These schemes are often heuristic and fixed over the course of training.

Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces a major bottleneck due to high communication overhead from frequent model updates between devices and the server, limiting deployment in resource-constrained wireless networks. In this paper, we propose a three-fold strategy. Firstly, an Adaptive Feature-Elimination Strategy to drop less important features while retaining high-value ones; secondly, Adaptive Gradient Innovation and Error Sensitivity-Based Quantization, which dynamically adjusts the quantization level for innovative gradient compression; and thirdly, Communication Frequency Optimization to enhance communication efficiency. We evaluated our proposed model's performance through extensive experiments, assessing accuracy, loss, and convergence compared to baseline techniques. The results show that our model achieves high communication efficiency in the framework while maintaining accuracy.

Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative machine learning while preserving data privacy, making it particularly suitable for Internet of Things (IoT) environments. However, resource-constrained IoT devices face significant challenges due to limited energy,unreliable communication channels, and the impracticality of assuming infinite blocklength transmission. This paper proposes a federated learning framework for IoT networks that integrates finite blocklength transmission, model quantization, and an error-aware aggregation mechanism to enhance energy efficiency and communication reliability. The framework also optimizes uplink transmission power to balance energy savings and model performance. Simulation results demonstrate that the proposed approach significantly reduces energy consumption by up to 75\% compared to a standard FL model, while maintaining robust model accuracy, making it a viable solution for FL in real-world IoT scenarios with constrained resources. This work paves the way for efficient and reliable FL implementations in practical IoT deployments. Index Terms: Federated learning, IoT, finite blocklength, quantization, energy efficiency.

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of quantized models from the network output perspective by designing better KD loss functions or optimizing QAT's forward and backward propagation. However, limited attention has been given to understanding the impact of input transformations, such as data augmentation (DA). The relationship between quantization-aware KD and DA remains unexplored. In this paper, we address the question: how to select a good DA in quantization-aware KD, especially for the models with low precisions? We propose a novel metric which evaluates DAs according to their capacity to maximize the Contextual Mutual Information--the information not directly related to an image's label--while also ensuring the predictions for each class are close to the ground truth labels on average. The proposed method automatically ranks and selects DAs, requiring minimal training overhead, and it is compatible with any KD or QAT algorithm. Extensive evaluations demonstrate that selecting DA strategies using our metric significantly improves state-of-the-art QAT and KD works across various model architectures and datasets.