This paper presents DCentNet, a novel decentralized multistage signal classification approach for biomedical data obtained from Internet of Things (IoT) wearable sensors, utilizing early exit point (EEP) to improve both energy e fficiency and processing speed. Traditionally, IoT sensor data is processed in a centralized manner on a single node, Cloud-native or Edge-native, which comes with several restrictions, such as significant energy consumption on the edge sensor and greater latency. To address these limitations, we propose DCentNet, a decentralized method based on Convolutional Neural Network (CNN) classifiers, where a single CNN model is partitioned into several sub-networks using one or more EEPs. Our method introduces encoder-decoder pairs at EEPs, which serve to compress large feature maps before transferring them to the next sub-network, drastically reducing wireless data transmission and power consumption. When the input can be confidently classified at an EEP, the processing can terminate early without traversing the entire network. To minimize sensor energy consumption and overall complexity, the initial sub-networks can be set up in the fog or on the edge. We also explore di fferent EEP locations and demonstrate that the choice of EEP can be altered to achieve a trade-o ff between performance and complexity by employing a genetic algorithm approach. DCentNet addresses the limitations of centralized processing in IoT wearable sensor data analysis, o ff ering improved e fficiency and performance. The experimental results of electrocardiogram (ECG) classification validate the success of our proposed method. With one EEP, the system saves 94.54% of wireless data transmission and a corresponding 21% decrease in complexity, while the classification accuracy and sensitivity remain almost una ffected and stay at their original levels. When employing two EEPs, the system demonstrates a sensitivity of 98.36% and an accuracy of 97.74%, concurrently leading to a 91.86% reduction in wireless data transmission and a reduction in complexity by 22%. DCentNet is implemented on an ARM Cortex-M4 based microcontroller unit (MCU).

The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy consumption. Sparse Mixture-of-Experts (SMoE) architectures have emerged as a solution, activating only a subset of parameters per token, thereby achieving faster inference while maintaining performance. However, SMoE models still face limitations in broader deployment due to their large parameter counts and significant GPU memory requirements. In this work, we introduce a gradient-free evolutionary strategy named EEP (Efficient Expert P}runing) to enhance the pruning of experts in SMoE models. EEP relies solely on model inference (i.e., no gradient computation) and achieves greater sparsity while maintaining or even improving performance on downstream tasks. EEP can be used to reduce both the total number of experts (thus saving GPU memory) and the number of active experts (thus accelerating inference). For example, we demonstrate that pruning up to 75% of experts in Mixtral $8\times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss. Remarkably, we observe improved performance on certain tasks, such as a significant increase in accuracy on the SQuAD dataset (from 53.4% to 75.4%), when pruning half of the experts. With these results, EEP not only lowers the barrier to deploying SMoE models,but also challenges the conventional understanding of model pruning by showing that fewer experts can lead to better task-specific performance without any fine-tuning. Code is available at https://github.com/imagination-research/EEP.

This study advances Early Event Prediction (EEP) in healthcare through Dynamic Survival Analysis (DSA), offering a novel approach by integrating risk localization into alarm policies to enhance clinical event metrics. By adapting and evaluating DSA models against traditional EEP benchmarks, our research demonstrates their ability to match EEP models on a time-step level and significantly improve event-level metrics through a new alarm prioritization scheme (up to 11% AuPRC difference). This approach represents a significant step forward in predictive healthcare, providing a more nuanced and actionable framework for early event prediction and management.

Modular and hierarchical community structures are pervasive in real-world complex systems. A great deal of effort has gone into trying to detect and study these structures. Important theoretical advances in the detection of modular have included identifying fundamental limits of detectability by formally defining community structure using probabilistic generative models. Detecting hierarchical community structure introduces additional challenges alongside those inherited from community detection. Here we present a theoretical study on hierarchical community structure in networks, which has thus far not received the same rigorous attention. We address the following questions: 1) How should we define a hierarchy of communities? 2) How do we determine if there is sufficient evidence of a hierarchical structure in a network? and 3) How can we detect hierarchical structure efficiently? We approach these questions by introducing a definition of hierarchy based on the concept of stochastic externally equitable partitions and their relation to probabilistic models, such as the popular stochastic block model. We enumerate the challenges involved in detecting hierarchies and, by studying the spectral properties of hierarchical structure, present an efficient and principled method for detecting them.

To address We present a novel negotiation protocol to facilitate this challenge, Alam et al. [2013b] presented a protocol to energy exchange between off-grid homes that facilitate negotiation over energy exchange. Their protocol are equipped with renewable energy generation and restricts the type and number of offers such that negotiation electricity storage. Our protocol imposes restrictions leads to a subgame perfect Nash equilibrium (SPNE). However, over negotiation such that it reduces the complex their protocol only allows point-to-point communication interdependent multi-issue negotiation to one and relies on a fully connected network topology (i.e., where agents have a strategy profile in subgame each home is connected to all other homes in the community) perfect Nash equilibrium. We show that our protocol whereby the number of connections and messages exchanged; is concurrent, scalable and; under certain conditions; grow quadratically with the number of connected leads to Pareto-optimal outcomes.

We present a novel negotiation protocol to facilitate energy exchange between off-grid homes that are equipped with renewable energy generation and electricity storage. Our protocol imposes restrictions over negotiation such that it reduces the complex interdependent multi-issue negotiation to one where agents have a strategy profile in subgame perfect Nash equilibrium. We show that our negotiation protocol is tractable, concurrent, scalable and leads to Pareto-optimal outcomes in a decentralised manner. We empirically evaluate our protocol and show that, in this instance, a society of agents can (i) improve the overall utilities by 14% and (ii) reduce their overall use of the batteries by 37%.