Distributed Machine Learning (DML) systems are utilized to enhance the speed of model training in data centers (DCs) and edge nodes. The Parameter Server (PS) communication architecture is commonly employed, but it faces severe long-tail latency caused by many-to-one "incast" traffic patterns, negatively impacting training throughput. To address this challenge, we design the \textbf{L}oss-tolerant \textbf{T}ransmission \textbf{P}rotocol (LTP), which permits partial loss of gradients during synchronization to avoid unneeded retransmission and contributes to faster synchronization per iteration. LTP implements loss-tolerant transmission through \textit{out-of-order transmission} and \textit{out-of-order Acknowledges (ACKs)}. LTP employs \textit{Early Close} to adjust the loss-tolerant threshold based on network conditions and \textit{Bubble Filling} for data correction to maintain training accuracy. LTP is implemented by C++ and integrated into PyTorch. Evaluations on a testbed of 8 worker nodes and one PS node demonstrate that LTP can significantly improve DML training task throughput by up to 30x compared to traditional TCP congestion controls, with no sacrifice to final accuracy.

We tackle the problem of joint frequency and power allocation while emphasizing the generalization capability of a deep reinforcement learning model. Most of the existing methods solve reinforcement learning-based wireless problems for a specific pre-determined wireless network scenario. The performance of a trained agent tends to be very specific to the network and deteriorates when used in a different network operating scenario (e.g., different in size, neighborhood, and mobility, among others). We demonstrate our approach to enhance training to enable a higher generalization capability during inference of the deployed model in a distributed multi-agent setting in a hostile jamming environment. With all these, we show the improved training and inference performance of the proposed methods when tested on previously unseen simulated wireless networks of different sizes and architectures. More importantly, to prove practical impact, the end-to-end solution was implemented on the embedded software-defined radio and validated using over-the-air evaluation.

Google has released an official video of its first ever foldable smartphone - the Pixel Fold. A video shows the sleek, silver device which opens up like a book with a vertical hinge, and has a camera array on the back that is similar to other Pixel devices. The tech giant has yet to release any technical details or price, as the full announcement will come on May 10 during its developer conference, Google I/O. This comes just a week after footage was leaked on Twitter of an alleged Pixel Fold prototype, which looks very similar to the one in the official video. The smartphone will see Google join Samsung, Huawei and many more of its rivals in offering a foldable device.

In recent years, there has been an increasing interest in the use of graph neural networks (GNNs) for analyzing dynamic graphs, which are graphs that evolve over time. However, there is still a lack of understanding of how different temporal graph neural network (TGNs) configurations can impact the accuracy of predictions on dynamic graphs. Moreover, the hunt for benchmark datasets for these TGNs models is still ongoing. Up until recently, Pytorch Geometric Temporal came up with a few benchmark datasets but most of these datasets have not been analyzed with different TGN models to establish the state-of-the-art. Therefore, this project aims to address this gap in the literature by performing a qualitative analysis of spatial-temporal dependence structure learning on dynamic graphs, as well as a comparative study of the effectiveness of selected TGNs on node and edge prediction tasks. Additionally, an extensive ablation study will be conducted on different variants of the best-performing TGN to identify the key factors contributing to its performance. By achieving these objectives, this project will provide valuable insights into the design and optimization of TGNs for dynamic graph analysis, with potential applications in areas such as disease spread prediction, social network analysis, traffic prediction, and more. Moreover, an attempt is made to convert snapshot-based data to the event-based dataset and make it compatible with the SOTA model namely TGN to perform node regression task.

A theory of neural networks (NNs) built upon collective variables would provide scientists with the tools to better understand the learning process at every stage. In this work, we introduce two such variables, the entropy and the trace of the empirical neural tangent kernel (NTK) built on the training data passed to the model. We empirically analyze the NN performance in the context of these variables and find that there exists correlation between the starting entropy, the trace of the NTK, and the generalization of the model computed after training is complete. This framework is then applied to the problem of optimal data selection for the training of NNs. To this end, random network distillation (RND) is used as a means of selecting training data which is then compared with random selection of data. It is shown that not only does RND select data-sets capable of outperforming random selection, but that the collective variables associated with the RND data-sets are larger than those of the randomly selected sets. The results of this investigation provide a stable ground from which the selection of data for NN training can be driven by this phenomenological framework.

Energy Efficiency of a wireless sensor network (WSN) relies on its main characteristics, including hop-number, user's location, allocated power, and relay. Identifying nodes, which have more impact on these characteristics, is, however, subject to a substantial computational overhead and energy consumption. In this paper, we proposed an active learning approach to address the computational overhead of identifying critical nodes in a WSN. The proposed approach can overcome biasing in identifying non-critical nodes and needs much less effort in fine-tuning to adapt to the dynamic nature of WSN. This method benefits from the cooperation of clustering and classification modules to iteratively decrease the required number of data in a typical supervised learning scenario and to increase the accuracy in the presence of uninformative examples, i.e., non-critical nodes. Experiments show that the proposed method has more flexibility, compared to the state-of-the-art, to be employed in large scale WSN environments, the fifth-generation mobile networks (5G), and massively distributed IoT (i.e., sensor networks), where it can prolong the network lifetime.

In high performance systems it is sometimes hard to build very large graphs that are efficient both with respect to memory and compute. This paper proposes a data structure called Markov-chain-priority-queue (MCPrioQ), which is a lock-free sparse markov-chain that enables online and continuous learning with time-complexity of $O(1)$ for updates and $O(CDF^{-1}(t))$ inference. MCPrioQ is especially suitable for recommender-systems for lookups of $n$-items in descending probability order. The concurrent updates are achieved using hash-tables and atomic instructions and the lookups are achieved through a novel priority-queue which allows for approximately correct results even during concurrent updates. The approximatly correct and lock-free property is maintained by a read-copy-update scheme, but where the semantics have been slightly updated to allow for swap of elements rather than the traditional pop-insert scheme.

Poverty is a multifaceted phenomenon linked to the lack of capabilities of households to earn a sustainable livelihood, increasingly being assessed using multidimensional indicators. Its spatial pattern depends on social, economic, political, and regional variables. Artificial intelligence has shown immense scope in analyzing the complexities and nuances of poverty. The proposed project aims to examine the poverty situation of rural India for the period of 1990-2022 based on the quality of life and livelihood indicators. The districts will be classified into `advanced', `catching up', `falling behind', and `lagged' regions. The project proposes to integrate multiple data sources, including conventional national-level large sample household surveys, census surveys, and proxy variables like daytime, and nighttime data from satellite images, and communication networks, to name a few, to provide a comprehensive view of poverty at the district level. The project also intends to examine causation and longitudinal analysis to examine the reasons for poverty. Poverty and inequality could be widening in developing countries due to demographic and growth-agglomerating policies. Therefore, targeting the lagging regions and the vulnerable population is essential to eradicate poverty and improve the quality of life to achieve the goal of `zero poverty'. Thus, the study also focuses on the districts with a higher share of the marginal section of the population compared to the national average to trace the performance of development indicators and their association with poverty in these regions.

IoT has a significant role in the smart campus. This paper presents a detailed description of the Smart Campus dataset based on LoRaWAN. LoRaWAN is an emerging technology that enables serving hundreds of IoT devices. First, we describe the LoRa network that connects the devices to the server. Afterward, we analyze the missing transmissions and propose a k-nearest neighbor solution to handle the missing values. Then, we predict future readings using a long short-term memory (LSTM). Finally, as one example application, we build a deep neural network to predict the number of people inside a room based on the selected sensor's readings. Our results show that our model achieves an accuracy of $95 \: \%$ in predicting the number of people. Moreover, the dataset is openly available and described in detail, which is opportunity for exploration of other features and applications.

In this paper, we present a novel approach for the design of leaky-wave holographic antennas that generates OAM-carrying electromagnetic waves by combining Flat Optics (FO) and machine learning (ML) techniques. To improve the performance of our system, we use a machine learning technique to discover a mathematical function that can effectively control the entire radiation pattern, i.e., decrease the side lobe level (SLL) while simultaneously increasing the central null depth of the radiation pattern. Precise tuning of the parameters of the impedance equation based on holographic theory is necessary to achieve optimal results in a variety of scenarios. In this research, we applied machine learning to determine the approximate values of the parameters. We can determine the optimal values for each parameter, resulting in the desired radiation pattern, using a total of 77,000 generated datasets. Furthermore, the use of ML not only saves time, but also yields more precise and accurate results than manual parameter tuning and conventional optimization methods.