SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time environmental supervision during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, leveraging generative models to jointly learn the optical, physical, and signal properties within each designated environment. Our work introduces the Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH), an innovative offline, fully differentiable approach that can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, outperforms the baseline by 4e^-2 radian in RT accuracy, and only fades 0.5 dB away from toplined channel gain estimation.

Long Sequence Modeling with Attention Tensorization: From Sequence to Tensor Learning

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based model is the mismatch between the limited-range modeling power of full attention and the long-range token dependency in the input sequence. In this work, we propose to scale up the attention receptive field by tensorizing long input sequences into compact tensor representations followed by attention on each transformed dimension. The resulting Tensorized Attention can be adopted as efficient transformer backbones to extend input context length with improved memory and time efficiency. We show that the proposed attention tensorization encodes token dependencies as a multi-hop attention process, and is equivalent to Kronecker decomposition of full attention. Extensive experiments show that tensorized attention can be used to adapt pretrained LLMs with improved efficiency. Notably, Llama-8B with tensorization is trained under 32,768 context length and can steadily extrapolate to 128k length during inference with $11\times$ speedup, compared to full attention with FlashAttention-2.

SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language understanding, information retrieval and search, translation, chatbots, virtual assistance, and many more. However, it is well known that LLMs are massive in terms of the number of parameters. Additionally, the self-attention mechanism in the underlying architecture of LLMs, Transformers, has quadratic complexity in terms of both computation and memory with respect to the input sequence length. For these reasons, LLM inference is resource-intensive, and thus, the throughput of LLM inference is limited, especially for the longer sequences. In this report, we design a collaborative inference architecture between a server and its clients to alleviate the throughput limit. In this design, we consider the available resources on both sides, i.e., the computation and communication costs. We develop a dynamic programming-based algorithm to optimally allocate computation between the server and the client device to increase the server throughput, while not violating the service level agreement (SLA). We show in the experiments that we are able to efficiently distribute the workload allowing for roughly 1/3 reduction in the server workload, while achieving 19 percent improvement over a greedy method. As a result, we are able to demonstrate that, in an environment with different types of LLM inference requests, the throughput of the server is improved.

Over-the-Air Federated Learning via Weighted Aggregation

This paper introduces a new federated learning scheme that leverages over-the-air computation. A novel feature of this scheme is the proposal to employ adaptive weights during aggregation, a facet treated as predefined in other over-the-air schemes. This can mitigate the impact of wireless channel conditions on learning performance, without needing channel state information at transmitter side (CSIT). We provide a mathematical methodology to derive the convergence bound for the proposed scheme in the context of computational heterogeneity and general loss functions, supplemented with design insights. Accordingly, we propose aggregation cost metrics and efficient algorithms to find optimized weights for the aggregation. Finally, through numerical experiments, we validate the effectiveness of the proposed scheme. Even with the challenges posed by channel conditions and device heterogeneity, the proposed scheme surpasses other over-the-air strategies by an accuracy improvement of 15% over the scheme using CSIT and 30% compared to the one without CSIT.

Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications

The emergence of large language models (LLMs) has significantly impacted various fields, from natural language processing to sectors like medicine and finance. However, despite their rapid proliferation, the applications of LLMs in telecommunications remain limited, often relying on general-purpose models that lack domain-specific specialization. This lack of specialization results in underperformance, particularly when dealing with telecommunications-specific technical terminology and their associated mathematical representations. This paper addresses this gap by first creating and disseminating Tele-Data, a comprehensive dataset of telecommunications material curated from relevant sources, and Tele-Eval, a large-scale question-and-answer dataset tailored to the domain. Through extensive experiments, we explore the most effective training techniques for adapting LLMs to the telecommunications domain, ranging from examining the division of expertise across various telecommunications aspects to employing parameter-efficient techniques. We also investigate how models of different sizes behave during adaptation and analyze the impact of their training data on this behavior. Leveraging these findings, we develop and open-source Tele-LLMs, the first series of language models ranging from 1B to 8B parameters, specifically tailored for telecommunications. Our evaluations demonstrate that these models outperform their general-purpose counterparts on Tele-Eval while retaining their previously acquired capabilities, thus avoiding the catastrophic forgetting phenomenon.

Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling algorithm for FL over wireless networks that tackles both system and statistical heterogeneity to minimize the wall-clock convergence time. We obtain a new tractable convergence bound for FL algorithms with arbitrary client sampling probability. Based on the bound, we analytically establish the relationship between the total learning time and sampling probability with an adaptive bandwidth allocation scheme, which results in a non-convex optimization problem. We design an efficient algorithm for learning the unknown parameters in the convergence bound and develop a low-complexity algorithm to approximately solve the non-convex problem. Our solution reveals the impact of system and statistical heterogeneity parameters on the optimal client sampling design. Moreover, our solution shows that as the number of sampled clients increases, the total convergence time first decreases and then increases because a larger sampling number reduces the number of rounds for convergence but results in a longer expected time per-round due to limited wireless bandwidth. Experimental results from both hardware prototype and simulation demonstrate that our proposed sampling scheme significantly reduces the convergence time compared to several baseline sampling schemes.

Predictive Handover Strategy in 6G and Beyond: A Deep and Transfer Learning Approach

Next-generation cellular networks will evolve into more complex and virtualized systems, employing machine learning for enhanced optimization and leveraging higher frequency bands and denser deployments to meet varied service demands. This evolution, while bringing numerous advantages, will also pose challenges, especially in mobility management, as it will increase the overall number of handovers due to smaller coverage areas and the higher signal attenuation. To address these challenges, we propose a deep learning based algorithm for predicting the future serving cell utilizing sequential user equipment measurements to minimize the handover failures and interruption time. Our algorithm enables network operators to dynamically adjust handover triggering events or incorporate UAV base stations for enhanced coverage and capacity, optimizing network objectives like load balancing and energy efficiency through transfer learning techniques. Our framework complies with the O-RAN specifications and can be deployed in a Near-Real-Time RAN Intelligent Controller as an xApp leveraging the E2SM-KPM service model. The evaluation results demonstrate that our algorithm achieves a 92% accuracy in predicting future serving cells with high probability. Finally, by utilizing transfer learning, our algorithm significantly reduces the retraining time by 91% and 77% when new handover trigger decisions or UAV base stations are introduced to the network dynamically.

From Similarity to Superiority: Channel Clustering for Time Series Forecasting

Time series forecasting has attracted significant attention in recent decades. Previous studies have demonstrated that the Channel-Independent (CI) strategy improves forecasting performance by treating different channels individually, while it leads to poor generalization on unseen instances and ignores potentially necessary interactions between channels. Conversely, the Channel-Dependent (CD) strategy mixes all channels with even irrelevant and indiscriminate information, which, however, results in oversmoothing issues and limits forecasting accuracy. There is a lack of channel strategy that effectively balances individual channel treatment for improved forecasting performance without overlooking essential interactions between channels. Motivated by our observation of a correlation between the time series model's performance boost against channel mixing and the intrinsic similarity on a pair of channels, we developed a novel and adaptable Channel Clustering Module (CCM). CCM dynamically groups channels characterized by intrinsic similarities and leverages cluster identity instead of channel identity, combining the best of CD and CI worlds. Extensive experiments on real-world datasets demonstrate that CCM can (1) boost the performance of CI and CD models by an average margin of 2.4% and 7.2% on long-term and short-term forecasting, respectively; (2) enable zero-shot forecasting with mainstream time series forecasting models; (3) uncover intrinsic time series patterns among channels and improve interpretability of complex time series models.

Machine Learning on Blockchain Data: A Systematic Mapping Study

Context: Blockchain technology has drawn growing attention in the literature and in practice. Blockchain technology generates considerable amounts of data and has thus been a topic of interest for Machine Learning (ML). Objective: The objective of this paper is to provide a comprehensive review of the state of the art on machine learning applied to blockchain data. This work aims to systematically identify, analyze, and classify the literature on ML applied to blockchain data. This will allow us to discover the fields where more effort should be placed in future research. Method: A systematic mapping study has been conducted to identify the relevant literature. Ultimately, 159 articles were selected and classified according to various dimensions, specifically, the domain use case, the blockchain, the data, and the machine learning models. Results: The majority of the papers (49.7%) fall within the Anomaly use case. Bitcoin (47.2%) was the blockchain that drew the most attention. A dataset consisting of more than 1.000.000 data points was used by 31.4% of the papers. And Classification (46.5%) was the ML task most applied to blockchain data. Conclusion: The results confirm that ML applied to blockchain data is a relevant and a growing topic of interest both in the literature and in practice. Nevertheless, some open challenges and gaps remain, which can lead to future research directions. Specifically, we identify novel machine learning algorithms, the lack of a standardization framework, blockchain scalability issues and cross-chain interactions as areas worth exploring in the future.

Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition

The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-the-art attention model is scalable to accommodate the growing sequence lengths typically encountered in high-resolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of capturing both short-term fluctuations and long-term trends in the data. We then propose a new time series transformer backbone (KronTime) by introducing Kronecker-decomposed attention to process such multi-level time series, which sequentially calculates attention from the lower level to the upper level. Experiments on four long time series datasets demonstrate superior classification results with improved efficiency compared to baseline methods.