Link adaptation in 5G wireless networks faces fundamental challenges due to the stochastic nature of the radio environment. Deep reinforcement learning (DRL) has shown potential for automating adaptive control, but it often suffers from instability when user mobility, fading, and interference introduce significant variability in link performance. This inconsistency in action outcomes, particularly when adjusting the downlink target block error rate (BLER), complicates the learning process and slows convergence. To address this, we propose a probabilistic representation learning framework in which the variance of each user’s latent state is conditioned on the selected BLER. This structure enables the DRL agent to reason about action-dependent uncertainty and learn more robust, risk-aware policies. We implement this representation within DRL agents and evaluate the approach using a commercial-grade 5G system-level simulator based on ns-3. Experimental results show that the proposed method improves downlink throughput by up to 19.0% over fixed-rule baselines, achieves up to 11.3% gain over heuristic eOLLA algorithms, and reduces convergence time by 46.2%, consistently demonstrating superior performance under diverse mobility scenarios.

As technologies for 4G and 5G networks become increasingly complex, user equipment's (UE) energy consumption also increased significantly. The 4G and 5G systems employ connected-mode discontinuous reception (C-DRX) to save UEs energy consumption by intermittently suspending network connections. However, optimizing the C-DRX operation is complex that requires considering various network conditions, including traffic patterns of each UE and the scheduling algorithms of a base station (BS). In this paper, we introduce a novel approach, a Multi-Agent Deep Reinforcement Learning (MADRL) algorithm with an integrated self-attention mechanism. This approach empowers the model to optimize C-DRX parameters independent of BSs' scheduling algorithms, enhancing its adaptability to dynamically changing network conditions. Simulation results illustrate that our MADRL-based C-DRX optimization algorithm consistently outperforms traditional methods under varying network conditions, affirming its robustness and efficacy for real- world network optimization.

Increased network traffic demands have led to ex-tremely dense network deployments. This translates to significant growth in energy consumption at the radio access networks, resulting in high network operation costs (OPEX). In this work, we apply deep reinforcement learning to reduce the energy consumption at the base station in dense wireless networks, by allowing cells that overlap in geographical areas to be put in standby mode according to the changing network conditions. We start by formulating the problem of the cell on/off energy saving in dense wireless networks as a Markov decision process. Then, a deep reinforcement learning (DRL) solution is proposed. This DRL solution takes into account different key performance indicators (KPIs) of both the network and user equipment and aims to reduce the energy consumed by the network without significantly impacting the overall KPIs. The performance of the proposed solution is evaluated using a practical network simulator.

Document labeling is a critical step in building various machine learning applications. However, the step can be time-consuming and arduous, requiring a significant amount of human efforts. To support an efficient document labeling environment, we present a system called Attentive Interactive Labeling Assistant (AILA). In its core, AILA uses Interactive Attention Module (IAM), a novel module that visually highlights words in a document that labelers may pay attention to when labeling a document. IAM utilizes attention-based Deep Neural Networks which not only support a prediction of which words to highlight but also enable labelers to indicate words that should be assigned a high attention weight while labeling to improve the future quality of word prediction.We evaluated the labeling efficiency and the accuracy by comparing the conditions with and without IAM in our study. The results showed that participants' labeling efficiency increased significantly under the condition with IAM than the condition without IAM, while the two conditions maintained roughly the same labeling accuracy.

Detecting anomalous events of a particular area in a timely manner is an important task. Geo-tagged social media data are useful resource for this task; however, the abundance of everyday language in them makes this task still challenging. To address such challenges, we present TopicOnTiles, a visual analytics system that can reveal information relevant to anomalous events in a multi-level tile-based map interface by using social media data. To this end, we adopt and improve a recently proposed topic modeling method that can extract spatio-temporally exclusive topics corresponding to a particular region and a time point. Furthermore, we utilize a tile-based map interface to efficiently handle large-scale data in parallel. Our user interface effectively highlights anomalous tiles using our novel glyph visualization that encodes the degree of anomaly computed by our exclusive topic modeling processes. To show the effectiveness of our system, we present several usage scenarios using real-world datasets as well as comprehensive user study results.

Abstract Embedding and visualizing large‐scale high‐dimensional data in a two‐dimensional space is an important problem, because such visualization can reveal deep insights of complex data. However, most of the existing embedding approaches run on an excessively high precision, even when users want to obtain a brief insight from a visualization of large‐scale datasets, ignoring the fact that in the end, the outputs are embedded onto a fixed‐range pixel‐based screen space. Motivated by this observation and directly considering the properties of screen space in an embedding algorithm, we propose Pixel‐Aligned Stochastic Neighbor Embedding (PixelSNE), a highly efficient screen resolution‐driven 2D embedding method which accelerates Barnes‐Hut tree‐based t‐distributed stochastic neighbor embedding (BH‐SNE), which is known to be a state‐of‐the‐art 2D embedding method. Our experimental results show a significantly faster running time for PixelSNE compared to BH‐SNE for various datasets while maintaining comparable embedding quality.

Understanding newly emerging events or topics associated with a particular region of a given day can provide deep insight on the critical events occurring in highly evolving metropolitan cities. We propose herein a novel topic modeling approach on text documents with spatio-temporal information (e.g., when and where a document was published) such as location-based social media data to discover prevalent topics or newly emerging events with respect to an area and a time point. We consider a map view composed of regular grids or tiles with each showing topic keywords from documents of the corresponding region. To this end, we present a tilebased spatio-temporally exclusive topic modeling approach called STExNMF, based on a novel nonnegative matrix factorization (NMF) technique. STExNMF mainly works based on the two following stages: (1) first running a standard NMF of each tile to obtain general topics of the tile and (2) running a spatiotemporally exclusive NMF on a weighted residual matrix. These topics likely reveal information on newly emerging events or topics of interest within a region. We demonstrate the advantages of our approach using the geo-tagged Twitter data of New York City. We also provide quantitative comparisons in terms of the topic quality, spatio-temporal exclusiveness, topic variation, and qualitative evaluations of our method using several usage scenarios. In addition, we present a fast topic modeling technique of our model by leveraging parallel computing.