Search

Recent cross-domain recommendation (CDR) studies assume that disentangled domain-shared and domain-specific user representations can mitigate domain gaps and facilitate effective knowledge transfer. However, achieving perfect disentanglement is challenging in practice, because user behaviors in CDR are highly complex, and the true underlying user preferences cannot be fully captured through observed user-item interactions alone. Given this impracticability, we instead propose to model {\it joint identifiability} that establishes unique correspondence of user representations across domains, ensuring consistent preference modeling even when user behaviors exhibit shifts in different domains. To achieve this, we introduce a hierarchical user preference modeling framework that organizes user representations by the neural network encoder's depth, allowing separate treatment of shallow and deeper subspaces. In the shallow subspace, our framework models the interest centroids for each user within each domain, probabilistically determining the users' interest belongings and selectively aligning these centroids across domains to ensure fine-grained consistency in domain-irrelevant features. For deeper subspace representations, we enforce joint identifiability by decomposing it into a shared cross-domain stable component and domain-variant components, linked by a bijective transformation for unique correspondence. Empirical studies on real-world CDR tasks with varying domain correlations demonstrate that our method consistently surpasses state-of-the-art, even with weakly correlated tasks, highlighting the importance of joint identifiability in achieving robust CDR., Comment: 12 pages, 6 figures, under review

In the past few years, Artificial Intelligence (AI)-based weather forecasting methods have widely demonstrated strong competitiveness among the weather forecasting systems. However, these methods are insufficient for high-spatial-resolution short-term nowcasting within 6 hours, which is crucial for warning short-duration, mesoscale and small-scale weather events. Geostationary satellite remote sensing provides detailed, high spatio-temporal and all-day observations, which can address the above limitations of existing methods. Therefore, this paper proposed an advanced data-driven thermal infrared cloud images forecasting model, "DaYu." Unlike existing data-driven weather forecasting models, DaYu is specifically designed for geostationary satellite observations, with a temporal resolution of 0.5 hours and a spatial resolution of ${0.05}^\circ$ $\times$ ${0.05}^\circ$. DaYu is based on a large-scale transformer architecture, which enables it to capture fine-grained cloud structures and learn fast-changing spatio-temporal evolution features effectively. Moreover, its attention mechanism design achieves a balance in computational complexity, making it practical for applications. DaYu not only achieves accurate forecasts up to 3 hours with a correlation coefficient higher than 0.9, 6 hours higher than 0.8, and 12 hours higher than 0.7, but also detects short-duration, mesoscale, and small-scale weather events with enhanced detail, effectively addressing the shortcomings of existing methods in providing detailed short-term nowcasting within 6 hours. Furthermore, DaYu has significant potential in short-term climate disaster prevention and mitigation.

Symmetric orbifold CFTs contain twist operators that can join and split copies of the CFT, leading to the creation of pairs from the vacuum. In this paper, we study the pair creation processes involving four twist-2 operators. In addition to the pair creation previously observed purely in the left or right moving sectors, we find a novel mixing between left and right movers during pair creation. This phenomenon arises from nontrivial monodromy conditions that originate from a genus-one covering surface, where left and right movers become coupled through the torus., Comment: 44 pages, 7 figures

The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has spurred the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival times of mobile sensory data vary due to modality size and network dynamics, which can lead to delays (if waiting for slower data) or accuracy decline (if inference proceeds without waiting). Moreover, the diversity and dynamic nature of mobile systems exacerbate this challenge. In response, we present a shift to \textit{opportunistic} inference for asynchronous distributed multi-modal data, enabling inference as soon as partial data arrives. While existing methods focus on optimizing modality consistency and complementarity, known as modal affinity, they lack a \textit{computational} approach to control this affinity in open-world mobile environments. AdaFlow pioneers the formulation of structured cross-modality affinity in mobile contexts using a hierarchical analysis-based normalized matrix. This approach accommodates the diversity and dynamics of modalities, generalizing across different types and numbers of inputs. Employing an affinity attention-based conditional GAN (ACGAN), AdaFlow facilitates flexible data imputation, adapting to various modalities and downstream tasks without retraining. Experiments show that AdaFlow significantly reduces inference latency by up to 79.9\% and enhances accuracy by up to 61.9\%, outperforming status quo approaches.

Ubiquitous on-device heart rate sensing is vital for high-stress individuals and chronic patients. Non-contact sensing, compared to contact-based tools, allows for natural user monitoring, potentially enabling more accurate and holistic data collection. However, in open and uncontrolled mobile environments, user movement and lighting introduce. Existing methods, such as curve-based or short-range deep learning recognition based on adjacent frames, strike the optimal balance between real-time performance and accuracy, especially under limited device resources. In this paper, we present UbiHR, a ubiquitous device-based heart rate sensing system. Key to UbiHR is a real-time long-range spatio-temporal model enabling noise-independent heart rate recognition and display on commodity mobile devices, along with a set of mechanisms for prompt and energy-efficient sampling and preprocessing. Diverse experiments and user studies involving four devices, four tasks, and 80 participants demonstrate UbiHR's superior performance, enhancing accuracy by up to 74.2\% and reducing latency by 51.2\%.

On-device adapting to continual, unpredictable domain shifts is essential for mobile applications like autonomous driving and augmented reality to deliver seamless user experiences in evolving environments. Test-time adaptation (TTA) emerges as a promising solution by tuning model parameters with unlabeled live data immediately before prediction. However, TTA's unique forward-backward-reforward pipeline notably increases the latency over standard inference, undermining the responsiveness in time-sensitive mobile applications. This paper presents AdaShadow, a responsive test-time adaptation framework for non-stationary mobile data distribution and resource dynamics via selective updates of adaptation-critical layers. Although the tactic is recognized in generic on-device training, TTA's unsupervised and online context presents unique challenges in estimating layer importance and latency, as well as scheduling the optimal layer update plan. AdaShadow addresses these challenges with a backpropagation-free assessor to rapidly identify critical layers, a unit-based runtime predictor to account for resource dynamics in latency estimation, and an online scheduler for prompt layer update planning. Also, AdaShadow incorporates a memory I/O-aware computation reuse scheme to further reduce latency in the reforward pass. Results show that AdaShadow achieves the best accuracy-latency balance under continual shifts. At low memory and energy costs, Adashadow provides a 2x to 3.5x speedup (ms-level) over state-of-the-art TTA methods with comparable accuracy and a 14.8% to 25.4% accuracy boost over efficient supervised methods with similar latency., Comment: This paper is accepted by SenSys 2024. Copyright may be transferred without notice

As one of the most well-studied cohesive subgraph models, the $k$-core is widely used to find graph nodes that are ``central'' or ``important'' in many applications, such as biological networks, social networks, ecological networks, and financial networks. For distributed networks, e.g., Decentralized Online Social Networks (DOSNs) such that each vertex is a client as a single computing unit, the distributed $k$-core decomposition algorithms are already proposed. However, current distributed approaches fail to adequately protect privacy and security. In today's data-driven world, data privacy and security have attracted more and more attention, e.g., DOSNs are proposed to protect privacy by storing user information locally without using a single centralized server. In this work, we are the first to propose the secure version of the distributed $k$-core decomposition., Comment: 14 pages, 7 figures

We construct entire curves in projective spaces that are simultaneously frequently hypercyclic for translations along countably many specified directions, while preserving optimal slow growth rates. Moreover, we demonstrate that there do not exist entire curves that are frequently hypercyclic for translations along uncountably many directions while still exhibiting optimal slow growth. This result contrasts with the phenomenon observed for hypercyclic entire functions, which can be hypercyclic for translations along uncountably many directions while maintaining slow growth. Our approach is fundamentally grounded in Nevanlinna theory, and the construction is heuristically guided by the Oka principle. This work provides a new perspective on the intricate interplay between the dynamical properties and growth rates of entire curves in projective spaces.

Diffusion generative models, famous for their performance in image generation, are popular in various cross-domain applications. However, their use in the communication community has been mostly limited to auxiliary tasks like data modeling and feature extraction. These models hold greater promise for fundamental problems in network optimization compared to traditional machine learning methods. Discriminative deep learning often falls short due to its single-step input-output mapping and lack of global awareness of the solution space, especially given the complexity of network optimization's objective functions. In contrast, diffusion generative models can consider a broader range of solutions and exhibit stronger generalization by learning parameters that describe the distribution of the underlying solution space, with higher probabilities assigned to better solutions. We propose a new framework Diffusion Model-based Solution Generation (DiffSG), which leverages the intrinsic distribution learning capabilities of diffusion generative models to learn high-quality solution distributions based on given inputs. The optimal solution within this distribution is highly probable, allowing it to be effectively reached through repeated sampling. We validate the performance of DiffSG on several typical network optimization problems, including mixed-integer non-linear programming, convex optimization, and hierarchical non-convex optimization. Our results show that DiffSG outperforms existing baselines. In summary, we demonstrate the potential of diffusion generative models in tackling complex network optimization problems and outline a promising path for their broader application in the communication community., Comment: 8 pages, 5 figures

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry. When GPU hardware resources are limited, we can explore alternative options on CPUs. To mitigate the financial burden and alleviate constraints imposed by hardware resources, optimizing inference performance is necessary. In this paper, we introduce an easily deployable inference performance optimization solution aimed at accelerating LLMs on CPUs. In this solution, we implement an effective way to reduce the KV cache size while ensuring precision. We propose a distributed inference optimization approach and implement it based on oneAPI Collective Communications Library. Furthermore, we propose optimization approaches for LLMs on CPU, and conduct tailored optimizations for the most commonly used models. The code is open-sourced at https://github.com/intel/xFasterTransformer., Comment: 5 pages, 6 figure, ICML 2024 on Foundation Models in the Wild

Artificial Intelligence of Things (AIoT) is an emerging frontier based on the deep fusion of Internet of Things (IoT) and Artificial Intelligence (AI) technologies. Although advanced deep learning techniques enhance the efficient data processing and intelligent analysis of complex IoT data, they still suffer from notable challenges when deployed to practical AIoT applications, such as constrained resources, and diverse task requirements. Knowledge transfer is an effective method to enhance learning performance by avoiding the exorbitant costs associated with data recollection and model retraining. Notably, although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances of various knowledge transfer techniques for AIoT field. This survey endeavors to introduce a new concept of knowledge transfer, referred to as Crowd Knowledge Transfer (CrowdTransfer), which aims to transfer prior knowledge learned from a crowd of agents to reduce the training cost and as well as improve the performance of the model in real-world complicated scenarios. Particularly, we present four transfer modes from the perspective of crowd intelligence, including derivation, sharing, evolution and fusion modes. Building upon conventional transfer learning methods, we further delve into advanced crowd knowledge transfer models from three perspectives for various AIoT applications. Furthermore, we explore some applications of AIoT areas, such as human activity recognition, urban computing, multi-robot system, and smart factory. Finally, we discuss the open issues and outline future research directions of knowledge transfer in AIoT community., Comment: This paper has been accepted for publication in IEEE Communications Surveys & Tutorials. Copyright will be transferred without notice, after this version may no longer be accessible

Given an undirected graph, the $k$-core is a subgraph in which each node has at least $k$ connections, which is widely used in graph analytics to identify core subgraphs within a larger graph. The sequential $k$-core decomposition algorithm faces limitations due to memory constraints and data graphs can be inherently distributed. A distributed approach is proposed to overcome limitations by allowing each vertex to independently do calculation by only using local information. This paper explores the experimental evaluation of a distributed $k$-core decomposition algorithm. By assuming that each vertex is a client as a single computing unit, we simulate the process using Golang, leveraging its Goroutine and message passing. Due to the fact that the real-world data graphs can be large with millions of vertices, it is expensive to build such a distributed environment with millions of clients if the experiments run in a real-life scenario. Therefore, our experimental simulation can effectively evaluate the running time and message passing for the distributed $k$-core decomposition.

In this short note, we remove the small degeneracy assumption in our earlier works [10, 11]. This is achieved by a technical improvement of Corollary 5.1 in [10]. As a consequence, we establish the same geometric estimates for diameter, Green's functions and Sobolev inequalities under an entropy bound for the K\"ahler metrics, without any small degeneracy assumption.

Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (VLM) to interpret video anomalies precisely. Recognizing the difference in motion information between abnormal and normal videos, Hawk explicitly integrates motion modality to enhance anomaly identification. To reinforce motion attention, we construct an auxiliary consistency loss within the motion and video space, guiding the video branch to focus on the motion modality. Moreover, to improve the interpretation of motion-to-language, we establish a clear supervisory relationship between motion and its linguistic representation. Furthermore, we have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions. The final results demonstrate that Hawk achieves SOTA performance, surpassing existing baselines in both video description generation and question-answering. Our codes/dataset/demo will be released at https://github.com/jqtangust/hawk.

Clouds play a crucial role in the Earth's water and energy cycles, underscoring the importance of high spatiotemporal resolution data on cloud phase and properties for accurate numerical modeling and weather prediction. Currently, Moderate Resolution Imaging Spectroradiometer (MODIS) provides cloud products with a spatial resolution of 1 km. However, these products suffer from a lengthy revisit cycle. This study develops a generative diffusion model (donated as CloudDiff) for super-resolution retrieval of high spatiotemporal cloud phase and properties, applicable both day and night. Leveraging 2 km spatial resolution Himawari-8 Advanced Himawari Imager (AHI) thermal infrared (TIR) radiances and viewing geometry as condition, alongside daytime MODIS products as targets, the model can generate cloud phase (CLP), cloud top height (CTH), cloud optical thickness (COT), and cloud effective radius (CER) at 1 km spatial resolution and 10-minute temporal resolution. The conditional diffusion model can generate sharper images and capture finer local features than deterministic super-resolution approaches. It draws multiple samples based on the underlying probability distribution, enabling retrieval uncertainty assessment. Evaluations show agreement between cloud phase and properties derived from the CloudDiff and MODIS cloud products. The ensemble mean is found to enhance retrieval accuracy and credibility, outperforming the deterministic model.

We establish a necessary and sufficient condition for solving a general class of fully nonlinear elliptic equations on closed Riemannian or hermitian manifolds, including both hessian and hessian quotient equations. It settles an open problem of Li and Urbas. Such a condition is based on an analytic slope invariant analogous to the slope stability and the Nakai-Moishezon criterion in complex geometry. As an application, we solve the non-constant $J$-equation on both hermitian manifolds and singular K\"ahler spaces.

There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the mobile devices hold potential to accelerate DL inference via parallel execution across heterogeneous processors. Various efficient parallel methods have been explored to optimize computation distribution, achieve load balance, and minimize communication cost across processors. Yet their practical effectiveness in the dynamic and diverse real-world mobile environment is less explored. This paper presents a holistic empirical study to assess the capabilities and challenges associated with parallel DL inference on heterogeneous mobile processors. Through carefully designed experiments covering various DL models, mobile software/hardware environments, workload patterns, and resource availability, we identify limitations of existing techniques and highlight opportunities for cross-level optimization.

Running multi-task DNNs on mobiles is an emerging trend for various applications like autonomous driving and mobile NLP. Mobile DNNs are often compressed to fit the limited resources and thus suffer from degraded accuracy and generalizability due to data drift. DNN evolution, e.g., continuous learning and domain adaptation, has been demonstrated effective in overcoming these issues, mostly for single-task DNN, leaving multi-task DNN evolution an important yet open challenge. To fill up this gap, we propose AdaBridge, which exploits computational redundancies in multi-task DNNs as a unique opportunity for dynamic data and computation reuse, thereby improving training efficacy and resource efficiency among asynchronous multi-task co-evolution in edge systems. Experimental evaluation shows that AdaBridge achieves 11% average accuracy gain upon individual evolution baselines., Comment: Accepted by NSDI'24 Poster

Deep neural network (DNN) has driven extensive applications in mobile technology. However, for long-running mobile apps like voice assistants or video applications on smartphones, energy efficiency is critical for battery-powered devices. The rise of heterogeneous processors in mobile devices today has introduced new challenges for optimizing energy efficiency. Our key insight is that partitioning computations across different processors for parallelism and speedup doesn't necessarily correlate with energy consumption optimization and may even increase it. To address this, we present AdaOper, an energy-efficient concurrent DNN inference system. It optimizes energy efficiency on mobile heterogeneous processors while maintaining responsiveness. AdaOper includes a runtime energy profiler that dynamically adjusts operator partitioning to optimize energy efficiency based on dynamic device conditions. We conduct preliminary experiments, which show that AdaOper reduces energy consumption by 16.88% compared to the existing concurrent method while ensuring real-time performance.

Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. Existing works rely on either representation alignment or transformation bridges, but they struggle on identifying domain-shared from domain-specific latent factors. Specifically, while CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability as they primarily fixate on the marginal distribution within a particular domain. Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated. In this study, we explore what should and should not be transferred in cross-domain user representations from a causality perspective. We propose a Hierarchical subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution, termed HJID, to preserve domain-specific behaviors from domain-shared factors. HJID organizes user representations into layers: generic shallow subspaces and domain-oriented deep subspaces. We first encode the generic pattern in the shallow subspace by minimizing the Maximum Mean Discrepancy of initial layer activation. Then, to dissect how domain-oriented latent factors are encoded in deeper layers activation, we construct a cross-domain causality-based data generation graph, which identifies cross-domain consistent and domain-specific components, adhering to the Minimal Change principle. This allows HJID to maintain stability whilst discovering unique factors for different domains, all within a generative framework of invertible transformations that guarantee the joint identifiability. With experiments on real-world datasets, we show that HJID outperforms SOTA methods on a range of strongly and weakly correlated CDR tasks., Comment: accepted to SIGIR 2024 as a Full Research Paper

Persuasion, as one of the crucial abilities in human communication, has garnered extensive attention from researchers within the field of intelligent dialogue systems. We humans tend to persuade others to change their viewpoints, attitudes or behaviors through conversations in various scenarios (e.g., persuasion for social good, arguing in online platforms). Developing dialogue agents that can persuade others to accept certain standpoints is essential to achieving truly intelligent and anthropomorphic dialogue system. Benefiting from the substantial progress of Large Language Models (LLMs), dialogue agents have acquired an exceptional capability in context understanding and response generation. However, as a typical and complicated cognitive psychological system, persuasive dialogue agents also require knowledge from the domain of cognitive psychology to attain a level of human-like persuasion. Consequently, the cognitive strategy-enhanced persuasive dialogue agent (defined as CogAgent), which incorporates cognitive strategies to achieve persuasive targets through conversation, has become a predominant research paradigm. To depict the research trends of CogAgent, in this paper, we first present several fundamental cognitive psychology theories and give the formalized definition of three typical cognitive strategies, including the persuasion strategy, the topic path planning strategy, and the argument structure prediction strategy. Then we propose a new system architecture by incorporating the formalized definition to lay the foundation of CogAgent. Representative works are detailed and investigated according to the combined cognitive strategy, followed by the summary of authoritative benchmarks and evaluation metrics. Finally, we summarize our insights on open issues and future directions of CogAgent for upcoming researchers., Comment: 36 pages, 6 figures

We use families of circular null geodesics as probes of a family of microstate geometries, known as $(1,0,n)$ superstrata. These geometries carry a left-moving momentum wave and the behavior of some of the geodesic probes is very sensitive to this background wave. The left-moving geodesics behave like BPS particles and so can be placed in circular orbits anywhere in the geometry and actually "float" at fixed radius and angle in the three-dimensional "capped BTZ" geometry. The right-moving geodesics behave like non-BPS particles. We show that they provide a simple geometric characterization of the black-hole bound: when the momentum charge of the geometry is below this bound, such geodesics can be placed anywhere, but exceeding the bound, even by a small amount, means these geodesics are restricted to the deep interior of the geometry. We also show that for left-moving string probes, the tidal forces remain comparable with those of global AdS$_3$. Nevertheless, for some of these probes, the "bumps" in the geometry induce an oscillatory mass term and we discuss how this can lead to chaotic scrambling of the state of the string., Comment: 29 pages, 8 figures

The rise of mobile devices with abundant sensory data and local computing capabilities has driven the trend of federated learning (FL) on these devices. And personalized FL (PFL) emerges to train specific deep models for each mobile device to address data heterogeneity and varying performance preferences. However, mobile training times vary significantly, resulting in either delay (when waiting for slower devices for aggregation) or accuracy decline (when aggregation proceeds without waiting). In response, we propose a shift towards asynchronous PFL, where the server aggregates updates as soon as they are available. Nevertheless, existing asynchronous protocols are unfit for PFL because they are devised for federated training of a single global model. They suffer from slow convergence and decreased accuracy when confronted with severe data heterogeneity prevalent in PFL. Furthermore, they often exclude slower devices for staleness control, which notably compromises accuracy when these devices possess critical personalized data. Therefore, we propose EchoPFL, a coordination mechanism for asynchronous PFL. Central to EchoPFL is to include updates from all mobile devices regardless of their latency. To cope with the inevitable staleness from slow devices, EchoPFL revisits model broadcasting. It intelligently converts the unscalable broadcast to on-demand broadcast, leveraging the asymmetrical bandwidth in wireless networks and the dynamic clustering-based PFL. Experiments show that compared to status quo approaches, EchoPFL achieves a reduction of up to 88.2% in convergence time, an improvement of up to 46% in accuracy, and a decrease of 37% in communication costs, Comment: accepted by Ubicomp2024

Uniform bounds are obtained using the auxiliary Monge-Amp\`ere equation method for solutions of very general classes of fully non-linear partial differential equations, assuming the existence of a ${C}$-subsolution in the sense of G. Sz\'ekelyhidi and B. Guan. The main advantage over previous estimates is in the K\"ahler case, where the new estimates remain uniform as the background metric is allowed to degenerate.

Let $X$ be a K\"ahler manifold with semi-ample canonical bundle $K_X$. It is proved by Jian-Shi-Song that for any K\"ahler class $\gamma$, there exists $\delta>0$ such that for all $t\in (0, \delta)$ there exists a unique cscK metric $g_t$ in $K_X+ t \gamma $. In this paper, we prove that $\{ (X, g_t) \}_{ t\in (0, \delta)} $ have uniformly bounded K\"ahler potentials, volume forms and diameters. As a consequence, these metric spaces are pre-compact in the Gromov-Hausdorff sense., Comment: 13 pages, no figures. All comments are welcome!

The bound state of one NS5 brane (wrapped on a $\mathbb{T}^4$) and $N$ NS1-branes has two dual descriptions: its low-energy dynamics is described by the symmetric orbifold of $\mathbb{T}^4$, while the near horizon geometry is captured by string theory on ${\rm AdS}_3 \times {\rm S}^3\times \mathbb{T}^4$ with one unit of NS flux. The latter theory is exactly solvable in the hybrid formalism, and this allows one to prove the equivalence of the two descriptions. In this paper we extend this duality to $\mathbb{Z}_k$ orbifolds of this ${\rm AdS}_3 \times {\rm S}^3$ background. In particular, we show that the corresponding worldsheet spectrum reproduces exactly the perturbative excitations on top of a certain non-perturbative state in the dual symmetric orbifold theory. Since the ${\rm AdS}/{\rm CFT}$ duality map is exact for these models, we obtain an interesting picture of how the duality relates boundary and bulk descriptions., Comment: 37 pages, 1 figure

This paper considers optimal traffic signal control in smart cities, which has been taken as a complex networked system control problem. Given the interacting dynamics among traffic lights and road networks, attaining controller adaptivity and scalability stands out as a primary challenge. Capturing the spatial-temporal correlation among traffic lights under the framework of Multi-Agent Reinforcement Learning (MARL) is a promising solution. Nevertheless, existing MARL algorithms ignore effective information aggregation which is fundamental for improving the learning capacity of decentralized agents. In this paper, we design a new decentralized control architecture with improved environmental observability to capture the spatial-temporal correlation. Specifically, we first develop a topology-aware information aggregation strategy to extract correlation-related information from unstructured data gathered in the road network. Particularly, we transfer the road network topology into a graph shift operator by forming a diffusion process on the topology, which subsequently facilitates the construction of graph signals. A diffusion convolution module is developed, forming a new MARL algorithm, which endows agents with the capabilities of graph learning. Extensive experiments based on both synthetic and real-world datasets verify that our proposal outperforms existing decentralized algorithms.

We establish a uniform Sobolev inequality for K\"ahler metrics, which only require an entropy bound and no lower bound on the Ricci curvature. We further extend our Sobolev inequality to singular K\"ahler metrics on K\"ahler spaces with normal singularities. This allows us to build a general theory of global geometric analysis on singular K\"ahler spaces including the spectral theorem, heat kernel estimates, eigenvalue estimates and diameter estimates. Such estimates were only known previously in very special cases such as Bergman metrics. As a consequence, we derive various geometric estimates, such as the diameter estimate and the Sobolev inequality, for K\"ahler-Einstein currents on projective varieties with definite or vanishing first Chern class.

With the rapid development of deep learning, recent research on intelligent and interactive mobile applications (e.g., health monitoring, speech recognition) has attracted extensive attention. And these applications necessitate the mobile edge computing scheme, i.e., offloading partial computation from mobile devices to edge devices for inference acceleration and transmission load reduction. The current practices have relied on collaborative DNN partition and offloading to satisfy the predefined latency requirements, which is intractable to adapt to the dynamic deployment context at runtime. AdaMEC, a context-adaptive and dynamically-combinable DNN deployment framework is proposed to meet these requirements for mobile edge computing, which consists of three novel techniques. First, once-for-all DNN pre-partition divides DNN at the primitive operator level and stores partitioned modules into executable files, defined as pre-partitioned DNN atoms. Second, context-adaptive DNN atom combination and offloading introduces a graph-based decision algorithm to quickly search the suitable combination of atoms and adaptively make the offloading plan under dynamic deployment contexts. Third, runtime latency predictor provides timely latency feedback for DNN deployment considering both DNN configurations and dynamic contexts. Extensive experiments demonstrate that AdaMEC outperforms state-of-the-art baselines in terms of latency reduction by up to 62.14% and average memory saving by 55.21%.

Vehicular crowd intelligence (VCI) is an emerging research field. Facilitated by state-of-the-art vehicular ad-hoc networks and artificial intelligence, various VCI applications come to place, e.g., collaborative sensing, positioning, and mapping. The collaborative property of VCI applications generally requires data to be shared among participants, thus forming network-wide intelligence. How to fulfill this process without compromising data privacy remains a challenging issue. Although federated learning (FL) is a promising tool to solve the problem, adapting conventional FL frameworks to VCI is nontrivial. First, the centralized model aggregation is unreliable in VCI because of the existence of stragglers with unfavorable channel conditions. Second, existing FL schemes are vulnerable to Non-IID data, which is intensified by the data heterogeneity in VCI. This paper proposes a novel federated learning framework called RaftFed to facilitate privacy-preserving VCI. The experimental results show that RaftFed performs better than baselines regarding communication overhead, model accuracy, and model convergence., Comment: 8 pages,8 figures

By means of hypercyclic operator theory, we complement our previous results on hypercyclic holomorphic maps between complex Euclidean spaces having slow growth rates,by showing {\it abstract abundance} rather than {\it explicit existence}. Next, we establish that, in the space of holomorphic maps from $\mathbb{C}^n$ to any connected Oka manifold $Y$, equipped with the compact-open topology, there exists a {\em dense} subset consisting of common {\em frequently hypercyclic} elements for all nontrivial translation operators. To our knowledge, this is new even for $n=1$ and $Y=\mathbb{C}$.