The recent development of 3D Gaussian splatting (3DGS) has led to great interest in 4D dynamic spatial reconstruction. Existing approaches mainly rely on full-length multi-view videos, while there has been limited exploration of online reconstruction methods that enable on-the-fly training and per-timestep streaming. Current 3DGS-based streaming methods treat the Gaussian primitives uniformly and constantly renew the densified Gaussians. Thus, they overlook the difference between dynamic and static features and neglect the temporal continuity of the scene. To address these limitations, we propose a novel pipeline for iterative streamable 4D dynamic spatial reconstruction. It comprises three stages: a selective inheritance stage that retains priors from previous timesteps to preserve the temporal continuity, a dynamics-aware shift stage that distinguishes dynamic and static primitives and employs distinct strategies to optimize their movements, and an error-guided densification stage that efficiently identifies Gaussians requiring densification to accommodate emerging objects. Our method achieves state-of-the-art performance in online 4D reconstruction, demonstrating compact storage, the fastest on-the-fly training speed, and superior representation quality.

Wireless channel modeling plays a pivotal role in designing, analyzing, and optimizing wireless communication systems. Nevertheless, developing an effective channel modeling approach has been a long-standing challenge. This issue has been escalated due to denser network deployment, larger antenna arrays, and broader bandwidth in next-generation networks. To address this challenge, we put forth WRF-GS, a novel framework for channel modeling based on wireless radiation field (WRF) reconstruction using 3D Gaussian splatting (3D-GS). WRF-GS employs 3D Gaussian primitives and neural networks to capture the interactions between the environment and radio signals, enabling efficient WRF reconstruction and visualization of the propagation characteristics. The reconstructed WRF can then be used to synthesize the spatial spectrum for comprehensive wireless channel characterization. While WRF-GS demonstrates remarkable effectiveness, it faces limitations in capturing high-frequency signal variations caused by complex multipath effects. To overcome these limitations, we propose WRF-GS+, an enhanced framework that integrates electromagnetic wave physics into the neural network design. WRF-GS+ leverages deformable 3D Gaussians to model both static and dynamic components of the WRF, significantly improving its ability to characterize signal variations. In addition, WRF-GS+ accelerates the splatting process by simplifying the 3D-GS modeling operation and reducing sample complexity. Experimental results demonstrate that both WRF-GS and WRF-GS+ outperform baselines for spatial spectrum synthesis, including ray tracing and other deep-learning approaches. Notably, WRF-GS+ achieves state-of-the-art performance in the received signal strength indication (RSSI) and channel state information (CSI) prediction tasks, surpassing existing methods by more than 0.7 dB and 3.36 dB, respectively. The code is available at https://github.com/wenchaozheng/WRF-GSplus.

Pre-trained language models have made significant strides in natural language processing tasks, enabling flexible fine-tuning for downstream applications. However, in few-shot learning scenarios, pre-trained models face challenges related to overfitting due to limited training samples, which hinders their ability to capture data diversity and robustly handle input variations. To overcome these limitations, we propose the Saliency-Augmented Consistency Regularization (SACR) framework, a novel self-training strategy designed to improve few-shot learning performance and robustness. SACR consists of three key components: (1) Saliency-guided Data Perturbation, which uses saliency analysis to identify and perturb words that significantly influence model predictions, generating semantically consistent pseudo-samples; (2) Semantic-equivalent Sample Mining, which employs K-means clustering to select semantically similar samples and prevent semantic shift; and (3) Consistency Training, where regularization ensures consistency between the semantics and prediction distributions of the original and perturbed samples. We conducted extensive experiments on 15 public datasets to evaluate our approach. SACR significantly outperforms strong baseline models and demonstrates superior generalization capabilities compared to state-of-the-art methods, achieving an average 1.0% improvement in classification accuracy.

4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and a GPU-friendly rasterizer, enabling rapid rendering speeds. Despite its advantages, 4DGS faces significant challenges, notably the requirement of millions of 4D Gaussians, each with extensive associated attributes, leading to substantial memory and storage cost. This paper introduces a memory-efficient framework for 4DGS. We streamline the color attribute by decomposing it into a per-Gaussian direct color component with only 3 parameters and a shared lightweight alternating current color predictor. This approach eliminates the need for spherical harmonics coefficients, which typically involve up to 144 parameters in classic 4DGS, thereby creating a memory-efficient 4D Gaussian representation. Furthermore, we introduce an entropy-constrained Gaussian deformation technique that uses a deformation field to expand the action range of each Gaussian and integrates an opacity-based entropy loss to limit the number of Gaussians, thus forcing our model to use as few Gaussians as possible to fit a dynamic scene well. With simple half-precision storage and zip compression, our framework achieves a storage reduction by approximately 190$\times$ and 125$\times$ on the Technicolor and Neural 3D Video datasets, respectively, compared to the original 4DGS. Meanwhile, it maintains comparable rendering speeds and scene representation quality, setting a new standard in the field. Code is available at https://github.com/Xinjie-Q/MEGA.

We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading processes of objects is essential for achieving high-fidelity results. Therefore, it is critical to incorporate global illumination to account for indirect lighting that reaches an object after multiple bounces across the scene. Previous 3DGS-based methods have attempted to model indirect lighting by characterizing indirect illumination as learnable lighting volumes or additional attributes of each Gaussian, while using baked occlusion to represent shadow effects. These methods, however, fail to accurately model the complex physical interactions between light and objects, making it impossible to construct realistic indirect illumination during relighting. To address this limitation, we propose to calculate indirect lighting using efficient path tracing with deferred shading. In our framework, we first render a G-buffer to capture the detailed geometry and material properties of the scene. Then, we perform physically-based rendering (PBR) only for direct lighting. With the G-buffer and previous rendering results, the indirect lighting can be calculated through a lightweight path tracing. Our method effectively models indirect lighting under any given lighting conditions, thereby achieving better novel view synthesis and competitive relighting. Quantitative and qualitative results show that our GI-GS outperforms existing baselines in both rendering quality and efficiency. Project page: https://stopaimme.github.io/GI-GS-site/.

Aspect Sentiment Triplet Extraction (ASTE) has emerged as a pivotal task in sentiment analysis , focusing on extracting the aspect terms along with the corresponding opinion terms and the expressed sentiments. Recently, generative models have achieved significant success in ASTE task. However, existing generative approaches fail to further model the specific relations within the context for ASTE at the encoding phase, making it difficult to establish the nuanced connections between aspect and opinion terms. Additionally, these approaches rely on simple structured templates at the decoding phase to pair aspect terms with opinion terms, which fails to provide effective relation information for the decoding process. To address the aforementioned issues, we propose ReHyGen, a novel relational hypergraph enhanced framework designed to enhance the relational modeling capabilities of generative ASTE models during both the encoding and decoding phases. Specifically, ReHyGen comprises two core components: the Relational Hypergraph Enhanced Module (RHEM) and the Relational Prompt Module (RPM). RHEM leverages the hypergraph attention network and auxiliary relation classification to capture high-order word interactions and boundary-sensitive word pair relations. RPM incorporates relational information into the decoding phase by providing relation-aware prompts, guiding the generation of more accurate target sequences. Extensive experiments on benchmark datasets demonstrate that our proposed framework significantly improve the performance of generative ASTE models.

Federated learning (FL) is a distributed learning paradigm that maximizes the potential of data-driven models for edge devices without sharing their raw data. However, devices often have non-independent and identically distributed ( non-IID) data, meaning their local data distributions can vary significantly. The heterogeneity in input data distributions across devices, commonly referred to as the feature shift problem, can adversely impact the training convergence and accuracy of the global model. To analyze the intrinsic causes of the feature shift problem, we develop a generalization error bound in FL, which motivates us to propose FedCiR, a client-invariant representation learning framework that enables clients to extract informative and client-invariant features. Specifically, we improve the mutual information term between representations and labels to encourage representations to carry essential classification knowledge, and diminish the mutual information term between the client set and representations conditioned on labels to promote representations of clients to be client-invariant. We further incorporate two regularizers into the FL framework to bound the mutual information terms with an approximate global representation distribution to compensate for the absence of the ground-truth global representation distribution, thus achieving informative and client-invariant feature extraction. To achieve global representation distribution approximation, we propose a data-free mechanism performed by the server without compromising privacy. Extensive experiments demonstrate the effectiveness of our approach in achieving client-invariant representation learning and solving the data heterogeneity issue.

Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL yields a superior global model, even when client models are trained with non-convex objective functions and on heterogeneous local datasets. However, the rationale behind its success remains poorly understood. To shed light on this issue, we first visualize the loss landscape of FL over client and global models to illustrate their geometric properties. The visualization shows that the client models encompass the global model within a common basin, and interestingly, the global model may deviate from the basin's center while still outperforming the client models. To gain further insights into model averaging in FL, we decompose the expected loss of the global model into five factors related to the client models. Specifically, our analysis reveals that the global model loss after early training mainly arises fromi)the client model's loss on non-overlapping data between client datasets and the global dataset andii)the maximum distance between the global and client models. Based on the findings from our loss landscape visualization and loss decomposition, we propose utilizing iterative moving averaging (IMA) on the global model at the late training phase to reduce its deviation from the expected minimum, while constraining client exploration to limit the maximum distance between the global and client models. Our experiments demonstrate that incorporating IMA into existing FL methods significantly improves their accuracy and training speed on various heterogeneous data setups of benchmark datasets. Code is available athttps://github.com/TailinZhou/FedIMA.

Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model updates. To improve communication efficiency, over-the-air computation (AirComp) has been applied to FL, which leverages analog modulation to harness the superposition property of radio waves such that numerous devices can upload their model updates concurrently for aggregation. However, the uplink channel noise incurs considerable model aggregation distortion, which is critically determined by the device scheduling and compromises the learned model performance. In this paper, we propose a probabilistic device scheduling framework for over-the-air FL, namedPO-FL, to mitigate the negative impact of channel noise, where each device is scheduled according to a certain probability and its model update is reweighted using this probability in aggregation. We prove the unbiasedness of this aggregation scheme and demonstrate the convergence of PO-FL on both convex and non-convex loss functions. Our convergence bounds unveil that the device scheduling affects the learning performance through thecommunication distortionandglobal update variance. Based on the convergence analysis, we further develop a channel and gradient-importance aware algorithm to optimize the device scheduling probabilities in PO-FL. Extensive simulation results show that the proposed PO-FL framework with channel and gradient-importance awareness achieves faster convergence and produces better models than baseline methods.

Future wireless networks are expected to support diverse mobile services, including artificial intelligence (AI) services and ubiquitous data transmissions. Federated learning (FL), as a revolutionary learning approach, enables collaborative AI model training across distributed mobile edge devices. By exploiting the superposition property of multiple-access channels, over-the-air computation allows concurrent model uploading from massive devices over the same radio resources, and thus significantly reduces the communication cost of FL. In this paper, we study the coexistence of over-the-air FL and traditional information transfer (IT) in a mobile edge network, where an access point (AP) coordinates a set of devices for over-the-air FL and serves multiple devices for information transfer in the meantime. We propose a coexisting federated learning and information transfer (CFLIT) communication framework, where the FL and IT devices share the wireless spectrum in an orthogonal frequency division multiplexing (OFDM) system. Under this framework, we aim to maximize the IT data rate and guarantee a given FL convergence performance by optimizing the long-term radio resource allocation. A key challenge that limits the spectrum efficiency of the coexisting system lies in the large overhead incurred by frequent communication between the server and edge devices for FL model aggregation. To address the challenge, we rigorously analyze the impact of the computation-to-communication ratio on the convergence of over-the-air FL in wireless fading channels. The analysis reveals the existence of an optimal computation-to-communication ratio that minimizes the amount of radio resources needed for over-the-air FL to converge to a given error tolerance. Based on the analysis, we propose a low-complexity online algorithm to jointly optimize the radio resource allocation for both the FL devices and IT devices. We further derive an analytical expression of the achievable data rate of IT users. Extensive numerical simulations verify the superior performance of the proposed design for the coexistence of FL and IT devices in wireless cellular systems.

Federated learning (FL) has recently emerged as a promising technology to enable artificial intelligence (AI) at the network edge, where distributed mobile devices collaboratively train a shared AI model under the coordination of an edge server. To significantly improve the communication efficiency of FL, over-the-air computation allows a large number of mobile devices to concurrently upload their local models by exploiting the superposition property of wireless multi-access channels. Due to wireless channel fading, the model aggregation error at the edge server is dominated by the weakest channel among all devices, causing severe straggler issues. In this paper, we propose a relay-assisted cooperative FL scheme to effectively address the straggler issue. In particular, we deploy multiple half-duplex relays to cooperatively assist the devices in uploading the local model updates to the edge server. The nature of the over-the-air computation poses system objectives and constraints that are distinct from those in traditional relay communication systems. Moreover, the strong coupling between the design variables renders the optimization of such a system challenging. To tackle the issue, we propose an alternating-optimization-based algorithm to optimize the transceiver and relay operation with low complexity. Then, we analyze the model aggregation error in a single-relay case and show that our relay-assisted scheme achieves a smaller error than the one without relays provided that the relay transmit power and the relay channel gains are sufficiently large. The analysis provides critical insights on relay deployment in the implementation of cooperative FL. Extensive numerical results show that our design achieves faster convergence compared with state-of-the-art schemes.

Leveraging recent advances on mobile edge computing (MEC), edge intelligence has emerged as a promising paradigm to support mobile artificial intelligence (AI) applications at the network edge. In this paper, we consider the AI service placement problem in a multi-user MEC system, where the access point (AP) places the most up-to-date AI program at user devices to enable local computing/task execution at the user side. To fully utilize the stringent wireless spectrum and edge computing resources, the AP sends the AI service program to a user only when enabling local computing at the user yields a better system performance. We formulate a mixed-integer non-linear programming (MINLP) problem to minimize the total computation time and energy consumption of all users by jointly optimizing the service placement (i.e., which users to receive the program) and resource allocation (on local CPU frequencies, uplink bandwidth, and edge CPU frequency). To tackle the MINLP problem, we derive analytical expressions to calculate the optimal resource allocation decisions with low complexity. This allows us to efficiently obtain the optimal service placement solution by search-based algorithms such as meta-heuristic or greedy search algorithms. To enhance the algorithm scalability in large-sized networks, we further propose an ADMM (alternating direction method of multipliers) based method to decompose the optimization problem into parallel tractable MINLP subproblems. The ADMM method eliminates the need of searching in a high-dimensional space for service placement decisions and thus has a low computational complexity that grows linearly with the number of users. Simulation results show that the proposed algorithms perform extremely close to the optimum and significantly outperform the other representative benchmark algorithms.

In this paper, we consider the service placement problem in a multi-user MEC system, where the access point (AP) places the most up-to-date artificial intelligent (AI) program at user devices via a broadcast channel. In particular, a user that successfully receives the program can execute its tasks both locally and remotely at the AP via partial task offloading. Otherwise, all its computations must be offloaded to and executed at the AP. We formulate a mixed-integer non-linear programming (MINLP) problem to minimize the total computation time and energy consumption of all users. The problem is particularly challenging because the service placement solution (i.e., which users to receive the program) is combinatorial in nature and strongly coupled with the computation offloading decision of each user (how much task to be executed at the AP) and resource allocation (on local CPU frequencies and uplink bandwidth). We tackle the problem with an ADMM (alternating direction method of multipliers) based method that effectively decomposes the problem into parallel smaller and tractable MINLP subproblems. Simulation results show that the proposed method achieves a performance extremely close to the optimum and has a low computational complexity that grows linearly with the number of users.

This paper studies joint uplink (UL) and downlink (DL) resource allocation in an orthogonal frequency-division multiple-access (OFDMA) based cloud radio access network (CRAN), where the distributed remote radio heads (RRHs) cooperatively serve the users' UL and DL transmission over different subcarriers (SCs). We aim to maximize the system throughput through jointly optimizing UL/DL scheduling, SC assignment, RRH selection and power allocation under the maximum power and fronthaul capacity constraints. We formulate the problem as a mixed integer programming problem which is nonconvex and NP-hard. We propose an optimal algorithm based on the Lagrange duality method to solve this problem. We also propose a suboptimal algorithm to further reduce the complexity. Simulation results illustrate that the proposed algorithms can considerably improve the system throughput compared to other benchmark schemes.

This paper studies resource allocation in a user- centric cloud radio access network (CRAN), where remote radio heads (RRHs) communicate with users using orthogonal frequency-division multiple-access (OFDMA). We aim to maximize the system throughput through joint RRH selection and SC allocation under fronthaul capacity constraints. We formulate the problem as a non-convex problem which is NP-hard. To solve this complex problem efficiently, we propose a near-optimal algorithm based on gradient method to achieve a suboptimal solution. Simulation results show that the proposed joint resource allocation scheme can attain significant throughput gains compared to other benchmark schemes.