While essential for stateful modern workloads like Large Language Model agents and IoT services, long-lived connections impede cloud infrastructure agility by complicating maintenance and load balancing. Existing connection migration solutions either lack support for industrial-grade encrypted traffic or fail to prevent packet loss during handover in active production environments. To address this gap, we propose Zephyr, a zero-loss and transparent TLS connection migration framework for cross-node migration between servers with different addresses. Zephyr ensures transport-layer consistency by orchestrating an eBPF-based packet buffering mechanism to safely intercept in-flight data. At the application layer, rather than deeply modifying standard TLS libraries, Zephyr creatively reuses the native session resumption mechanism via a “fake client” strategy to reconstruct complex cryptographic states without client involvement. Implemented in widely-used industrial stacks (Nginx and OpenSSL), Zephyr achieves connection migration with approximately 4.1 ms downtime and strict zero packet loss. This approach enables seamless infrastructure optimization without disrupting cloud services.

Accurate origin-destination (OD) passenger flow prediction is crucial for enhancing metro system efficiency, optimizing scheduling, and improving passenger experiences. However, current models often fail to effectively capture the asynchronous departure characteristics of OD flows and underutilize the inflow and outflow data, which limits their prediction accuracy. To address these issues, we propose CSP-AIT-Net, a novel spatiotemporal graph attention framework designed to enhance OD flow prediction by incorporating asynchronous inflow tracking and advanced station semantics representation. Our framework restructures the OD flow prediction paradigm by first predicting outflows and then decomposing OD flows using a spatiotemporal graph attention mechanism. To enhance computational efficiency, we introduce a masking mechanism and propose asynchronous passenger flow graphs that integrate inflow and OD flow with conservation constraints. Furthermore, we employ contrastive learning to extract high-dimensional land use semantics of metro stations, enriching the contextual understanding of passenger mobility patterns. Validation of the Shanghai metro system demonstrates improvement in short-term OD flow prediction accuracy over state-of-the-art methods. This work contributes to enhancing metro operational efficiency, scheduling precision and safety.

Point cloud reconstruction is an ingredient in geometry modeling, computer graphics, and 3D vision. In this paper, we propose a novel unsupervised learning method called the Recurrent Multi-Step Moving Strategy, which progressively moves query points toward the underlying surface to accurately learn unsigned distance fields (UDFs) for point cloud reconstruction. Specifically, we design a recurrent network for UDF estimation that integrates a multi-step strategy for query movement. This model treats query movement as a trajectory prediction process, establishing dependencies between the current query move decision and the previous path, thus utilizing temporal information to improve UDF estimation accuracy. Further, we design distance and gradient regularization losses to ensure the precision, consistency, and continuity of the estimated UDFs. Extensive evaluations, comparisons, and ablation studies are conducted to show the superiority of our method over the competing approaches in terms of reconstruction accuracy and generality. Our unsupervised reconstruction method outperforms many supervised techniques and demonstrates efficacy across diverse scenarios, including single-object, indoor, and outdoor benchmarks.

Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently witnessed excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) fail to simultaneously handle the problems of missing attributes, inaccurate attributes and scarce node labels, which limits their expressiveness. In this paper, we propose a generative self-supervised model GraMI to address these issues simultaneously. Specifically, GraMI first initializes all the nodes in the graph with a low-dimensional representation matrix. After that, based on the variational graph autoencoder framework, GraMI learns both node-level and attribute-level embeddings in the encoder, which can provide fine-grained semantic information to construct node attributes. In the decoder, GraMI reconstructs both links and attributes. Instead of directly reconstructing raw features for attributed nodes, GraMI generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed. In this way, GraMI can not only complete informative features for non-attributed nodes, but rectify inaccurate ones for attributed nodes. Finally, we conduct extensive experiments to show the superiority of GraMI in tackling HINs with missing and inaccurate attributes. Our code and data can be found here: https://github.com/See-r/GraMI.

Graph neural networks (GNNs) have recently demonstrated significant success. Active learning for GNNs aims to query the valuable samples from the unlabeled data for annotation to maximize the GNNs' performance at a low cost. However, most existing methods for reinforced active learning in GNNs may lead to a highly imbalanced class distribution, especially in highly skewed class scenarios. This further adversely affects the classification performance. To tackle this issue, in this paper, we propose a novel reinforced class-balanced active learning framework for GNNs, namely, GraphCBAL. It learns an optimal policy to acquire class-balanced and informative nodes for annotation, maximizing the performance of GNNs trained with selected labeled nodes. GraphCBAL designs class-balance-aware states, as well as a reward function that achieves trade-off between model performance and class balance. We further upgrade GraphCBAL to GraphCBAL++ by introducing a punishment mechanism to obtain a more class-balanced labeled set. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed approaches, achieving superior performance over state-of-the-art baselines. In particular, our methods can strike the balance between classification results and class balance. We provide our code and data at https://github.com/cici-chengcheng/GraphCBAL.

With the rapid development of deep learning, the convolutional neural networks (CNNs) have been widely used in hyperspectral image classification (HSIC) and achieved excellent performance. However, CNNs reuse the same kernel weights over different locations, resulting in the insufficient capability of capturing diversity spatial interactions. Moreover, CNNs usually require a large amount of training samples to optimize the learnable parameters. When training samples are limited, the classification performance of CNN tends to drop off a cliff. To tackle the aforementioned issues, a novel residual spatial attention kernel generation network (RSAKGN) is proposed for HSIC. First, a spatial attention kernel generation module (SAKGM) is built to extract discriminative semantic features, which can dynamically calculate the attention weights to generate specific spatial attention kernels over different locations. Then, we combine the SAKGM with residual learning framework by embedding the SAKGM into a bottleneck residual block to obtain the residual spatial attention block (RSAB). The RSAKGN is constructed by stacking several RSABs. Experimental results on three public HSI datasets demonstrate that the proposed RSAKGN method outperforms several state-of-the-arts with small sample size.

This paper presents a unified grammatical framework capable of reconstructing a variety of scene types (e.g., urban, campus, county etc.) from a single input image. The key idea of our approach is to study a novel commonsense reasoning framework that mainly exploits two types of prior knowledges: (i) prior distributions over a single dimension of objects, e.g., that the length of a sedan is about 4.5 meters; (ii) pair-wise relationships between the dimensions of scene entities, e.g., that the length of a sedan is shorter than a bus. These unary or relative geometric knowledge, once extracted, are fairly stable across different types of natural scenes, and are informative for enhancing the understanding of various scenes in both 2D images and 3D world. Methodologically, we propose to construct a hierarchical graph representation as a unified representation of the input image and related geometric knowledge. We formulate these objectives with a unified probabilistic formula and develop a data-driven Monte Carlo method to infer the optimal solution with both bottom-to-up and top-down computations. Results with comparisons on public datasets showed that our method clearly outperforms the alternative methods.

A framework of synthetic data generator to generate social media timeline structures is proposed in this paper, which is useful for benchmarking query processing over social media data, and validating hypothesis over users' behavior. It is flexible to generate synthetic data with different distributions. With the help of its asynchronized parallel processing model and delayed update strategy, it is efficient to feed out timeline structure with high throughput. We show in experiments that our method can generate realistic social media timeline structures efficiently.

The demonstration of a benchmark, named as BSMA, for Benchmarking Social Media Analytics, is introduced in this paper. BSMA is designed to benchmark data management systems supporting analytical queries over social media. It is different to existing benchmarks in that: 1) Both real-life data and a synthetic data generator are provided. The real-life dataset contains a social network of 1.6 million users, and all their tweeting and retweeting activities. The data generator can generate both social networks and synthetic timelines that follow data distributions determined by predefined parameters. 2) A set of workloads are provided. The data generator is in responsible for producing updates. A workload generator produces queries based on predefined query templates by generating query arguments online. BSMA workloads cover a large amount of queries with graph operations, temporal queries, hotspot queries, and aggregate queries. Furthermore, the argument generator is capable of sampling data items in the timeline following power-law distribution online. 3) A toolkit is provided to measure and report the performance of systems that implement the benchmark. Furthermore, a prototype system based on dataset and workloads of BSMA is also implemented. The demonstration will include two parts, i.e. the internals of data and workload generator, as well as the performance testing of reference implementations.