Cooperative localization between vehicles and infrastructure is pivotal in overcoming bottlenecks of localization accuracy with respect to multipath and non-line-of-sight (NLOS) effects for urban operations. Within the vehicle-to-infrastructure (V2I) principle and intelligent transport system (ITS), roadside sensors are capable of providing additional measurement to enhance a vehicle's localization performance. This paper introduces a cooperative localization framework that uses infrastructure cameras from roadside unit (RSU) to aid in minimizing positioning errors for ego vehicles (EV s). Positions extracted from RSU cameras are loosely fused with local Global Navigation Satellite System (GNSS) information along with inertial measurement unit (IMU) readings using extended Kalman filter (EKF). To compensate for localization errors, Long Short-Term Memory (LSTM) is applied to augment fusion accuracy by learning geographic positioning error distributions with ground truth from the training dataset. By demonstrating the framework over CARLA, the experimental results indicate that under normal GNSS conditions, the LSTM-based fusion method reduces the RMSE of the position error by 38% compared to the EKF. After introducing GNSS bias and considering GNSS outage, the RMSE of the position error is reduced by 31 % and 30%, respectively.

Fraud detection on multi-relation graphs aims to identify fraudsters in graphs. Graph Neural Network (GNN) models leverage graph structures to pass messages from neighbors to the target nodes, thereby enriching the representations of those target nodes. However, feature and structural inconsistency in the graph, owing to fraudsters' camouflage behaviors, diminish the suspiciousness of fraud nodes which hinders the effectiveness of GNN-based models. In this work, we propose DiG-In-GNN, Discriminative Feature Guided GNN against Inconsistency, to dig into graphs for fraudsters. Specifically, we use multi-scale contrastive learning from the perspective of the neighborhood subgraph where the target node is located to generate guidance nodes to cope with the feature inconsistency. Then, guided by the guidance nodes, we conduct fine-grained neighbor selection through reinforcement learning for each neighbor node to precisely filter nodes that can enhance the message passing and therefore alleviate structural inconsistency. Finally, the two modules are integrated together to obtain discriminable representations of the nodes. Experiments on three fraud detection datasets demonstrate the superiority of the proposed method DiG-In-GNN, which obtains up to 20.73% improvement over previous state-of-the-art methods. Our code can be found at https://github.com/GraphBerry/DiG-In-GNN.

Deep Neural Network (DNN) training on a large scale is extremely time-consuming and computationally intensive, which is accelerated by distributed training. In recent years, pipeline parallelism has been developed, which enables partitioning the model across several devices, e.g. GPU, and training efficiency is improved by dividing data batches into micro-batches, with each of them processed by a different stage of the model. Currently, parallel training assumes pipeline placement and partitioning are static, with parameters updating each iteration, without accounting for freezing. This results in computational resources not being fully utilized. In this paper, we propose FreezePipe, a novel method for optimizing deep learning training that combines the freezing mechanism with pipeline parallel training. In FreezePipe, a lightweight method for determining the freezing strategy based on gradient changes is employed. Considering that resources need to be released based on the frozen layer, a lightweight model partitioning algorithm was designed to determine the optimal strategy for pipeline partitioning. Experimental results show that FreezePipe can reduce the training time by 64.5% compared to Torchgpipe on CIFAR-10 dataset without compromising any model performance.