Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity of opinions across sub-populations, inadvertently favoring dominant groups. The state-of-the-art, MaxMin-RLHF, addresses this by learning group-specific reward models, and by optimizing for the group receiving the minimum reward, thereby promoting fairness. However, we identify that a key limitation of MaxMin-RLHF is its poor performance when the minimum-reward group is a minority. To mitigate this drawback, we introduce a novel framework, termed *SharedRep-RLHF*. At its core, SharedRep-RLHF learns and leverages *shared preference traits* in annotations among various groups, in contrast to learning separate reward models across groups. We first show that MaxMin-RLHF is provably suboptimal in learning shared traits, and then quantify the sample complexity of SharedRep RLHF. Experiments across diverse natural language tasks showcase the effectiveness of ShareRep-RLHF compared to MaxMin-RLHF with a gain of up to 20% in win rate.

Autonomous driving is a major paradigm shift in transportation, with the potential to enhance safety, optimize traffic congestion, and reduce fuel consumption. Although autonomous vehicles rely on advanced sensors and on-board computing systems to navigate without human control, full awareness of the driving environment also requires a cooperative effort via Vehicle-to-Everything (V2X) communication. Specifically, vehicles send and receive sensor observations to/from other vehicles to extend perception beyond their own sensing range. However, transmitting large volumes of data can be challenging for current V2X communication technologies, so data compression represents a crucial solution to reduce the message size and link congestion. In this paper, we present a statistical characterization of automotive data, focusing on Light Detection and Ranging (LiDAR) sensors. Notably, we provide models for the size of both raw and compressed point clouds. The use of statistical traffic models offers several advantages compared to using real data, such as faster simulations, reduced storage requirements, and greater flexibility in the application design. Furthermore, statistical models can be used for understanding traffic patterns and analyzing statistics, which is crucial to design and optimize wireless networks. We validate our statistical models via a Kolmogorov-Smirnoff (KS) test implementing a Bootstrap Resampling scheme. Moreover, we show via ns-3 simulations that using statistical models yields results in terms of latency and throughput that are comparable to real data, which also demonstrates the accuracy of the models.

Data integrity becomes paramount as the number of Internet of Things (ioT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities can prevent disruptions and data bias in the state of an IoT application. This paper presents LE3D, an ensemble framework of data drift estimators capable of detecting abnormal sensor behaviours. Working collaboratively with surrounding ioT devices, the type of drift (natural/abnormal) can also be identified and reported to the end-user. The proposed framework is a lightweight and unsupervised implementation able to run on resource-constrained IoT devices. Our framework is also generalisable, adapting to new sensor streams and environments with minimal online reconfiguration. We compare our method against state-of-the-art ensemble data drift detection frameworks, evaluating both the real-world detection accuracy as well as the resource utilisation of the implementation. Experimenting with real-world data and emulated drifts, we show the effectiveness of our method, which achieves up to 97% of detection accuracy while requiring minimal resources to run.

In a fully autonomous driving framework, where vehicles operate without human intervention, information sharing plays a fundamental role. In this context, new network solutions have to be designed to handle the large volumes of data generated by the rich sensor suite of the cars in a reliable and efficient way. Among all the possible sensors, Light Detection and Ranging (LiDAR) can produce an accurate 3D point cloud representation of the surrounding environment, which in turn generates high data rates. For this reason, efficient point cloud compression is paramount to alleviate the burden of data transmission over bandwidth-constrained channels and to facilitate real-time communications. In this paper, we propose a pipeline to efficiently compress LiDAR observations in an automotive scenario. First, we leverage the capabilities of RangeNet++, a Deep Neural Network (DNN) used to semantically infer point labels, to reduce the channel load by selecting the most valuable environmental data to be disseminated. Second, we compress the selected points using Draco, a 3D compression algorithm which is able to obtain compression up to the quantization error. Our experiments, validated on the Semantic KITTI dataset, demonstrate that it is possible to compress and send the information at the frame rate of the LiDAR, thus achieving real-time performance.