Lane change prediction, encompassing both intention recognition and trajectory forecasting, is essential for the safe operation of autonomous vehicles in mixed-traffic environments. Existing models predominantly follow a data-driven paradigm, learning directly from historical vehicle states through an end-to-end approach. Inspired by the emerging paradigm of enhancing model generalizability through domain knowledge, we propose KnowLCP to explicitly model and integrate driving knowledge into the lane change prediction task. Specifically, we incorporate three types of knowledge: traffic risk awareness to improve intention prediction, vehicle kinematics to ensure the physical feasibility of predicted trajectories, and intention intensity to refine trajectory forecasting. Furthermore, we introduce a novel knowledge injection strategy that enhances mutual information during integration and proves superior to the traditional parallel input mechanism, which simply feeds knowledge features alongside historical states. Extensive experiments on two real-world trajectory datasets demonstrate that KnowLCP achieves average improvements of 8.3-10.3% in intention prediction and 10.1-10.3% in trajectory prediction over the best-performing baselines.

The rapid development of the Internet of Medical Things (IoMT) enables automatic recording of surgical reports via interconnected medical devices. However, the reliability of these data is often compromised by missing data, frequently stemming from intermittent IoT communication issues like network disruptions or device malfunctions. This incomplete data critically hinders downstream medical applications and violates implicit network intents related to data integrity and timeliness within an Intent-based Networking (IBN), essential for supporting proactive resource allocation in operating rooms and optimized surgical scheduling. While existing studies focus on addressing missing event types, event time imputation remains a significant, underexplored challenge due to the need to capture implicit temporal contexts and complex cross surgical procedures dependencies. To tackle this for IoMT, we propose a novel Surgical event time IMputation in Intent-Based Networking(SIM-IBN) model. SIM-IBN employs continuous-time LSTMs with attention mechanisms to learn intra-and inter-sequence correlations, effectively recovering missing timestamps. By enhancing data reliability at the source, SIM-IBN serves as a crucial component enabling IBN systems to better fulfill intents for dependable IoMT operations. Rigorous evaluation on real-world surgical event datasets demonstrates SIM-IBN’s superiority over state-of-the-art baselines by up to 11.88% across various missing data scenarios, validating its potential to enable more reliable IoMT systems and enhance operational efficiency in smart healthcare environments.

Vehicle trajectory prediction (VTP) is a prominent research topic in autonomous vehicles (AVs). However, existing studies concentrate on improving prediction accuracy, overlooking how VTP accuracy influences the effectiveness of downstream tasks such as collision avoidance. In this paper, we investigate the relationship between VTP accuracy and key performance indicators (KPIs) of cooperative collision avoidance systems (CCAS) for connected AVs operating at blind intersections. To this end, we propose a generalized error model (GEM) that enables the generation of customizable VTP errors. GEM is integrated into an error injection framework to produce diverse, error-controlled trajectories in real time. Our experiments quantitatively characterize the relationship among VTP accuracy, warning thresholds and strategies, and CCAS KPIs. The results reveal a common pattern: as VTP error increases, CCAS recall improves while precision declines, demonstrating a negative correlation that is difficult to balance. This underscores the need for effective trade-offs between recall and precision in CCAS design. With a general collision warning strategy, CCAS can preemptively report over 90% of collisions, substantially enhancing traffic safety, though at the expense of a reduced precision. To mitigate this, we devise a density-based warning strategy (DCWS) that improves precision across the entire VTP accuracy space while maintaining recall at acceptable levels. Notably, DCWS gradually decouples CCAS KPIs from VTP accuracy performance, highlighting the crucial role of warning strategies. The quantitative results presented in this paper can help practitioners assess the impact of their VTP models on CCAS and select appropriate warning thresholds.

The rapid spread of diverse information on online social platforms has prompted both academia and industry to realize the importance of predicting content popularity, which could benefit a wide range of applications, such as recommendation systems and strategic decision-making. Recent works mainly focused on extracting spatiotemporal patterns inherent in the information diffusion process within a given observation period so as to predict its popularity over a future period of time. However, these works often overlook the future popularity trend, as future popularity could either increase exponentially or stagnate, introducing uncertainties to the prediction performance. Additionally, how to transfer the preceding-term dynamics learned from the observed diffusion process into future-term trends remains an unexplored challenge. Against this background, we propose CasFT, which leverages observed information Cascades and dynamic cues extracted via neural ODEs as conditions to guide the generation of Future popularity-increasing Trends through a diffusion model. These generated trends are then combined with the spatiotemporal patterns in the observed information cascade to make the final popularity prediction. Extensive experiments conducted on three real-world datasets demonstrate that CasFT significantly improves the prediction accuracy compared to state-of-the-art approaches.

As artificial intelligence techniques evolve, we are approaching a critical moment for the widespread deployment of autonomous vehicles. Subsequently, the emergence of mixed-autonomy traffic environments presents formidable challenges to autonomous vehicles, especially for the accurate prediction of lane change intentions of their surrounding human-driven vehicles, which is crucial for ensuring the safety of autonomous vehicles. Existing lane change prediction models mainly focus on capturing the temporal variations in the movement dynamics of individual vehicles. However, the neglect to consider inter-vehicle interactions hinders their capability in complex lane change scenarios, resulting in suboptimal prediction performance. Moreover, current interaction-aware approaches for autonomous driving fail to explicitly model future interactions between vehicles, leading to unreasonable prediction results that can cause collisions between vehicles. To address the above issues, we propose to incorporate the concept of perceived safety into future interaction modeling and design a dual-view interaction-aware lane change prediction model. We evaluate the proposed model on two real-world datasets and experimental results show that the proposed model achieves average improvements of 11.7-12.4% in classification ability and 75.6-95.7% in forecast ability over the best-performing baselines across the two datasets. The ablation study and investigation into future interaction modeling demonstrate that our model has advantages in interpreting lane change scenarios from a driving safety perspective.

With the ubiquity of hyper-relational facts in modern Knowledge Graphs (KGs), existing link prediction techniques mostly focus on learning the sophisticated relationships among multiple entities and relations contained in a fact, while ignoring the multimodal information, which often provides additional clues to boost link prediction performance.Nevertheless, traditional multimodal fusion approaches, which are mainly designed for triple facts under either entity-centric or relation-guided fusion schemes, fail to integrate the multimodal information with the rich context of the hyperrelational fact consisting of multiple entities and relations.Against this background, we propose HyperFM, a Hyper-relational Factcentric Multimodal Fusion technique.It effectively captures the intricate interactions between different data modalities while accommodating the hyper-relational structure of the KG in a fact-centric manner via a customized Hypergraph Transformer.We evaluate Hy-perFM against a sizeable collection of baselines in link prediction tasks on two real-world KG datasets.The results show that HyperFM consistently achieves the best performance, yielding an average improvement of 6.0-6.8% over the best-performing baselines on the two datasets.Moreover, a series of ablation studies systematically validate our fact-centric fusion scheme.

In mixed-autonomy traffic environments, accurately predicting the lane change behavior of human-driven vehicles is critical for ensuring the safety and reliability of autonomous vehicle decision-making. However, existing approaches face two major challenges: 1) they tend to represent the relationships between the target vehicle and surrounding vehicles using parameters like relative position and speed. This approach either requires a fixed number of surrounding vehicles or introduces significant noise by relying on virtual vehicles; and 2) they often fail to fully exploit the vast amount of available vehicle trajectory data, leaving the complexities of vehicular interactions underexplored. To address these issues, this paper presents a novel lane change prediction framework using Transformer-based transfer learning. Our design aims to leverage inter-vehicle interactions learned from trajectory data to improve lane-change prediction accuracy. Specifically, pre-trained trajectory prediction models are used to adapt dynamically to the varying number of surrounding vehicles and to capture interaction context from large sets of trajectory data. We then refine the Transformer model to integrate this context and predict the target vehicle’s lane change intentions. The Transformer encoder transforms trajectory interaction context into a lane-change-oriented context using aggregated multi-head attention. The Transformer decoder, in turn, utilizes this context alongside the target vehicle’s states through relation-aware multi-head attention to forecast lane change behavior. Extensive experiments on two real-world datasets demonstrate that our proposed framework outperforms state-of-the-art baselines in both accuracy and robustness.

Ensuring the smooth operation of road traffic is a momentous target in Intelligent Transportation Systems, which can be expedited by a secure and reliable Internet of Vehicles (IoV). As prominent carriers of the IoV, intelligent vehicles (IVs), that bear the promising potential for alleviating traffic congestion, have become the core road traffic participants. However, the mixed-traffic environment escalates the risk of IVs, as the discretionary lane change behaviors of nearby human-driven vehicles may result in collisions with IVs, compromising the robust performance of the IoV. Recent studies have utilized advanced deep learning techniques to achieve proactive lane change intention prediction, including Recurrent Neural Networks and Transformer. Although attaining reasonable prediction performance, they adopt the data-driven paradigm, which excessively focuses on learning from data while neglecting the domain knowledge. Against this background, we propose to employ the knowledge-driven paradigm and design KLEP, a knowledge-driven lane change prediction framework. KLEP incorporates driving knowledge into lane change modeling, presenting the top-down hierarchical cognitive process of drivers when performing lane change maneuvers. Extensive experiments conducted on two real-world natural driving datasets demonstrate the effectiveness of KLEP. Compared to state-of-the-art lane change prediction baselines, KLEP consistently outperforms them and achieves average improvements of 6.2-7.1% and 53.0-67.2% on intention classification and intention forecast tasks across different datasets, respectively. We also validate that KLEP has strong interpretability that aligns with real-world physical laws in lane change scenarios and is lightweight enough to fulfill online prediction.

Information popularity prediction is important yet challenging in various domains, including viral marketing and news recommendations. The key to accurately predicting information popularity lies in subtly modeling the underlying temporal information diffusion process behind observed events of an information cascade, such as the retweets of a tweet. To this end, most existing methods either adopt recurrent networks to capture the temporal dynamics from the first to the last observed event or develop a statistical model based on self-exciting point processes to make predictions. However, information diffusion is intrinsically a complex continuous-time process with irregularly observed discrete events, which is oversimplified using recurrent networks as they fail to capture the irregular time intervals between events, or using self-exciting point processes as they lack flexibility to capture the complex diffusion process. Against this background, we propose ConCat, modeling theContinuous-time dynamics ofCascades for information popularity prediction. On the one hand, it leverages neural Ordinary Differential Equations (ODEs) to model irregular events of a cascade in continuous time based on the cascade graph and sequential event information. On the other hand, it considers cascade events as neural temporal point processes (TPPs) parameterized by a conditional intensity function which can also benefit the popularity prediction task. We conduct extensive experiments to evaluate ConCat on three real-world datasets. Results show that ConCat achieves superior performance compared to state-of-the-art baselines, yielding 2.3%-33.2% improvement over the best-performing baselines across the three datasets.

Most existing research on vehicle re-identification (Re-ID) focuses on supervised methods, while unsupervised methods that can take advantage of massive unlabeled data are underexplored. Due to the similarity of tasks, unsupervised person Re-ID methods that employ clustering to generate pseudo labels for model training can achieve good performance on unsupervised vehicle Re-ID task. However, vehicle exhibit higher intra-ID compactness and inter-ID separability within camera than person, which has not been exploited to reduce pseudo label noise for unsupervised vehicle Re-ID. To address this issue, we propose a camera-aware differentiated clustering with focal contrastive learning (CDF) method for unsupervised vehicle Re-ID task. Unlike the conventional global clustering approach that adopts a uniform processing strategy for pseudo-label generation, a camera-aware differentiated clustering (CDC) approach is designed to reduce label noise. In CDC, the entire clustering process is divided into two stages: inter-camera and intra-camera clustering, and each stage adopts different clustering strategies that are carefully designed according to the differences in feature distribution within and across cameras. By considering the distribution of pseudo labels generated by CDC, a measure for calculating the reliability of inter-camera and intra-camera pseudo labels is further designed, and a focal contrastive learning loss is proposed to improve the model’s ID discrimination ability within and across cameras. Extensive experiments on VeRi-776 and VERI-Wild demonstrate the effectiveness of each designed component and the superiority of the CDF.

State-of-the-art unsupervised object re-identification (Re-ID) methods conduct model training with pseudo labels generated by clustering techniques. Unfortunately, due to the existence of inter-ID similarity and intra-ID variance problems in vehicle Re-ID, clustering sometimes mixes different similar vehicles together or splits images of the same vehicle in different views into different clusters. To enhance the model’s ID discrimination capability in the presence of such kinds of label noise, we propose an inter-intra cluster reorganization approach (ICR) to reorganize the relationship between instances within and between clusters, which can provide higher-quality contrastive learning guidance based on existing clustering results. In the intra-cluster reorganization, we design a camera-aware maximum reliability sub-cluster organization approach, which reorganizes each cluster into several intersecting sub-clusters of higher quality based on the finer intra-camera clustering results. We further design a novel metric called centroid reliability to measure the reliability of intra-cluster contrastive learning. In the inter-cluster reorganization, we propose an ambiguous cluster discrimination criterion to measure the probability that two clusters belong to the same vehicle. Based on this criterion, we design a focal contrastive loss to adaptively re-organize the contribution of ambiguous clusters in model training to perform better contrastive learning. Extensive experiments on VeRi-776 and VERI-Wild demonstrate that ICR is effective and can achieve state-of-the-art performance.

Knowledge Graph (KG) embeddings have become a powerful paradigm to resolve link prediction tasks for KG completion. The widely adopted triple-based representation, where each triplet$(h,r,t)$links two entities$h$and$t$through a relation$r$, oversimplifies the complex nature of the data stored in a KG, in particular for hyper-relational facts, where each fact contains not only a base triplet$(h,r,t)$, but also the associated key-value pairs$(k,v)$. Even though a few recent techniques tried to learn from such data by transforming a hyper-relational fact into an n-ary representation (i.e., a set of key-value pairs only without triplets), they result in suboptimal models as they are unaware of the triplet structure, which serves as the fundamental data structure in modern KGs and preserves the essential information for link prediction. Moreover, as the KG schema information has been shown to be useful for resolving link prediction tasks, it is thus essential to incorporate the corresponding hyper-relational schema in KG embeddings. Against this background, we propose sHINGE, a schema-aware hyper-relational KG embedding model, which learns from hyper-relational facts directly (without the transformation to the n-ary representation) and their corresponding hyper-relational schema in a KG. Our extensive evaluation shows the superiority of sHINGE on various link prediction tasks over KGs. In particular, compared to a sizeable collection of 21 baselines, sHINGE consistently outperforms the best-performing triple-based KG embedding method, hyper-relational KG embedding method, and schema-aware KG embedding method by 19.1%, 1.8%, and 12.9%, respectively.

Knowledge graph (KG) schema, which prescribes a high-level structure and semantics of a KG, is significantly helpful for KG completion and reasoning problems. Despite its usefulness, open-domain KGs do not practically have a unified and fixed schema. Existing approaches usually extract schema information using entity types from a KG where each entity e can be associated with a set of types {Te, by either heuristically taking one type for each entity or exhaustively combining the types of all entities in a fact (to get entity-typed tuples, (h_type, r, t_type) for example). However, these two approaches either overlook the role of multiple types of a single entity across different facts or introduce non-negligible noise as not all the type combinations actually support the fact, thus failing to capture the sophisticated schema information. Against this background, we study the problem of modeling hyper-relational schema, which is formulated as mixed hyper-relational tuples ({Th}, r, {Tt}, k, {Tv1},...) with two-fold hyper-relations: each type set T may contain multiple types and each schema tuple may contain multiple key-type set pairs (k, Tv). To address this problem, we propose HELIOS, a hyper-relational schema model designed to subtly learn from such hyper-relational schema tuples by capturing not only the correlation between multiple types of a single entity, but also the correlation between types of different entities and relations in a schema tuple. We evaluate HELIOS on three real-world KG datasets in different schema prediction tasks. Results show that HELIOS consistently outperforms state-of-the-art hyper-relational link prediction techniques by 20.0-29.7%, and is also much more robust than baselines in predicting types and relations across different positions in a hyper-relational schema tuple.

The accurate trajectory prediction of surrounding vehicles is crucial for the sustainability and safety of connected and autonomous vehicles under mixed traffic streams in the real world. The task of trajectory prediction is challenging because there are all kinds of factors affecting the motions of vehicles, such as the individual movements, the ambient driving environment especially road conditions, and the interactions with neighboring vehicles. To resolve the above issues, this work proposes a novel Heterogeneous Context-Aware Graph Convolutional Networks following the Encoder-Decoder architecture, which simultaneously extracts the hidden contexts from individual historical trajectories, varying driving scene, and inter-vehicle interactional behaviors. Specifically, the historical vehicle trajectories are fed into Temporal Convolutional Network to capture the individual context. Besides, a 2-Dimensional Convolutional Network with temporal attention is designed for transforming the scene image stream into compressing scene context. Then a Spatio-Temporal Dynamic Graph Convolutional Networks is devised to model the evolving interactional patterns, which incorporates the acquired individual and scene contexts as the representation of the node. Finally, the aforementioned three contexts are combined and fed into the decoder to produce future trajectories. The proposed model is validated on two real-world datasets which contain various driving scenarios. Results demonstrated that the proposed model outperforms state-of-the-art methods in prediction accuracy and achieves immense stability towards different vehicle states.

Destination prediction is crucial for many location based services such as sightseeing places recommendation and targeted advertisements push. Most existing techniques utilize the historical trajectories to predict destinations, but they fail to well describe the spatio-temporal characteristics of trajectories and suffer the trajectory sparsity problem, i.e., the available historical trajectories are hard to cover all probable trajectories. The temporal sensitivity of historical trajectories highlights the sparsity problem even more. In this paper, we address this problem by building a probabilistic generative model to capture the spatio-temporal features of trajectories. We develop an extended Latent Dirichlet Allocation (LDA) model to characterize the generative mechanism of track points in each trajectory. In this model, trajectory, track point of trajectory and destination are regarded as document, word and response respectively. To address the trajectory sparsity problem, each trajectory is expressed by the distribution of trajectory patterns which are the topics discovered from historical trajectories. Then, the most likely destination is predicted through the trajectory patterns. The experiments performed on a real-world taxi trajectory dataset from Guangzhou confirm the advantage of the probabilistic generative model in destination prediction, achieving remarkable accuracy and strong interpretability.