Fine-grained urban flow inference is crucial for urban planning and intelligent transportation systems, enabling precise traffic management and resource allocation. However, the practical deployment of existing methods is hindered by two key challenges: the prohibitive computational cost of over-parameterized models and the suboptimal performance of conventional loss functions on the highly skewed distribution of urban flows. To address these challenges, we propose a unified solution that synergizes architectural efficiency with adaptive optimization. Specifically, we first introduce PLGF, a lightweight yet powerful architecture that employs a Progressive Local-Global Fusion strategy to effectively capture both fine-grained details and global contextual dependencies. Second, we propose DualFocal Loss, a novel function that integrates dual-space supervision with a difficulty-aware focusing mechanism, enabling the model to adaptively concentrate on hard-to-predict regions. Extensive experiments on 4 real-world scenarios validate the effectiveness and scalability of our method. Notably, while achieving state-of-the-art performance, PLGF reduces the model size by up to 97% compared to current high-performing methods. Furthermore, under comparable parameter budgets, our model yields an accuracy improvement of over 10% against strong baselines.

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known as the long-tail problem. This issue leads to reduced serendipity for users and diminished profits for sellers, ultimately harming the overall system. Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity, making them a promising solution to this problem. In this paper, we introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance SRS performance. To bridge the gap between general-purpose LLM and the recommendation domain, we propose a Supervised Contrastive Fine-Tuning (SCFT) approach. This approach includes attribute-level data augmentation and a tailored contrastive loss to make LLM more recommendation-friendly. Additionally, we emphasize the importance of integrating collaborative signals into LLM-generated embeddings, for which we propose Recommendation Adaptation Training (RAT). This further refines the embeddings for optimal use in SRS. The LLMEmb-derived embeddings can be seamlessly integrated with any SRS model, underscoring the practical value. Comprehensive experiments conducted on three real-world datasets demonstrate that LLMEmb significantly outperforms existing methods across multiple SRS models.

As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics, including unpredictable traffic conditions, diverse driver behaviors, and fluctuating supply and demand patterns. These challenges have resulted in travel difficulties for passengers in certain areas, while many drivers in other areas are unable to secure orders, leading to a decline in the overall quality of urban transportation services. To address these issues, this paper introduces GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching. GARLIC utilizes multiview graphs to capture hierarchical traffic states, and learns a dynamic reward function that accounts for individual driving behaviors. The framework further integrates a GPT model trained with a custom loss function to enable high-precision predictions and optimize dispatching policies in real-world scenarios. Experiments conducted on two real-world datasets demonstrate that GARLIC effectively aligns with driver behaviors while reducing the empty load rate of vehicles.

Representation learning of urban spatial-temporal data is fundamental and critical, serving a wide range of intelligent applications. Given that road networks and trajectories are inherently interrelated, their joint representation learning can significantly enhance the accuracy and utility of these applications. However, effectively learning joint representations for these two types of data remains challenging, particularly due to the complexities of interaction modeling and cross-scale optimization. To this end, we propose a unified framework, named UniTR, for joint representation learning of road networks and trajectories. Specifically, we first design a hierarchical propagation mechanism to model the complex many-to-many interactions between road networks and trajectories, thereby generating informative embeddings. Then, a triple-level contrastive optimization module is incorporated to systematically select valid positive and negative samples, further refining the embeddings. Experiments conducted on real-world datasets from two cities clearly demonstrate the effectiveness and superiority of UniTR.

POI representation learning plays a crucial role in handling tasks related to user mobility data. Recent studies have shown that enriching POI representations with multimodal information can significantly enhance their task performance. Previously, the textual information incorporated into POI representations typically involved only POI categories or check-in content, leading to relatively weak textual features in existing methods. In contrast, large language models (LLMs) trained on extensive text data have been found to possess rich textual knowledge. However leveraging such knowledge to enhance POI representation learning presents two key challenges: first, how to extract POI-related knowledge from LLMs effectively, and second, how to integrate the extracted information to enhance POI representations. To address these challenges, we propose POI-Enhancer, a portable framework that leverages LLMs to improve POI representations produced by classic POI learning models. We first design three specialized prompts to extract semantic information from LLMs efficiently. Then, the Dual Feature Alignment module enhances the quality of the extracted information, while the Semantic Feature Fusion module preserves its integrity. The Cross Attention Fusion module then fully adaptively integrates such high-quality information into POI representations and Multi-View Contrastive Learning further injects human-understandable semantic information into these representations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our framework, showing significant improvements across all baseline representations.

Temporal non-stationarity, the phenomenon that time series distributions change over time, poses fundamental challenges to reliable time series forecasting. Intuitively, the complex time series can be decomposed into two factors, i.e., time-invariant and time-varying components, which indicate static and dynamic patterns, respectively. Nonetheless, existing methods often conflate the time-varying and time-invariant components, and jointly learn the combined long-term patterns and short-term fluctuations, leading to suboptimal performance facing distribution shifts. To address this issue, we initiatively propose a lightweight static-dynamic decomposition framework, TimeEmb, for time series forecasting. TimeEmb innovatively separates time series into two complementary components: (1) time-invariant component, captured by a novel global embedding module that learns persistent representations across time series, and (2) time-varying component, processed by an efficient frequency-domain filtering mechanism inspired by full-spectrum analysis in signal processing. Experiments on real-world datasets demonstrate that TimeEmb outperforms state-of-the-art baselines and requires fewer computational resources. We conduct comprehensive quantitative and qualitative analyses to verify the efficacy of static-dynamic disentanglement. This lightweight framework can also improve existing time-series forecasting methods with simple integration. To ease reproducibility, our code is available at https://github.com/showmeon/TimeEmb.

Building a universal trajectory foundation model is a promising solution to address the limitations of existing trajectory modeling approaches, such as task specificity, regional dependency, and data sensitivity. Despite its potential, data preparation, pre-training strategy development, and architectural design present significant challenges in constructing this model. Therefore, we introduce **UniTraj**, a Universal Trajectory foundation model that aims to address these limitations through three key innovations. First, we construct **WorldTrace**, an unprecedented dataset of 2.45 million trajectories with billions of GPS points spanning 70 countries, providing the diverse geographic coverage essential for region-independent modeling. Second, we develop novel pre-training strategies--Adaptive Trajectory Resampling and Self-supervised Trajectory Masking--that enable robust learning from heterogeneous trajectory data with varying sampling rates and quality. Finally, we tailor a flexible model architecture to accommodate a variety of trajectory tasks, effectively capturing complex movement patterns to support broad applicability. Extensive experiments across multiple tasks and real-world datasets demonstrate that UniTraj consistently outperforms existing methods, exhibiting superior scalability, adaptability, and generalization, with WorldTrace serving as an ideal yet non-exclusive training resource. The implementation codes and full dataset are available at https://github.com/Yasoz/UniTraj.

Generating trajectory data is among promising solutions to addressing privacy concerns, collection costs, and proprietary restrictions usually associated with human mobility analyses. However, existing trajectory generation methods are still in their infancy due to the inherent diversity and unpredictability of human activities, grappling with issues such as fidelity, flexibility, and generalizability. To overcome these obstacles, we propose ControlTraj, a Controllable Trajectory generation framework with the topology-constrained diffusion model. Distinct from prior approaches, ControlTraj utilizes a diffusion model to generate high-fidelity trajectories while integrating the structural constraints of road network topology to guide the geographical outcomes. Specifically, we develop a novel road segment autoencoder to extract fine-grained road segment embedding. The encoded features, along with trip attributes, are subsequently merged into the proposed geographic denoising UNet architecture, named GeoUNet, to synthesize geographic trajectories from white noise. Through experimentation across three real-world data settings, ControlTraj demonstrates its ability to produce human-directed, high-fidelity trajectory generation with adaptability to unexplored geographical contexts.

The recent surge in Large Language Models (LLMs) has garnered significant attention across numerous fields. Fine-tuning is often required to fit general LLMs for a specific domain, like the web-based healthcare system. However, two problems arise during fine-tuning LLMs for medical applications. One is the task variety problem, which involves distinct tasks in real-world medical scenarios. The variety often leads to sub-optimal fine-tuning for data imbalance and seesaw problems. Besides, the large amount of parameters in LLMs leads to huge time and computation consumption by fine-tuning. To address these two problems, we propose a novel parameter efficient fine-tuning framework for multi-task medical applications, dubbed as MOELoRA. The designed framework aims to absorb both the benefits of mixture-of-expert (MOE) for multi-task learning and low-rank adaptation (LoRA) for parameter efficient fine-tuning. For unifying MOE and LoRA, we devise multiple experts as the trainable parameters, where each expert consists of a pair of low-rank matrices to retain the small size of trainable parameters. Then, a task-motivated gate function for all MOELoRA layers is proposed, which can control the contributions of each expert and produce distinct parameters for various tasks. We conduct experiments on a multi-task medical dataset, indicating MOELoRA outperforms the existing parameter efficient fine-tuning methods. The code is available online.

Urban mobility analysis has been extensively studied in the past decade using a vast amount of GPS trajectory data, which reveals hidden patterns in movement and human activity within urban landscapes. Despite its significant value, the availability of such datasets often faces limitations due to privacy concerns, proprietary barriers, and quality inconsistencies. To address these challenges, this paper presents a synthetic trajectory dataset with high fidelity, offering a general solution to these data accessibility issues. Specifically, the proposed dataset adopts a diffusion model as its synthesizer, with the primary aim of accurately emulating the spatial-temporal behavior of the original trajectory data. These synthesized data can retain the geo-distribution and statistical properties characteristic of real-world datasets. Through rigorous analysis and case studies, we validate the high similarity and utility between the proposed synthetic trajectory dataset and real-world counterparts. Such validation underscores the practicality of synthetic datasets for urban mobility analysis and advocates for its wider acceptance within the research community. Finally, we publicly release the trajectory synthesizer and datasets, aiming to enhance the quality and availability of synthetic trajectory datasets and encourage continued contributions to this rapidly evolving field. The dataset is released for public online availability https://github.com/Applied-Machine-Learning-Lab/SynMob.

Pervasive integration of GPS-enabled devices and data acquisition technologies has led to an exponential increase in GPS trajectory data, fostering advancements in spatial-temporal data mining research. Nonetheless, GPS trajectories contain personal geolocation information, rendering serious privacy concerns when working with raw data. A promising approach to address this issue is trajectory generation, which involves replacing original data with generated, privacy-free alternatives. Despite the potential of trajectory generation, the complex nature of human behavior and its inherent stochastic characteristics pose challenges in generating high-quality trajectories. In this work, we propose a spatial-temporal diffusion probabilistic model for trajectory generation (DiffTraj). This model effectively combines the generative abilities of diffusion models with the spatial-temporal features derived from real trajectories. The core idea is to reconstruct and synthesize geographic trajectories from white noise through a reverse trajectory denoising process. Furthermore, we propose a Trajectory UNet (Traj-UNet) deep neural network to embed conditional information and accurately estimate noise levels during the reverse process. Experiments on two real-world datasets show that DiffTraj can be intuitively applied to generate high-fidelity trajectories while retaining the original distributions. Moreover, the generated results can support downstream trajectory analysis tasks and significantly outperform other methods in terms of geo-distribution evaluations.

Historical user-item interaction datasets are essential in training modern recommender systems for predicting user preferences. However, the arbitrary user behaviors in most recommendation scenarios lead to a large volume of noisy data instances being recorded, which cannot fully represent their true interests. While a large number of denoising studies are emerging in the recommender system community, all of them suffer from highly dynamic data distributions. In this paper, we propose a Deep Reinforcement Learning (DRL) based framework, AutoDenoise, with an Instance Denoising Policy Network, for denoising data instances with an instance selection manner in deep recommender systems. To be specific, AutoDenoise serves as an agent in DRL to adaptively select noise-free and predictive data instances, which can then be utilized directly in training representative recommendation models. In addition, we design an alternate two-phase optimization strategy to train and validate the AutoDenoise properly. In the searching phase, we aim to train the policy network with the capacity of instance denoising; in the validation phase, we find out and evaluate the denoised subset of data instances selected by the trained policy network, so as to validate its denoising ability. We conduct extensive experiments to validate the effectiveness of AutoDenoise combined with multiple representative recommender system models.

In modern traffic management, one of the most essential yet challenging tasks is accurately and timely predicting traffic. It has been well investigated and examined that deep learning-based Spatio-temporal models have an edge when exploiting Spatio-temporal relationships in traffic data. Typically, data-driven models require vast volumes of data, but gathering data in small cities can be difficult owing to constraints such as equipment deployment and maintenance costs. To resolve this problem, we propose TrafficTL, a cross-city traffic prediction approach that uses big data from other cities to aid data-scarce cities in traffic prediction. Utilizing a periodicity-based transfer paradigm, it identifies data similarity and reduces negative transfer caused by the disparity between two data distributions from distant cities. In addition, the suggested method employs graph reconstruction techniques to rectify defects in data from small data cities. TrafficTL is evaluated by comprehensive case studies on three real-world datasets and outperforms the state-of-the-art baseline by around 8 to 25 percent.

Privacy-preserving transportation mode identification (TMI) is among the key challenges toward future intelligent transportation systems. With recent developments in federated learning (FL), crowdsourcing has emerged as a promising cost-effective data source for training powerful TMI classifiers without compromising users’ data privacy. However, existing TMI approaches have relied heavily on the availability of transportation mode labels, which is often limited in real-world applications. While recent semisupervised studies have partially addressed this issue by assigning pseudolabels to unlabeled data, such practice often degrades classification performance as more unlabeled data are incorporated. In response to this issue, we present a semisupervised FL scheme for TMI termed mean teacher semisupervised FL (MTSSFL). MTSSFL trains a deep neural network ensemble under a novel semisupervised FL framework, achieving highly accurate and privacy-protected crowdsourced TMI without depending on the availability of massive labeled data. MTSSFL introducesconsistency updatingto insert the global model in the gradient updates of the local models that only have unlabeled data to improve their training. We also devisemean-teacher-averaging, a secure parameter aggregation mechanism that further boosts the global model’s TMI performance without requiring additional training. Our extensive case studies on a real-world data set demonstrate that MTSSFL’s classification accuracy is merely 1.1% lower than the state-of-the-art semisupervised TMI approach while being the only one to satisfy FL’s privacy-preserving constraints. In addition, MTSSFL can achieve high accuracy with less training overhead due to the proposed semisupervised learning design.

Estimated time of arrival (ETA) is one of the critical services offered by navigation and hailing providers. The majority of existing solutions approach ETA as a regression problem and leverage GPS trajectories for estimation. However, the travel time fluctuates greatly between different trips, making simple regression methods skewed. Additionally, these methods are incapable of conducting estimation in practice because the trajectories of future trips are unknown. To jointly tackle these problems, we propose a novel Categorical approximate method to Estimate Time of Arrival (CatETA). Specifically, we formulate the ETA problem as a classification problem and label it with the average time of each category. To eliminate bias in categorical labeling, we approximate travel time using the weighted average of different classes in the testing stage. Then, we design a network structure that extracts the spatio-temporal features of link sequences and integrates a set of global information. Furthermore, we merge link sequences according to network topology and graph embedding to alleviate the computational burden associated with large-scale link networks. Comprehensive experiments on real-world datasets demonstrate that CatETA considerably improves the estimation performance and significantly reduces computational effort.

GPS trajectories serve as a significant data source for travel mode identification along with the development of various GPS-enabled smart devices. However, such data directly integrate user private information, thus hindering users from sharing data with third parties. On the other hand, existing identification methods heavily depend on the respective manual travel mode annotations, whose production is economically inefficient and error-prone. In this paper, we propose a Semi-supervised Federated Learning (SSFL) framework that can accurately identify travel modes without using users’ raw trajectories data or relying on notable data labels. Specifically, we propose a new identification model named convolutional neural network-gated recurrent unit model in SSFL to accurately infer travel modes from GPS trajectories. Second, we design a pseudo-labeling method for the clients to set pseudo-labels on their local unlabeled dataset by using a small public dataset at the server. Furthermore, we adopt a grouping-based aggregation scheme and a data flipping augmentation scheme, which can boost the convergence and performance of the proposed framework. Comprehensive evaluations on a real-world dataset show that SSFL outperforms centralized semi-supervised baselines and is robust to the non-independent and identically distributed data commonly seen in practice.

Along with urbanization and the deployment of GPS sensors in vehicles and mobile phones, massive amounts of trajectory data have been generated for city areas. The analysis of these data has substantially contributed to research and advancements of travel time estimation. However, existing work focuses on estimating travel time inside a particular area, and cross-area travel time estimation has privacy security challenges due to data exchange issues among areas. Meanwhile, the majority of methods estimate a deterministic travel time for a given trajectory, which does not account for complex traffic situations and user requirements. To address these problems, we propose a cross-area travel time uncertainty estimation algorithm for estimating the uncertainty of travel times while preserving privacy among different areas. Specifically, we design a comprehensive cross-area privacy-preserving solution that trains a tailor-made neural network travel time estimator in each area by local data, and incorporates federated learning for training. Furthermore, we employ Bayesian deep learning principles and adopt Monte-Carlo dropout to quantify the uncertainty associated with travel time. To evaluate the proposed approach, we conduct a series of comprehensive case studies with two real-world trajectory datasets. Extensive results demonstrate the superiority of the proposed approach compared to baselines in the context of the cross-area setting.

The deployment of Global Positioning System (GPS) sensors in modern smartphones and wearable devices has enabled the acquisition of high-coverage urban trajectories. Extracting knowledge from such diverse spatiotemporal data is essential for optimizing intelligent transportation system operations. Yet a deeper understanding of users’ mobility patterns also requires identifying their associated transportation modes. Combined with growing privacy concerns, the considerable effort involved in manual data annotation means that GPS trajectories are in reality not labeled by transportation mode. This poses a significant challenge for machine learning classifiers, which often perform best when trained on large amounts of labeled data. As such, this paper investigates a wide range of time series augmentation methods aiming to improve the real-world applicability of transportation mode identification. In our extensive experiments on Microsoft’s Geolife dataset, both discrete wavelet transform and flip augmentations pushed the transportation mode identification accuracy of a convolutional neural network from 85.1% to 87.3% and 87.2%, respectively.

Federated Learning (FL) is a privacy-oriented framework that allows distributed edge devices to jointly train a shared global model without transmitting their sensed data to centralized servers. FL aims to balance the naturally conflicting objectives of obtaining massive amounts of data while protecting sensitive information. However, the data stored locally on each edge device are typically not independent and identically distributed (non-IID). Such data heterogeneity poses a severe statistical challenge for the optimization and convergence of the global model. In response to this issue, we propose Federated One-vs-All (FedOVA), an efficient FL algorithm that first decomposes a multi-class classification problem into more straightforward binary classification problems and then combines their respective outputs using ensemble learning. Experiments on several public datasets show that FedOVA achieves higher accuracy and faster convergence than federated averaging and data sharing. Furthermore, our approach can support practical settings with a large number of clients (up to 1000 clients) in FL.

GPS trajectory is one of the most significant data sources in intelligent transportation systems (ITS). A simple application is to use these data sources to help companies or organizations identify users' travel behavior. However, since GPS trajectory is directly related to private data (e.g., location) of users, citizens are unwilling to share their private information with the third-party. How to identify travel modes while protecting the privacy of users is a significant issue. Fortunately, Federated Learning (FL) framework can achieve privacy-preserving deep learning by allowing users to keep GPS data locally instead of sharing data. In this paper, we propose a Roust Federated Learning-based Travel Mode Identification System to identify travel mode without compromising privacy. Specifically, we design an attention augmented model architectures and leverage robust FL to achieve privacy-preserving travel mode identification without accessing raw GPS data from the users. Compared to existing models, we are able to achieve more accurate identification results than the centralized model. Furthermore, considering the problem of non-Independent and Identically Distributed (non-IID) GPS data in the realworld, we develop a secure data sharing strategy to adjust the distribution of local data for each user, thereby the proposed model with non-IID data can achieve accuracy close to the distribution of IID data. Extensive experimental studies on a real-world dataset demonstrate that the proposed model can achieve accurate identification without compromising privacy and being robust to real-world non-IID data.