location-based service developers

Abstract: Human mobility data are fundamental to Web-based location services and broader urban applications, and mobility generation provides synthetic trajectories when real data are costly or inaccessible. Although recent mobility generators have incorporated collective mobility patterns, they primarily focus on individual trajectories and aggregate population dynamics, leaving evolving community structures formed by user-location interactions insufficiently modeled. In this paper, we study community-consistent human mobility generation. To this end, we formulate mobility generation as the generation of dynamic user-location graphs to model community structures and propose MOTION, a Multi-agent framework for cOmmuniTy-consIstent human mObility geNeration. MOTION consists of user agents, location agents, and a global manager agent. MOTION first detects coherent communities from historical mobility using the Leiden algorithm and extracts community-conditioned interaction priors to guide the generation process. Guided by these priors, the user agents plan mobility, search destination candidates, and infer user movements from the individual view. In parallel, selectively activated location agents infer likely user arrivals from the community view. The manager coordinates both views, diagnoses interactions causing deviations, and attributes targeted reflection signals to revise user decisions, location attraction, and source-user selection. Experiments on two real-world datasets show that MOTION outperforms baselines by at least 4.05% across reported metrics of individual trajectories, population and flow distributions, and community and graph structures. Further analyses confirm its robustness, privacy preservation, and downstream utility. The code is available at https://anonymous.4open.science/r/MOTION-04C4.

Abstract: Next point-of-interest (POI) recommendation uses visit histories and POI content, but text and images are often missing. Large language model agents have been applied to recommender systems for preference modeling and evidence acquisition. The challenge is to select agents that can jointly analyze the available evidence for each request. We propose \textsc{CATH} (\emph{Complementary Agents via Task Hypergraphs}), which learns to select agent groups for tasks such as comparing candidates or analyzing a POI with missing content. Agents with distinct processing roles are the task hypergraph nodes; each hyperedge connects the selected group and records its analysis goal and target POIs. The policy selects members conditioned on the request, task, and agents already selected. During execution, members share candidate-linked results that guide their subsequent operations. Completed tasks update candidate states and agent memories within the request. A shared ranking head converts candidate states into corrections to a fixed base ranking. Supervised ranking trains the executor, followed by policy optimization that accounts for computation cost. Experiments under natural missingness on Gowalla-CA, Foursquare-NYC, and Foursquare-TKY show 8.4--9.1\% relative NDCG@20 gains over HyperAgent4POI, the strongest prior baseline evaluated. Additional analyses compare group-selection and execution designs, test ranking under additional masking, and characterize quality--cost tradeoffs.

Abstract: Cardinality estimation is fundamental for query optimization in database systems. Histogram-based estimators are widely used for their simplicity and efficiency but rely on point-centric partitioning that assumes record independence. This assumption breaks in trajectory data, where records from the same moving object show strong spatiotemporal dependencies. Conventional axis-aligned histograms therefore fragment trajectories across partition boundaries, leading to overestimation through duplicate counting. This error reflects a structural limitation of partition boundaries that are misaligned with trajectory-induced density patterns. To this end, we propose TraHist, a histogram-based estimator approximating density-aligned partitioning via efficient grid-based propagation. TraHist builds density-adaptive rectilinear buckets to preserve trajectory continuity and local density coherence while keeping histogram efficiency. Experiments on large-scale real-world datasets show that TraHist reduces estimation error by over 20x relative to the strongest competing estimator in query regimes where trajectory fragmentation is a dominant source of estimation error, while maintaining sub-millisecond query latency and competitive construction cost.

Abstract: Road-network trajectory synthesis under local differential privacy (LDP) enables mobility data analysis without uploading raw trajectories to an untrusted server. Existing locally private trajectory synthesis methods mainly model whole trajectories, point sequences, or grid-level mobility patterns. However, they cannot handle non-uniform privacy risks caused by local road-network and trajectory contexts, such as endpoints, long-stay-associated regions, and low-out-degree branches. They also do not directly protect conditional next-hop choices on road networks, where a user's selected successor may reveal sensitive local movement intentions. To address these challenges, we propose TrajRACE, a locally private synthesis framework for road-network trajectories. TrajRACE uses start, segment-count, and transition reports to represent trajectories. For each transition, it keeps the current road segment as a public aggregation context and perturbs the true successor among legal successors on the client side. It then assigns risk-aware protection strengths to transitions according to local road-network and trajectory contexts. Finally, the server recovers population-level start, segment-count, and conditional transition statistics from heterogeneous privatized reports, and generates synthetic trajectories that follow the public road-network topology. Experiments on three road-network trajectory datasets demonstrate the effectiveness of TrajRACE in improving synthetic-data utility across distributional, query-based, and pattern-level metrics, while providing stronger protection for high-risk local transitions.

Abstract: Individual mobility trajectories support urban analysis and location-based services, yet most trajectory generators require observations from their deployment city. This assumption excludes precisely the cities where trajectories are unavailable even though points of interest (POIs) and their attributes can be obtained from public maps. We study target-trajectory-free generation: learning from POIs and trajectories in source cities while utilizing only POI coordinates and categories in a target city, with no target trajectory or trajectory-derived statistic available for training, model selection, or generation. Existing trajectory generators typically predict absolute destinations, entangling reusable movement behavior with city-specific POI identities and spatial layouts. Our core insight is to replace this city-bound output with context-conditioned relative transitions. We propose Nomad, a transfer-and-ground framework that separates learning how people move from determining where those movements are realized. Specifically, a history-conditioned flow-matching model learns from source trajectories a transition prior over semantic displacement between POI contexts, geographic displacement, and elapsed time; at inference, a behavior graph and an exploration--return walk ground sampled transitions onto the target POI map. This factorization enables a direct test of representation level transferability without assuming invariance of the full mobility distribution. Extensive experiments across ten cities and 14 transfers show that Nomad outperforms adaptation baselines in trajectory fidelity and downstream utility, lowering the average error over the best baseline of each metric by about 15% in distributional fidelity and about 3% in downstream utility.

Abstract: Residential and social sorting along political lines structure Americans' daily interactions, often limiting encounters with opposing viewpoints. Here, we combine high-resolution anonymized mobility data from 11 major U.S. metropolitan areas with precinct-level voting results to quantify and examine individuals' experienced partisan segregation in urban areas. We find that residential context provides a strong baseline for political exposure, but experienced partisan segregation is also shaped by everyday mobility behavior, since individuals living in similar residential environments can experience different levels of partisan segregation depending on their daily routines. In particular, individuals who travel farther encounter more politically diverse environments, especially in highly segregated areas, indicating that mobility range moderates the relationship between residential and experienced segregation, while exploring a wider range of places does not reduce partisan segregation and may even reinforce it. Moreover, place segregation largely reflects political geography, yet categories of points of interest have distinct segregation patterns, with community places and social businesses tending to attract more left-leaning visitors, reflecting visitation patterns rather than local accessibility alone. Our findings show that experienced partisan segregation extends beyond residential geography and is also associated with the mobility behavior and visitation patterns that structure people's daily lives.

Abstract: Uniformly rotated coordinate-wise median chooses a random orthonormal coordinate system, takes a median in each coordinate, and maps the resulting point back to the Euclidean plane. We determine its exact worst-case expected approximation ratio when social cost is the $L_p$ norm of the agents' Euclidean distances and $1<p<2$. The ratio is \(\frac{2^{2-1/p}}π\int_0^{π/2}(\cos^pθ+\sin^pθ)^{1/p}\ddθ\). This expression was previously established as a lower bound by Chan, Lin, and Wang; our contribution is the matching upper bound. The proof establishes a strengthened coordinate-wise median inequality relative to an arbitrary reference point. Its right-hand side is linear in a sum of direction-dependent norms, which permits direct averaging over rotations without the loss incurred by passing through a $p$th-moment bound. We give all auxiliary inequalities and a self-contained proof of tightness using the established two-cluster-and-outlier construction. The upper bound holds for every finite profile and every measurable choice within the coordinate median intervals, while odd-size profiles suffice for the matching lower bound. The result characterizes this fixed mechanism, rather than the optimal approximation ratio among all randomized strategyproof mechanisms.

Abstract: In a wireless network, the initial/random access mechanism (RACH) allows idle/new users to join the network and (possibly) request allocated transmission resources for subsequent traffic. Building on our own previous work, for cell-free user-centric networks, we consider location-dependent random access codebooks such that users in a certain geographic area (location) make use of the corresponding set of random access preambles (codewords). We expand our previous work in two ways: (1) we consider multipath channels with line-of-sight (LoS) propagation within a given radius; (2) we consider two different approaches. The first makes use of Zadoff-Chu (ZC) sequences and GLRT detection to cope with the unknown delay, and it is conceptually similar to the 3GPP 2-step RACH specification (here extended to the cell-free case). The second builds on our previous work on multisource approximate message passing (AMP). For both schemes, we also consider a novel near Maximum-Likelihood approach for localization of the random access users directly from the detected RACH preambles, implicitly using angle of arrival and time difference of arrival information embedded into the LoS components. Simulation results show that the AMP approach achieves generally better performance for random access user detection, while both approaches have similar localization capability with a slight superiority for the frequency-domain scheme.