The first paper titled “GeoGen: A Two-stage Coarse-to-Fine Framework for Fine-grained Synthetic Location-based Social Network Trajectory Generation”, which is led by his PhD student Rongchao Xu, accepted by the main track (acceptance rate: 17.6%). In this work, we propose a two-stage coarse-to-fine framework for large-scale Location-Based Social Network (LBSN) check-in trajectory generation. In the first stage, we reconstruct spatially continuous, temporally regular latent movement sequences from the original LBSN check-in trajectories and then design a Sparsity-aware Spatio-temporal Diffusion model (S2TDiff) with an efficient denoising network to learn their underlying behavioral patterns. In the second stage, we design Coarse2FineNet, a Transformer-based Seq2Seq architecture equipped with a dynamic context fusion mechanism in the encoder and a multi-task hybrid-head decoder, which generates fine-grained LBSN trajectories based on coarse-grained latent movement sequences by modeling semantic relevance and behavioral uncertainty. Extensive experiments on four real-world datasets show that GeoGen excels state-of-the-art models for both fidelity and utility evaluation, e.g., it increases over 69% and 55% in distance and radius metrics on the FS-TKY dataset.
The second paper titled “TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction”, which is led by his PhD student Dahai Yu, accepted by the AI for Social Impact Track for an Oral Presentation. The overall track acceptance rate is 24.1% and oral presentation rate is 7.5%. In this paper, we propose a unified framework called TrustEnergy for accurate and reliable user- level energy usage prediction. There are two key technical components in TrustEnergy, a novel memory-augmented spatiotemporal graph neural network and an innovative Conformalized Quantile Regression module. We implement and evaluate our TrustEnergy framework by using data from Florida, New York, and California, and the results show our TrustEnergy can achieve a 5.4% increase in prediction accuracy and 5.7% improvement in uncertainty quantification compared to state-of-the-art baselines.