Shuang Ao

Shuang Ao, Tianyi Zhou, Guodong Long et al.

Throughout long history, natural species have learned to survive by evolving their physical structures adaptive to the environment changes. In contrast, current reinforcement learning (RL) studies mainly focus on training an agent with a fixed morphology (e.g., skeletal structure and joint attributes) in a fixed environment, which can hardly generalize to changing environments or new tasks. In this paper, we optimize an RL agent and its morphology through ``morphology-environment co-evolution (MECE)'', in which the morphology keeps being updated to adapt to the changing environment, while the environment is modified progressively to bring new challenges and stimulate the improvement of the morphology. This leads to a curriculum to train generalizable RL, whose morphology and policy are optimized for different environments. Instead of hand-crafting the curriculum, we train two policies to automatically change the morphology and the environment. To this end, (1) we develop two novel and effective rewards for the two policies, which are solely based on the learning dynamics of the RL agent; (2) we design a scheduler to automatically determine when to change the environment and the morphology. In experiments on two classes of tasks, the morphology and RL policies trained via MECE exhibit significantly better generalization performance in unseen test environments than SOTA morphology optimization methods. Our ablation studies on the two MECE policies further show that the co-evolution between the morphology and environment is the key to the success.

Du Yin, Hao Xue, Arian Prabowo et al.

Existing traffic forecasting benchmarks assume a fixed sensor set, but real road-sensor networks grow continuously as the road network changes year by year. We introduce the XXLTraffic dataset family, which spans up to 27 years of California PeMS and Transport for NSW data. The fixed-sensor subsets of XXLTraffic support extremely long forecasting with multi-year gaps and standard hourly / daily long-horizon forecasting. We extend it to EvoXXLTraffic, a sensor-evolving reorganization that exposes per-year active sensors, yearly traffic-flow matrices, and yearly graph snapshots across nine PeMS districts, with growth ratios ranging from +305% to over +10,000%. We define a yearly streaming forecasting protocol on EvoXXLTraffic in which each calendar year is a continual task, and benchmark a wide range of representative baselines drawn from static spatio-temporal GNNs, naïve online schemes, evolving-graph continual methods, and retrieval / test-time methods. We find that our ultra-large evolutionary dataset better reflects the real world, and many state-of-the-art (SOTA) results no longer work. Our dataset complements existing benchmarks by enabling more realistic forecasting under ultra-long evolutionary road networks.

Peibo Li, Maarten de Rijke, Hao Xue et al.

The next Point of Interest (POI) recommendation task is to predict users' immediate next POI visit given their historical data. Location-Based Social Network (LBSN) data, which is often used for the next POI recommendation task, comes with challenges. One frequently disregarded challenge is how to effectively use the abundant contextual information present in LBSN data. Previous methods are limited by their numerical nature and fail to address this challenge. In this paper, we propose a framework that uses pretrained Large Language Models (LLMs) to tackle this challenge. Our framework allows us to preserve heterogeneous LBSN data in its original format, hence avoiding the loss of contextual information. Furthermore, our framework is capable of comprehending the inherent meaning of contextual information due to the inclusion of commonsense knowledge. In experiments, we test our framework on three real-world LBSN datasets. Our results show that the proposed framework outperforms the state-of-the-art models in all three datasets. Our analysis demonstrates the effectiveness of the proposed framework in using contextual information as well as alleviating the commonly encountered cold-start and short trajectory problems.

Peibo Li, Shuang Ao, Hao Xue et al.

Large language models (LLMs) have been adopted for next point-of-interest (POI) recommendation tasks. Typical LLM-based recommenders fall into two categories: prompt-based and supervised fine-tuning (SFT)-based models. Prompt-based models generally offer greater output flexibility but deliver lower accuracy, whereas SFT-based models achieve higher performance yet face a fundamental mismatch: next POI recommendation data does not naturally suit supervised fine-tuning. In SFT, the model is trained to reproduce the exact ground truth, but each training example provides only a single target POI, so there is no ground truth for producing a top-k list. To address this, we propose Refine-POI, a reinforcement fine-tuning framework for next POI recommendation. We introduce recommendation-driven rewards that enable LLMs to learn to generate top-k recommendation lists using only one ground-truth POI per example. Experiments on real-world datasets demonstrate that Refine-POI achieves state-of-the-art top-k recommendation performance.

Du Yin, Jinliang Deng, Shuang Ao et al.

Training models on spatio-temporal (ST) data poses an open problem due to the complicated and diverse nature of the data itself, and it is challenging to ensure the model's performance directly trained on the original ST data. While limiting the variety of training data can make training easier, it can also lead to a lack of knowledge and information for the model, resulting in a decrease in performance. To address this challenge, we presented an innovative paradigm that incorporates three separate forms of curriculum learning specifically targeting from spatial, temporal, and quantile perspectives. Furthermore, our framework incorporates a stacking fusion module to combine diverse information from three types of curriculum learning, resulting in a strong and thorough learning process. We demonstrated the effectiveness of this framework with extensive empirical evaluations, highlighting its better performance in addressing complex ST challenges. We provided thorough ablation studies to investigate the effectiveness of our curriculum and to explain how it contributes to the improvement of learning efficiency on ST data.

Du Yin, Hao Xue, Arian Prabowo et al.

Traffic forecasting is crucial for smart cities and intelligent transportation initiatives, where deep learning has made significant progress in modeling complex spatio-temporal patterns in recent years. However, current public datasets have limitations in reflecting the distribution shift nature of real-world scenarios, characterized by continuously evolving infrastructures, varying temporal distributions, and long temporal gaps due to sensor downtimes or changes in traffic patterns. These limitations inevitably restrict the practical applicability of existing traffic forecasting datasets. To bridge this gap, we present XXLTraffic, largest available public traffic dataset with the longest timespan collected from Los Angeles, USA, and New South Wales, Australia, curated to support research in extremely long forecasting beyond test adaptation. Our benchmark includes both typical time-series forecasting settings with hourly and daily aggregated data and novel configurations that introduce gaps and down-sample the training size to better simulate practical constraints. We anticipate the new XXLTraffic will provide a fresh perspective for the time-series and traffic forecasting communities. It would also offer a robust platform for developing and evaluating models designed to tackle the extremely long forecasting problems beyond test adaptation. Our dataset supplements existing spatio-temporal data resources and leads to new research directions in this domain.