arXiv subjects

Xuan Song

Publications and source records attributed to Xuan Song.

At least 55 records · Page 3Linked to original sources

arXiv2024

Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting

Multivariate time-series (MTS) forecasting is a paramount and fundamental problem in many real-world applications. The core issue in MTS forecasting is how to effectively model complex spatial-temporal patterns. In this paper, we develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. We name this framework SCNN, as an acronym of Structured Component-based Neural Network. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. In line with its reverse process, SCNN decouples MTS data into structured and heterogeneous components and then respectively extrapolates the evolution of these components, the dynamics of which are more traceable and predictable than the original MTS. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets. Additionally, we examine SCNN with different configurations and perform in-depth analyses of the properties of SCNN.

cs.LG↗

arXiv2024

Variable white dwarfs in TMTS: Asteroseismological analysis of a ZZ Ceti star, TMTS J17184064+2524314

The Tsinghua University-Ma Huateng Telescope for Survey (TMTS) has been constantly monitoring the northern sky since 2020 in search of rapidly variable stars. To find variable white dwarfs (WDs), the TMTS catalog is cross-matched with the WD catalog of Gaia EDR3, resulting in over 3000 light curves of WD candidates. The WD TMTS J17184064+2524314 (hereafter J1718) is the second ZZ~Ceti star discovered among these common sources. Based on the light curves from TMTS, follow-up photometric observations, and TESS, 10 periods and 3 combination periods are detected. A rotation period of $25.12\pm0.18$ hr is derived, according to the identified rotational splitting. Our spectroscopic observation indicates that this WD belongs to DA type with $T_{\rm eff}=11,670\pm604$ K, log $g=8.16\pm0.36$, $M = 0.70\pm0.23$ M$_{\odot}$, and age=$0.51\pm0.34$ Gyr. Based on core-parameterized asteroseismological model grids ($\geqslant$ 14 million), we derive a best-fit solution of $T_{\rm eff}=11,640\pm20$ K, log $g=8.267\pm0.008$, and $M = 0.750\pm0.005$ M$_{\odot}$ for J1718, consistent with the spectral fitting results. For this WD, the corresponding carbon and oxygen abundances in the core are 0.43 and 0.57, respectively. The distance derived from the intrinsic luminosity given by asteroseismology is $64\pm15$ pc, in accord with the distance of $70.1\pm0.2$ pc from Gaia DR3 within the uncertainties.

astro-ph.SR↗

arXiv2023

Learning to Generate Pseudo Personal Mobility

The importance of personal mobility data is widely recognized in various fields. However, the utilization of real personal mobility data raises privacy concerns. Therefore, it is crucial to generate pseudo personal mobility data that accurately reflects real-world mobility patterns while safeguarding user privacy. Nevertheless, existing methods for generating pseudo mobility data, such as mechanism-based and deep-learning-based approaches, have limitations in capturing sufficient individual heterogeneity. To address these gaps, taking pseudo-person(avatar) as ground-zero, a novel individual-based human mobility generator called GeoAvatar has been proposed - which considers individual heterogeneity in spatial and temporal decision-making, incorporates demographic characteristics, and provides interpretability. Our method utilizes a deep generative model to simulate heterogeneous individual life patterns, a reliable labeler for inferring individual demographic characteristics, and a Bayesian approach for generating spatial choices. Through our method, we have achieved the generation of heterogeneous individual human mobility data without accessing individual-level personal information, with good quality - we evaluated the proposed method based on physical features, activity patterns, and spatial-temporal characteristics, demonstrating its good performance, compared to mechanism-based modeling and black-box deep learning approaches. Furthermore, this method maintains extensibility for broader applications, making it a promising paradigm for generating human mobility data.

cs.CY↗

arXiv2023

Hyper-Relational Knowledge Graph Neural Network for Next POI

With the advancement of mobile technology, Point of Interest (POI) recommendation systems in Location-based Social Networks (LBSN) have brought numerous benefits to both users and companies. Many existing works employ Knowledge Graph (KG) to alleviate the data sparsity issue in LBSN. These approaches primarily focus on modeling the pair-wise relations in LBSN to enrich the semantics and thereby relieve the data sparsity issue. However, existing approaches seldom consider the hyper-relations in LBSN, such as the mobility relation (a 3-ary relation: user-POI-time). This makes the model hard to exploit the semantics accurately. In addition, prior works overlook the rich structural information inherent in KG, which consists of higher-order relations and can further alleviate the impact of data sparsity.To this end, we propose a Hyper-Relational Knowledge Graph Neural Network (HKGNN) model. In HKGNN, a Hyper-Relational Knowledge Graph (HKG) that models the LBSN data is constructed to maintain and exploit the rich semantics of hyper-relations. Then we proposed a Hypergraph Neural Network to utilize the structural information of HKG in a cohesive way. In addition, a self-attention network is used to leverage sequential information and make personalized recommendations. Furthermore, side information, essential in reducing data sparsity by providing background knowledge of POIs, is not fully utilized in current methods. In light of this, we extended the current dataset with available side information to further lessen the impact of data sparsity. Results of experiments on four real-world LBSN datasets demonstrate the effectiveness of our approach compared to existing state-of-the-art methods.

cs.AI↗

arXiv2023

STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting

With the rapid development of the Intelligent Transportation System (ITS), accurate traffic forecasting has emerged as a critical challenge. The key bottleneck lies in capturing the intricate spatio-temporal traffic patterns. In recent years, numerous neural networks with complicated architectures have been proposed to address this issue. However, the advancements in network architectures have encountered diminishing performance gains. In this study, we present a novel component called spatio-temporal adaptive embedding that can yield outstanding results with vanilla transformers. Our proposed Spatio-Temporal Adaptive Embedding transformer (STAEformer) achieves state-of-the-art performance on five real-world traffic forecasting datasets. Further experiments demonstrate that spatio-temporal adaptive embedding plays a crucial role in traffic forecasting by effectively capturing intrinsic spatio-temporal relations and chronological information in traffic time series.

cs.LG↗

arXiv2023

MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation

Urban time series data forecasting featuring significant contributions to sustainable development is widely studied as an essential task of the smart city. However, with the dramatic and rapid changes in the world environment, the assumption that data obey Independent Identically Distribution is undermined by the subsequent changes in data distribution, known as concept drift, leading to weak replicability and transferability of the model over unseen data. To address the issue, previous approaches typically retrain the model, forcing it to fit the most recent observed data. However, retraining is problematic in that it leads to model lag, consumption of resources, and model re-invalidation, causing the drift problem to be not well solved in realistic scenarios. In this study, we propose a new urban time series prediction model for the concept drift problem, which encodes the drift by considering the periodicity in the data and makes on-the-fly adjustments to the model based on the drift using a meta-dynamic network. Experiments on real-world datasets show that our design significantly outperforms state-of-the-art methods and can be well generalized to existing prediction backbones by reducing their sensitivity to distribution changes.

cs.LG↗

arXiv2023

Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution

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.

cs.AI↗

arXiv2023

Extend Wave Function Collapse to Large-Scale Content Generation

Wave Function Collapse (WFC) is a widely used tile-based algorithm in procedural content generation, including textures, objects, and scenes. However, the current WFC algorithm and related research lack the ability to generate commercialized large-scale or infinite content due to constraint conflict and time complexity costs. This paper proposes a Nested WFC (N-WFC) algorithm framework to reduce time complexity. To avoid conflict and backtracking problems, we offer a complete and sub-complete tileset preparation strategy, which requires only a small number of tiles to generate aperiodic and deterministic infinite content. We also introduce the weight-brush system that combines N-WFC and sub-complete tileset, proving its suitability for game design. Our contribution addresses WFC's challenge in massive content generation and provides a theoretical basis for implementing concrete games.

cs.AI↗

arXiv2023

Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention

Recent years have witnessed the great potential of attention mechanism in graph representation learning. However, while variants of attention-based GNNs are setting new benchmarks for numerous real-world datasets, recent works have pointed out that their induced attentions are less robust and generalizable against noisy graphs due to lack of direct supervision. In this paper, we present a new framework which utilizes the tool of causality to provide a powerful supervision signal for the learning process of attention functions. Specifically, we estimate the direct causal effect of attention to the final prediction, and then maximize such effect to guide attention attending to more meaningful neighbors. Our method can serve as a plug-and-play module for any canonical attention-based GNNs in an end-to-end fashion. Extensive experiments on a wide range of benchmark datasets illustrated that, by directly supervising attention functions, the model is able to converge faster with a clearer decision boundary, and thus yields better performances.

cs.LG↗

arXiv2023

Metapopulation Graph Neural Networks: Deep Metapopulation Epidemic Modeling with Human Mobility

Epidemic prediction is a fundamental task for epidemic control and prevention. Many mechanistic models and deep learning models are built for this task. However, most mechanistic models have difficulty estimating the time/region-varying epidemiological parameters, while most deep learning models lack the guidance of epidemiological domain knowledge and interpretability of prediction results. In this study, we propose a novel hybrid model called MepoGNN for multi-step multi-region epidemic forecasting by incorporating Graph Neural Networks (GNNs) and graph learning mechanisms into Metapopulation SIR model. Our model can not only predict the number of confirmed cases but also explicitly learn the epidemiological parameters and the underlying epidemic propagation graph from heterogeneous data in an end-to-end manner. The multi-source epidemic-related data and mobility data of Japan are collected and processed to form the dataset for experiments. The experimental results demonstrate our model outperforms the existing mechanistic models and deep learning models by a large margin. Furthermore, the analysis on the learned parameters illustrate the high reliability and interpretability of our model and helps better understanding of epidemic spread. In addition, a mobility generation method is presented to address the issue of unavailable mobility data, and the experimental results demonstrate effectiveness of the generated mobility data as an input to our model.

cs.CY↗

arXiv2023

LAMOST J2043+3413 -- a Fast Disk Precession SW Sextans Candidate in Period Gap

We present follow-up photometric observations and time-series analysis of a nova-like, SW Sextans-type, cataclysmic variable (CV) candidate, LAMOST J204305.95+341340.6 (here after J2043+3413), with Gaia G-band magnitude of 15.30 and a distance of 990 pc, which was identified from the LAMOST spectrum. The photometric data were collected with the Tsinghua-NAOC 0.8-m telescope (TNT), TESS, ZTF, and ASAS-SN. The TESS light curve reveals the presence of two prominent periods of 2.587(8) hours and 1.09(5) days, corresponding to the orbital and superorbital (precession) period, respectively. The TNT data obtained in 2020 shows a possible quasi-periodic oscillation of 1426 seconds. The precession period is about three times shorter than that of CVs with similar orbital periods, indicating an unusually fast precessing accretion disk. The ZTF data is found to show a sudden decline of $\sim0.4$ mag on MJD 58979. From the intermittent behavior of the eclipse, we deduce that J2043+3413 is an intermediate inclination system of CV, similar to V795 Her, which is also situated in the period gap.

astro-ph.SR↗

arXiv2023

Learning Gaussian Mixture Representations for Tensor Time Series Forecasting

Tensor time series (TTS) data, a generalization of one-dimensional time series on a high-dimensional space, is ubiquitous in real-world scenarios, especially in monitoring systems involving multi-source spatio-temporal data (e.g., transportation demands and air pollutants). Compared to modeling time series or multivariate time series, which has received much attention and achieved tremendous progress in recent years, tensor time series has been paid less effort. Properly coping with the tensor time series is a much more challenging task, due to its high-dimensional and complex inner structure. In this paper, we develop a novel TTS forecasting framework, which seeks to individually model each heterogeneity component implied in the time, the location, and the source variables. We name this framework as GMRL, short for Gaussian Mixture Representation Learning. Experiment results on two real-world TTS datasets verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/beginner-sketch/GMRL.

cs.LG↗

arXiv2023

Properties and Asteroseismological analysis of a new ZZ ceti discovered by TMTS

Tsinghua university-Ma Huateng Telescope for Survey (TMTS) aims to discover rapidly evolving transients by monitoring the northern sky. The TMTS catalog is cross-matched with the white dwarf (WD) catalog of Gaia EDR3, and light curves of more than a thousand WD candidates are obtained so far. Among them, the WD TMTS J23450729+5813146 (hereafter J2345) is one interesting common source. Based on the light curves from the TMTS and follow-up photometric observations, periods of 967.113 s, 973.734 s, 881.525 s, 843.458 s, 806.916 s and 678.273 s are identified. In addition, the TESS observations suggest a 3.39 h period but this can be attributed to the rotation of a comoving M dwarf located within 3". The spectroscopic observation indicates that this WD is DA type with Teff = 11778+/-617K,log g = 8.38+/-0.31,mass=0.84+/-0.20Msun and age=0.704+/-0.377 Gyrs. Asteroseismological analysis reveals a global best-fit solution of Teff =12110+/-10K and mass=0.760+/-0.005Msun,consistent with the spectral fitting results, and Oxygen and Carbon abundances in the core center are 0.73 and 0.27, respectively. The distance derived from the intrinsic luminosity given by asteroseismology is 93 parsec, which is in agreement with the distance of 98 parsec from Gaia DR3. Additionally, kinematic study shows that this WD is likely a thick disk star. The mass of its zero-age main-sequence mass is estimated to be 3.08 Msun and has a main-sequence plus cooling age of roughly 900 Myrs.

astro-ph.SR↗

arXiv2023

MegaCRN: Meta-Graph Convolutional Recurrent Network for Spatio-Temporal Modeling

Spatio-temporal modeling as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the underlying heterogeneity and non-stationarity implied in the graph streams, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (METR-LA and PEMS-BAY) and a large-scale spatio-temporal dataset that contains a variaty of non-stationary phenomena. Our model outperformed the state-of-the-arts to a large degree on all three datasets (over 27% MAE and 34% RMSE). Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle locations and time slots with different patterns and be robustly adaptive to different anomalous situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

cs.LG↗

arXiv2023

Domain Adversarial Graph Convolutional Network Based on RSSI and Crowdsensing for Indoor Localization

In recent years, the use of WiFi fingerprints for indoor positioning has grown in popularity, largely due to the widespread availability of WiFi and the proliferation of mobile communication devices. However, many existing methods for constructing fingerprint datasets rely on labor-intensive and time-consuming processes of collecting large amounts of data. Additionally, these methods often focus on ideal laboratory environments, rather than considering the practical challenges of large multi-floor buildings. To address these issues, we present a novel WiDAGCN model that can be trained using a small number of labeled site survey data and large amounts of unlabeled crowdsensed WiFi fingerprints. By constructing heterogeneous graphs based on received signal strength indicators (RSSIs) between waypoints and WiFi access points (APs), our model is able to effectively capture the topological structure of the data. We also incorporate graph convolutional networks (GCNs) to extract graph-level embeddings, a feature that has been largely overlooked in previous WiFi indoor localization studies. To deal with the challenges of large amounts of unlabeled data and multiple data domains, we employ a semi-supervised domain adversarial training scheme to effectively utilize unlabeled data and align the data distributions across domains. Our system is evaluated using a public indoor localization dataset that includes multiple buildings, and the results show that it performs competitively in terms of localization accuracy in large buildings.

cs.NI↗

arXiv2023

Adaptive Policy Learning for Offline-to-Online Reinforcement Learning

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected dataset. However, it will yield unsatisfactory performance if the quality of the offline datasets is poor. In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data. Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, that is, a pessimistic update strategy for the offline dataset and an optimistic/greedy update scheme for the online dataset. Such a simple and effective method provides a way to mix the offline and online RL and achieve the best of both worlds. We further provide two detailed algorithms for implementing the framework through embedding value or policy-based RL algorithms into it. Finally, we conduct extensive experiments on popular continuous control tasks, and results show that our algorithm can learn the expert policy with high sample efficiency even when the quality of offline dataset is poor, e.g., random dataset.

cs.LG↗

arXiv2023

Spatio-Temporal Meta-Graph Learning for Traffic Forecasting

Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity and non-stationarity implied in the traffic stream, in this study, we propose Spatio-Temporal Meta-Graph Learning as a novel Graph Structure Learning mechanism on spatio-temporal data. Specifically, we implement this idea into Meta-Graph Convolutional Recurrent Network (MegaCRN) by plugging the Meta-Graph Learner powered by a Meta-Node Bank into GCRN encoder-decoder. We conduct a comprehensive evaluation on two benchmark datasets (i.e., METR-LA and PEMS-BAY) and a new large-scale traffic speed dataset called EXPY-TKY that covers 1843 expressway road links in Tokyo. Our model outperformed the state-of-the-arts on all three datasets. Besides, through a series of qualitative evaluations, we demonstrate that our model can explicitly disentangle the road links and time slots with different patterns and be robustly adaptive to any anomalous traffic situations. Codes and datasets are available at https://github.com/deepkashiwa20/MegaCRN.

cs.LG↗

arXiv2023

Layer sliding and twisting induced electronic transitions in correlated magnetic 1T-NbSe2 bilayers

Correlated two-dimensional (2D) layers, like 1T-phases of TaS2, TaSe2 and NbSe2, exhibit rich tunability through varying interlayer couplings, which promotes the understanding of electron-correlation in the 2D limit. However, the coupling mechanism is, so far, poorly understood and was tentatively ascribed to interactions among the d_(z^2 ) orbitals of Ta or Nb atoms. Here, we theoretically show that the interlayer hybridization and localization strength of interfacial Se pz orbitals, rather than Nb d_(z^2 ) orbitals, govern the variation of electron-correlated properties upon interlayer sliding or twisting in correlated magnetic 1T-NbSe2 bilayers. Each of the both layers is in a star-of-David (SOD) charge-density-wave phase. Geometric and electronic structures, and magnetic properties of 28 different stacking configurations were examined and analyzed using density-functional-theory calculations. We found that the SOD contains a localized region (Reg-L), in which interlayer Se pz hybridization plays a paramount role in varying the energy levels of the two Hubbard bands. These variations lead to three electronic transitions among four insulating states, which demonstrated the effectiveness of interlayer interactions to modulate correlated magnetic properties in a prototypical correlated magnetic insulator.

cond-mat.mtrl-sci↗