Text-to-image generation tasks have driven remarkable advances in diverse media applications, yet most focus on single-turn scenarios and struggle with iterative, multi-turn creative tasks. Recent dialogue-based systems attempt to bridge this gap, but their single-agent, sequential paradigm often causes intention drift and incoherent edits. To address these limitations, we present Talk2Image, a novel multi-agent system for interactive image generation and editing in multi-turn dialogue scenarios. Our approach integrates three key components: intention parsing from dialogue history, task decomposition and collaborative execution across specialized agents, and feedback-driven refinement based on a multi-view evaluation mechanism. Talk2Image enables step-by-step alignment with user intention and consistent image editing. Experiments demonstrate that Talk2Image outperforms existing baselines in controllability, coherence, and user satisfaction across iterative image generation and editing tasks.

Tandem mass spectrometry (MS/MS) is a critical tool for identifying molecular structures. By efficiently separating molecular fragments based on their mass-to-charge (m/z) ratios, it facilitates molecular generation and subsequent scientific discoveries. However, de novo molecular generation from MS/MS spectra remains fundamentally constrained by two paramount challenges: the vast chemical space requires effective structural constraints, and the absence of fine-grained substructural generation weakens the correspondences between spectral features and molecular structures. In this work, we propose MSAnchor, a novel two-stage framework for MS/MS-based molecular structure generation. We mitigate the search space challenge through the introduction of Anchor-Extended Molecular Scaffold (AEMS) representation that explicitly encodes side-chain anchoring points, thereby dramatically reducing combinatorial complexity. Leveraging the explicit attachment sites provided by AEMS, we develop anchor-specific priors that establish effective alignments between spectral features and molecular substructures. This fine-grained substructural correspondence is further enhanced by a modified Conditional Information Bottleneck (CIB) module that extracts the most informative spectral components in a structure-aware manner. These innovations enable MSAnchor to generate molecular structures that closely reflect spectral characteristics while constraining combinatorial complexity. Extensive experiments on the CANOPUS and MassSpecGym datasets demonstrate that MSAnchor achieves state-of-the-art performance in molecular structure prediction from MS/MS spectra, with performance improvements that are particularly more pronounced for molecules with higher complexity.

Graph classification is a critical task in analyzing graph data, with applications across various domains. While graph neural networks (GNNs) have achieved remarkable results, their ability to generalize across graphs of varying scales remains a challenge. Conventional models often perform well on large-scale graphs but struggle with distributions that are skewed towards small scales. Conversely, models tailored to address scale imbalances frequently prioritize small-scale graphs, leading to diminished performance in more balanced scenarios. To overcome these limitations, we introduce a Unbalanced-Balanced Representation Converter (U2B), which exhibits no explicit bias toward graph scales. U2B employs a two-step workflow: a distillation phase to extract base features from both node-level and graph-level representations, followed by a refinement phase to generate unbiased representations for improved balance. In the distillation phase, a static constraint guides node-level adjustments, improving the representation of nodes in small graphs. Simultaneously, a dynamic constraint in the graph-level process mitigates biases toward features from large graphs. To ensure harmony between the representations, a consistency alignment loss is introduced, aligning node-level and graph-level features to create more cohesive and balanced graph representations. Extensive experiments on multiple datasets show that U2B achieves competitive performance.

Zhiqing Cui, Binwu Wang, Qingxiang Liu, Yeqiang Wang, Zhengyang Zhou, Yuxuan Liang, Yang Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Accurate forecasting of sequential data streams is a cornerstone of modern Web services, supporting applications such as traffic management, user behavior modeling, and online anomaly prevention. However, in many Web environments, new domains emerge rapidly and labeled history data is scarce, which makes zero-shot forecasting particularly challenging. Existing time-series pre-trained models (TSPMs) show promise but they lack the ability to dynamically incorporate external knowledge, while conventional retrieval-augmented generation (RAG) methods are rarely extended beyond text. In this work, we present QuiZSF, a retrieval-augmented forecasting framework that integrates search and forecasting for time series data. The framework performs search by retrieving structurally similar sequences from a large-scale time-series database, and it performs forecasting by integrating the retrieved knowledge into the target sequence. Specifically, QuiZSF introduces a ChronoRAG Base, a hierarchical tree-structured database that enables scalable and domain-aware retrieval, a Multi-grained Series Interaction Learner that captures fine- and coarse-grained dependencies between target and retrieved sequences, and a Model Cooperation Coherer that adapts retrieved knowledge to TSPMs. This design teaches models to actively perform search, align auxiliary information across modalities, and leverage it for more accurate forecasting. Extensive experiments on five public benchmarks demonstrate that QuiZSF consistently outperforms strong baselines, ranking first in up to 87.5% of zero-shot forecasting settings while maintaining high efficiency.

BACKGROUND: The use of generative large language models (LLMs) with electronic health record (EHR) data is rapidly expanding to support clinical and research tasks. This systematic review characterizes the clinical fields and use cases that have been studied and evaluated to date. METHODS: We followed the Preferred Reporting Items for Systematic Review and Meta-Analyses guidelines to conduct a systematic review of articles from PubMed and Web of Science published between January 1, 2023, and November 9, 2024. Studies were included if they used generative LLMs to analyze real-world EHR data and reported quantitative performance evaluations. Through data extraction, we identified clinical specialties and tasks for each included article, and summarized evaluation methods. RESULTS: Of the 18 735 articles retrieved, 196 met our criteria. Most studies focused on radiology (26.0%), oncology (10.7%), and emergency medicine (6.6%). Regarding clinical tasks, clinical decision support made up the largest proportion of studies (62.2%), while summarizations and patient communications made up the smallest, at 5.6% and 5.1%, respectively. In addition, GPT-4 and GPT-3.5 were the most commonly used generative LLMs, appearing in 60.2% and 57.7% of studies, respectively. Across these studies, we identified 22 unique non-NLP metrics and 35 unique NLP metrics. While NLP metrics offer greater scalability, none demonstrated a strong correlation with gold-standard human evaluations. CONCLUSION: Our findings highlight the need to evaluate generative LLMs on EHR data across a broader range of clinical specialties and tasks, as well as the urgent need for standardized, scalable, and clinically meaningful evaluation frameworks.

OBJECTIVE: Automated literature screening in biomedical research is often hindered by domain shifts and scarcity of labeled data, which limit model accuracy and generalizability. While large language models (LLMs) perform well in zero-shot settings, they often fail to capture complex, domain-specific reasoning patterns. To address this limitation, this study investigates whether an interactive, weakly supervised learning framework combining GPT (generative pre-trained transformer)'s fine-tuning adaptability with DeepSeek's reasoning capabilities can improve literature screening performance across biomedical domains. MATERIALS AND METHODS: We developed an active learning framework that leverages model disagreement between GPT-4o and DeepSeek to improve literature screening performance. This process began with a labeled corpus of 6331 articles on large language models, from which a model disagreement analysis was performed to identify cases where GPT-4o misclassified and DeepSeek produced correct predictions. Three GPT variants-GPT-4o, GPT-4o-mini, and GPT-4.1-nano, were fine-tuned under standard supervised learning settings using these disagreement-based samples. Fine-tuning prompts incorporated classification labels and, when available, rationale traces generated by DeepSeek to provide reasoning-augmented weak supervision. Model performance was evaluated on an independent benchmark set of 291 annotated articles across 10 topic queries in cancer immunotherapy and LLMs in medicine, using standard evaluation metrics, with recall as the primary measure. RESULTS: Fine-tuning GPT models using disagreement-based examples significantly improved performance. GPT-4o-mini achieved the best overall results after fine-tuning, especially with the highest F1 score (0.93, P < .001) and recall (0.95, P < .001). Across the biomedical topics, fine-tuned models consistently outperformed their zero-shot counterparts without increasing reviewer workload. DISCUSSION: These findings demonstrate the effectiveness of disagreement-driven active learning in enhancing GPT-based biomedical literature screening. Lightweight models like GPT-4o-mini benefit most from targeted, reasoning-enriched training, highlighting their suitability for scalable deployment. CONCLUSION: This study introduces an interactive active learning framework that leverages fine-tuned LLMs with reasoning capabilities to enhance literature screening. The approach offers a scalable solution to more efficient and reliable information retrieval in systematic reviews.

Spatio-temporal (ST) prediction is crucial in earth sciences, including meteorological forecasting and urban computing, to name just a few. Access to ample high-quality data, combined with deep models adept at inference, is essential for attaining significant outcomes. Yet, data scarcity and the substantial costs of sensor deployment result in notable data imbalances. Overly specialized models that lack causal linkages further undermine the generalizability of inference techniques. To address these challenges, we first introduce a causal framework for ST predictions, named $\mathtt{NuwaDynamics}$NuwaDynamicsNuwaDynamics, aimed at pinpointing causal regions in data and providing models with the capability for causal reasoning in a dual-phase process. Initially, we employ upstream self-supervision to identify causally significant patches, equipping the model with generalizable insights and performing targeted interventions on non-essential patches to approximate potential testing distributions. This stage is known as the discovery phase. Progressing from discovery, we apply the insights to downstream tasks tailored to specific ST goals, enhancing the model's recognition of a wider potential data distribution and augmenting its causal perceptual abilities (referred to as the Update phase). Additionally, we address environmental controllability and high computational complexity by implementing channel multiplication and conditional generation methods. This process, termed $\mathtt{NuwaDynamics+}$NuwaDynamics+NuwaDynamics+, can further be interpreted as the front-door adjustment technique in the causality domain. Through comprehensive experiments across ten real-world or simulated ST benchmarks, we demonstrate that integrating the $\mathtt{NuwaDynamics+}$NuwaDynamics+NuwaDynamics+ concept substantially improves various model performance. $\mathtt{NuwaDynamics+}$NuwaDynamics+NuwaDynamics+ concept also significantly enhances the versatility across various dynamic ST tasks, such as extreme weather forecasting and long-temporal-step super-resolution predictions.

Air quality forecasting has attracted increasing attention as global air pollution worsens. Spatiotemporal graph neural networks have become a leading paradigm, thanks to their ability to capture complex spatial and temporal dynamics in Air Quality Index (AQI) data. However, existing methods remain limited by weak modeling of long-range temporal dependencies and insufficient integration of meteorological factors. Building on a publicly available nationwide air quality dataset spanning eight years, we propose MADGCN, a Meteorology-Aware Decoupled Spatio-Temporal Convolutional Network that jointly addresses long-horizon temporal modeling and meteorological context fusion. MADGCN includes a dynamic causality discovery module grounded in Granger causality, which captures time-varying causal relationships between meteorological conditions and AQI dynamics. The inferred causal structures further guide a causal graph convolution module and a PatchMixer module, enabling effective spatial interaction modeling and multiscale temporal dependency learning. Extensive experiments against 16 strong baselines show that MADGCN achieves competitive performance for long-horizon air pollution forecasting and generalizes well under high-pollution regimes.

Irregular time series analysis is increasingly essential in data management due to the proliferation of complex data irregularly sampled by real-world systems. Traditional time series models, including RNN-based models and transformer variants, face significant challenges in generalizing to continuous-time paradigms, which are essential for capturing the ongoing dynamics of irregular time series. Neural Ordinary Differential Equations (NODEs) assume a continuous latent dynamic and provide an elegant framework for irregular time series analysis, yet they suffer from limitations like fragmented latent processes and the inability to fully exploit interdependencies among observations. To address these challenges, we propose a novel Differentiable hidden state enhanced neural ODE framework, termed DIFFODE, designed to effectively model irregular time series. Concretely, we introduce an attention-based differential hidden state that maps irregular observations into a continuous hidden state space, enabling the extraction of latent dynamics while preserving temporal continuity. Leveraging the theory of generalized inverses, DIFFODE innovatively derives ODEs to describe hidden state dynamics. Furthermore, we incorporate the Hoyer metric into our framework to enhance its capacity to capture subtle yet critical temporal shifts, significantly improving the accuracy of time series modeling. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of DIFFODE across three key tasks, including irregular time series classification, interpolation, and extrapolation.

Long-term time series forecasting (LTSF) has traditionally relied on large parameters to capture extended temporal dependencies, resulting in substantial computational costs and inefficiencies in both memory usage and processing time. However, time series data, unlike high-dimensional images or text, often exhibit temporal pattern similarity and low-rank structures, especially in long-term horizons. By leveraging this structure, models can be guided to focus on more essential, concise temporal data, improving both accuracy and computational efficiency. In this paper, we introduce TimeBase, an ultra-lightweight network to harness the power of minimalism in LTSF. TimeBase 1) extracts core basis temporal components and 2) transforms traditional point-level forecasting into efficient segment-level forecasting, achieving optimal utilization of both data and parameters. Extensive experiments on diverse real-world datasets show that TimeBase achieves remarkable efficiency and secures competitive forecasting performance. Additionally, TimeBase can also serve as a very effective plug-and-play complexity reducer for any patch-based forecasting models. Code is available at https://github.com/hqh0728/TimeBase.

Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design and training. The key towards increasing cross-domain knowledge is to enable collective intelligence and model evolution. In this paper, inspired by neuroscience theories, we theoretically derive the increased information boundary via learning cross-domain collective intelligence and propose a Synaptic EVOlutional spatiotemporal network, SynEVO, where SynEVO breaks the model independence and enables cross-domain knowledge to be shared and aggregated. Specifically, we first re-order the sample groups to imitate the human curriculum learning, and devise two complementary learners, elastic common container and task-independent extractor to allow model growth and task-wise commonality and personality disentanglement. Then an adaptive dynamic coupler with a new difference metric determines whether the new sample group should be incorporated into common container to achieve model evolution under various domains. Experiments show that SynEVO improves the generalization capacity by at most 42\% under cross-domain scenarios and SynEVO provides a paradigm of NeuroAI for knowledge transfer and adaptation. Code available at [https://github.com/Rodger-Lau/SynEVO](https://github.com/Rodger-Lau/SynEVO).

Recently, spatiotemporal graph convolutional networks have achieved dominant performance in spatiotemporal prediction tasks. However, most models relying on node-to-node messaging interaction exhibit sensitivity to spatiotemporal shifts, encountering out-of-distribution (OOD) challenges. To address these issues, we introduce \textbf{\underline{S}}patio-\textbf{\underline{T}}emporal \textbf{\underline{O}}OD \textbf{\underline{P}}rocessor (STOP), which employs a centralized messaging mechanism along with a message perturbation mechanism to facilitate robust spatiotemporal interactions. Specifically, the centralized messaging mechanism integrates Context-Aware Units for coarse-grained spatiotemporal feature interactions with nodes, effectively blocking traditional node-to-node messages. We also implement a message perturbation mechanism to disrupt this messaging process, compelling the model to extract generalizable contextual features from generated variant environments. Finally, we customize a spatiotemporal distributionally robust optimization approach that exposes the model to challenging environments, thereby further enhancing its generalization capabilities. Compared with 14 baselines across six datasets, STOP achieves up to \textbf{17.01\%} improvement in generalization performance and \textbf{18.44\%} improvement in inductive learning performance. The code is available at https://github.com/PoorOtterBob/STOP.

The out-of-distribution (OOD) generalization challenge is a longstanding problem in graph learning. Through studying the fundamental cause of data distribution shift, i.e., the changes of environments, significant progress has been achieved in addressing this issue. However, we observe that existing works still fail to effectively address complex environment shifts. Existing practices place excessive attention on extracting causal subgraphs, inevitably treating spurious subgraphs as environment variables. While spurious subgraphs are controlled by environments, the space of environment changes encompass more than the scale of spurious subgraphs. Therefore, existing efforts have a limited inference space for environments, leading to failure under severe environment changes. To tackle this issue, we propose a negative inference graph OOD framework (NeGo) to broaden the inference space for environment factors. Inspired by the successful practice of prompt learning in capturing underlying semantics and causal associations in large language models, we design a negative prompt environment inference to extract underlying environment information. We further introduce the environment-enhanced invariant subgraph learning to effectively exploit inferred environment embedding, ensuring the robust extraction of causal subgraph in the environment shifts. Lastly, we conduct a comprehensive evaluation of NeGo on real-world datasets and synthetic datasets across domains. NeGo outperforms baselines on nearly all datasets, which verify the effectiveness of our framework.

Visual pattern recognition usually plays important roles in robotics and automation society where the pattern recognition relies on representation learning. Existing representation learning often neglects two important issues, the diversity of intra-class representation and under-exploited label utilization, especially the negative feedback during training process. Fortunately, prototype learning potentially raises label utilization and encourages intra-class diversity. In this paper, we investigate the intra-class diversity and effective updates in prototype learning for enhanced visual pattern recognition. Specifically, we propose a Label-aware multi-Prototype learning, LamPro, by incorporating the label awareness into both prototype formation and update to improve the representation quality. Firstly, we design a supervised contrastive learning to achieve class-discriminative representations. Secondly, we randomly initialize multiple prototypes and update the nearest prototype upon the arrival of instance, to preserve intra-class diversity. Thirdly, we propose a novel Label-guided Adaptive Updating. We separate the prototype updates from the representation optimization and exploit the label indexes to directly implement the prediction feedback. To correct the model optimization directions, we identify the negative feedback, and correct the prototype updates via queries of labels. Finally, we design a memory-based counter to alternately update these deviated prototypes. Experiments verify the effectiveness of our label-aware and joint multi-prototype updating strategies.

Air quality prediction plays a crucial role in the development of smart cities, garnering significant attention from both academia and industry. Current air quality prediction models encounter two major limitations: their high computational complexity limits scalability to nationwide datasets, and they often regard weather covariates as optional auxiliary information. In reality, weather covariates can have a substantial impact on air quality indices (AQI), exhibiting a significant causal association. In this paper, we first present a nationwide air quality dataset to address the lack of open-source, large-scale datasets in this field. Then we propose a causal learning model, CauAir, for air quality prediction that harnesses the powerful representation capabilities of the Transformer to explicitly model the causal association between weather covariates and AQI. To address the high complexity of traditional Transformers, we design CachLormer, which features two key innovations: a simplified architecture with redundant components removed, and a cache-attention mechanism that employs learnable embeddings for perceiving causal association between AQI and weather covariates in a coarsegrained perspective. We use information theory to illustrate the superiority of the proposed model. Finally, experimental results on three datasets with 28 as the baseline demonstrate that our model achieves competitive performance, while maintaining high training efficiency and low memory consumption. The source code is available at CauAir Official Repository.

Dynamic graphs are ubiquitous in the real world, presenting the temporal evolution of individuals within spatial associations. Recently, dynamic graph learning research is flourishing, striving to more effectively capture evolutionary patterns and spatial correlations. However, existing methods still fail to address the issue of concept shift in dynamic graphs. Concept shift manifests as a distribution shift in the mapping pattern between historical observations and future evolution. The reason is that some environment variables in dynamic graphs exert varying effects on evolution patterns, but these variables are not effectively captured by the models, leading to the intractable concept shift issue. To tackle this issue, we propose a State-driven environment inference framework (Samen) to achieve a dynamic graph learning framework equipped with concept generalization ability. Firstly, we propose a two-stage environment inference and compression strategy. From the perspective of state space, we introduce a prefix-suffix collaborative state learning mechanism to bidirectionally model the spatio-temporal states. A hierarchical state compressor is further designed to refine the state information resulting in concept shift. Secondly, we propose a skip-connection spatio-temporal prediction module, which effectively utilizes the inferred environments to improve the model's generalization capability. Finally, we select seven datasets from different domains to validate the effectiveness of our model. By comparing the performance of different models on samples with concept shift, we verify that our Samen gains generalization capacity that existing methods fail to capture.

Time series forecasting is a critical and complex task, characterized by diverse temporal patterns, varying statistical properties, and different prediction horizons across datasets and domains. Conventional approaches typically rely on a single, unified model architecture to handle all forecasting scenarios. However, such monolithic models struggle to generalize across dynamically evolving time series with shifting patterns. In reality, different types of time series may require distinct modeling strategies. Some benefit from homogeneous multi-scale forecasting awareness, while others rely on more complex and heterogeneous signal perception. Relying on a single model to capture all temporal diversity and structural variations leads to limited performance and poor interpretability. To address this challenge, we propose a Multi-Agent Forecasting System (MAFS) that abandons the one-size-fits-all paradigm. MAFS decomposes the forecasting task into multiple sub-tasks, each handled by a dedicated agent trained on specific temporal perspectives (e.g., different forecasting resolutions or signal characteristics). Furthermore, to achieve holistic forecasting, agents share and refine information through different communication topology, enabling cooperative reasoning across different temporal views. A lightweight voting aggregator then integrates their outputs into consistent final predictions. Extensive experiments across 11 benchmarks demonstrate that MAFS significantly outperforms traditional single-model approaches, yielding more robust and adaptable forecasts.

The stable periodic patterns present in the time series data serve as the foundation for long-term forecasting. However, existing models suffer from limitations such as continuous and chaotic input partitioning, as well as weak inductive biases, which restrict their ability to capture such recurring structures. In this paper, we propose MoFo, which interprets periodicity as both the correlation of period-aligned time steps and the trend of period-offset time steps. We first design period-structured patches—2D tensors generated through discrete sampling—where each row contains only period-aligned time steps, enabling direct modeling of periodic correlations. Period-offset time steps within a period are aligned in columns. To capture trends across these offset time steps, we introduce a period-aware modulator. This modulator introduces an adaptive strong inductive bias through a regulated relaxation function, encouraging the model to generate attention coefficients that align with periodic trends. This function is end-to-end trainable, enabling the model to adaptively capture the distinct periodic patterns across diverse datasets. Extensive empirical results on widely used benchmark datasets demonstrate that MoFo achieves competitive performance while maintaining high memory efficiency and fast training speed.

The effectiveness of Spatiotemporal Graph Neural Networks (STGNNs) critically hinges on the quality of the underlying graph topology. While end-to-end adaptive graph learning methods have demonstrated promising results in capturing latent spatiotemporal dependencies, they often suffer from high computational complexity and limited expressive capacity. In this paper, we propose MAGE for efficient spatiotemporal forecasting. We first conduct a theoretical analysis demonstrating that the ReLU activation function employed in existing methods amplifies edge-level noise during graph topology learning, thereby compromising the fidelity of the learned graph structures. To enhance model expressiveness, we introduce a sparse yet balanced mixture-of-experts strategy, where each expert perceives the unique underlying graph through kernel-based functions and operates with linear complexity relative to the number of nodes. The sparsity mechanism ensures that each node interacts exclusively with compatible experts, while the balancing mechanism promotes uniform activation across all experts, enabling diverse and adaptive graph representations. Furthermore, we theoretically establish that a single graph convolution using the learned graph in MAGE is mathematically equivalent to multiple convolutional steps under conventional graphs. We evaluate MAGE against advanced baselines on multiple real-world spatiotemporal datasets. MAGE achieves competitive performance while maintaining strong computational efficiency.

Long-term time series forecasting (LTSF) aims to predict future trends based on historical data. While longer lookback windows theoretically offer more comprehensive insights, Transformer-based models often struggle with them. On one hand, longer windows introduce more noise and redundancy, hindering the model's learning process. On the other hand, Transformers suffer from attention dispersion and are prone to overfitting to noise, especially when processing long sequences. In this paper, we introduce the Maximum Effective Window (MEW) metric to assess a model's ability to effectively utilize the lookback window. We also propose two model-agnostic modules to enhance MEW, enabling models to better leverage historical data for improved performance. Specifically, to reduce redundancy and noise, we introduce the Information Bottleneck Filter (IBF), which employs information bottleneck theory to extract the most essential subsequences from the input. Additionally, we propose the Hybrid-Transformer-Mamba (HTM), which incorporates the Mamba mechanism for selective forgetting of long sequences while harnessing the Transformer's strong modeling capabilities for shorter sequences. We integrate these two modules into various Transformer-based models, and experimental results show that they effectively enhance MEW, leading to improved overall performance. Our code is available at \url{https://github.com/forever-ly/PIH}.

The World Wide Web thrives on intelligent services that depend heavily on accurate time series forecasting to navigate dynamic and evolving environments. Due to the partially-observed nature of real world, exclusively focusing on the target of interest, so-called endogenous variables, is insufficient for accurate forecasting, especially in web systems that are susceptible to external influences. Thus, utilizing exogenous variables to harness external information, i.e., forecasting with exogenous variable (FEV), is imperative. Nevertheless, as the external environment is complex and ever-evolving, inadequately capturing external influences can even lead to learning spurious correlations and invalid prediction. Fortunately, recent studies have demonstrated that large language models (LLMs) exhibit exceptional recognition capabilities across open real-world systems, including a deep understanding of exogenous environments. However, it is difficult to directly apply LLMs for FEV due to challenges of task activation, exogenous knowledge extraction, and feature space alignment. In this work, we devise ExoLLM, an LLM-driven method to sufficiently utilize Exogenous variables for time series forecasting. We begin by Meta-task Instruction to activate the knowledge transfer of LLM from natural language processing to FEV. To comprehensively understand the intricate and hierarchical influences of exogenous variables, we propose Multi-grained Prompts, encompassing diverse external influences, including natural attributes, trend correlations, and period relationships between two types of variables. Additionally, a Dual TS-Text Attention is devised to bridge the feature gap between text and numeric data in LLM. Evaluation on real-world datasets demonstrates ExoLLM's superiority in exploiting exogenous information for forecasting with open-world language knowledge.

Spatiotemporal (ST) learning has become a crucial technique to enable smart cities and sustainable urban development. Current ST learning models capture the heterogeneity via various spatial convolution and temporal evolution blocks. However, rapid urbanization leads to fluctuating distributions in urban data and city structures, resulting in existing methods suffering generalization and data adaptation issues. Despite efforts, existing methods fail to deal with newly arrived observations, and the limitation of those methods with generalization capacity lies in the repeated training that leads to inconvenience, inefficiency and resource waste. Motivated by complementary learning in neuroscience, we introduce a prompt-based complementary spatiotemporal learning termed ComS2T, to empower the evolution of models for data adaptation. We first disentangle the neural architecture into two disjoint structures, a stable neocortex for consolidating historical memory, and a dynamic hippocampus for new knowledge update. Then we train the dynamic spatial and temporal prompts by characterizing distribution of main observations to enable prompts adaptive to new data. This data-adaptive prompt mechanism, combined with a two-stage training process, facilitates fine-tuning of the neural architecture conditioned on prompts, thereby enabling efficient adaptation during testing. Extensive experiments validate the efficacy of ComS2T in adapting various spatiotemporal out-of-distribution scenarios while maintaining effective inferences.

While existing spatiotemporal prediction models have shown promising performance, they often rely on the assumption of input-label spatiotemporal consistency, and their high complexity raises concerns about scalability. To enhance both efficiency and performance, we integrate label information into the learning process and propose a spatiotemporal dynamic theory that outlines a bi-directional learning paradigm. Building on this paradigm, we design BiST, a lightweight yet effective Bi -directional S patio -T emporal prediction model. BiST incorporates two key processes: a forward spatiotemporal learning process and a backward correction process. The forward process utilizes MLP layers exclusively to model input correlations and generate base prediction. In the backward process, we implement a spatiotemporal decoupling module, which can learn the residual modeling deviation between input and label representations from a decoupled perspective. After smoothing the residual with a diffusion module, we can obtain the correction term to correct the base predictions. This innovative design enables BiST to achieve competitive performance while remaining lightweight. We evaluate BiST against 26 baselines across 13 datasets, including a large-scale dataset with ten thousand nodes and a longrange dataset spanning 20 years. An impressive experimental result demonstrates that BiST achieves a 8.13% improvement in performance compared to state-of-the-art models while consuming only 1.86% of the training time and 7.36% of the memory usage.

Subgraph learning has dominated most practices of improving the expressive power of Message Passing Neural Networks (MPNNs). Existing subgraph discovery policies can be classified into node-based and partition-based, which both achieve impressive performance in most scenarios. However, both mainstream solutions still face a subgraph degradation trap. Subgraph degradation is reflected in the phenomenon that the subgraph-level methods fail to offer any benefits over node-level MPNNs. In this work, we empirically investigate the existence of the subgraph degradation issue and introduce a unified perspective, perfect reconstruction, to provide insights for improving two lines of methods. We further propose a subgraph learning strategy guided by the principle of perfect reconstruction. To achieve this, two major issues should be well-addressed, i.e.,(i) how to ensure the subgraphs to possess with ‘perfect’ information? (ii) how to guarantee the ‘reconstruction’ power of obtained subgraphs?First, we propose a subgraph partition strategyRayleigh-resistanceto extract non-overlap subgraphs by leveraging the graph spectral theory. Second, we put forward aQuerymechanism to achieve subgraph-level equivariant learning, which guarantees subgraph reconstruction ability. These two parts,perfect subgraph partitionandequivariant subgraph learningare seamlessly unified as a novelRayleigh-resistanceEquivariantSubgraph learningarchitecture (RayE-Sub). Comprehensive experiments on both synthetic and real datasets demonstrate that our approach can consistently outperform previous subgraph learning architectures.

Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has become the de facto standard of graph representation learning. Recent works focused on designing self-supervised pre-training tasks to extract useful and universal transferable knowledge from large-scale unlabeled data. However, they have to face an inevitable question: traditional pre-training strategies that aim at extracting useful information about pre-training tasks, may not extract all useful information about the downstream task. In this paper, we reexamine the pre-training process within traditional pre-training and fine-tuning frameworks from the perspective of Information Bottleneck (IB) and confirm that the forgetting phenomenon in pre-training phase may cause detrimental effects on downstream tasks. Therefore, we propose a novelDelayedBottleneckingPre-training (DBP) framework which maintains as much as possible mutual information between latent representations and training data during pre-training phase by suppressing the compression operation and delays the compression operation to fine-tuning phase to make sure the compression can be guided with labeled fine-tuning data and downstream tasks. To achieve this, we design two information control objectives that can be directly optimized and further integrate them into the actual model design. Extensive experiments on both chemistry and biology domains demonstrate the effectiveness of DBP.

Spatiotemporal learning plays a crucial role in mobile computing techniques to empower smart cites. While existing research has made great efforts to achieve accurate predictions on the overall dataset, they still neglect the significant performance heterogeneity across samples. In this work, we designate the performance heterogeneity as the reason for unfair spatiotemporal learning, which not only degrades the practical functions of models, but also brings serious potential risks to real-world urban applications. To fix this gap, we propose a model-independent Fairness-aware framework for SpatioTemporal Graph learning (FairSTG), which inherits the idea of exploiting advantages of well-learned samples to challenging ones with collaborative mix-up. Specifically, FairSTG consists of a spatiotemporal feature extractor for model initialization, a collaborative representation enhancement for knowledge transfer between well-learned samples and challenging ones, and fairness objectives for immediately suppressing sample-level performance heterogeneity. Experiments on four spatiotemporal datasets demonstrate that our FairSTG significantly improves the fairness quality while maintaining comparable forecasting accuracy. Case studies show FairSTG can counter both spatial and temporal performance heterogeneity by our sample-level retrieval and compensation, and our work can potentially alleviate the risks on spatiotemporal resource allocation for underrepresented urban regions.

Understanding mobile traffic data and predicting future trends are essential for wireless operators and service providers to allocate resources efficiently and manage energy effectively. Despite the strong performance of existing models, accurately forecasting mobile traffic remains a challenge due to limited spatial and temporal modeling capabilities and high computational complexity. This paper introduces MobiMixer, a lightweight and efficient multi-scale spatiotemporal mixing model. Its core concept is to integrate multi-scale information from both spatial and temporal dimensions to improve performance on mobile traffic data. We develop a hierarchical interaction module that incorporates super nodes to enable global high-level feature interactions among nodes with common patterns. Additionally, we employ a dynamic time warping strategy to decouple mobile traffic sequences into stable and seasonal components, which are then modeled at different scales using a multi-scale temporal mixing module. We conduct extensive experiments on mobile traffic datasets collected from four international cities. Compared with 21 state-of-the-art benchmark models, MobiMixer demonstrates highly competitive performance, achieving a maximum improvement of 48.49% on the Milan mobile dataset. The model achieves an improvement in training efficiency of up to 10.69 times and reduces memory usage by 33.01%. The source code is available athttps://github.com/PoorOtterBob/Submitted_Code.

Multivariate time series (MTS) prediction has been widely adopted in various scenarios. Recently, some methods have employed patching to enhance local semantics and improve model performance. However, length-fixed patch are prone to losing temporal boundary information, such as complete peaks and periods. Moreover, existing methods mainly focus on modeling long-term dependencies across patches, while paying little attention to other dimensions (e.g., short-term dependencies within patches and complex interactions among cross-variavle patches). To address these challenges, we propose a pure MLP-based HDMixer, aiming to acquire patches with richer semantic information and efficiently modeling hierarchical interactions. Specifically, we design a Length-Extendable Patcher (LEP) tailored to MTS, which enriches the boundary information of patches and alleviates semantic incoherence in series. Subsequently, we devise a Hierarchical Dependency Explorer (HDE) based on pure MLPs. This explorer effectively models short-term dependencies within patches, long-term dependencies across patches, and complex interactions among variables. Extensive experiments on 9 real-world datasets demonstrate the superiority of our approach. The code is available at https://github.com/hqh0728/HDMixer.

With the progress of urban transportation systems, a significant amount of high-quality traffic data is continuously collected through streaming manners, which has propelled the prosperity of the field of spatial-temporal graph prediction. In this paper, rather than solely focusing on designing powerful models for static graphs, we shift our focus to spatial-temporal graph prediction in the dynamic scenario, which involves a continuously expanding and evolving underlying graph. To address inherent challenges, a decoupled learning framework (DLF) is proposed in this paper, which consists of a spatial-temporal graph learning network (DSTG) with a specialized decoupling training strategy. Incorporating inductive biases of time-series structures, DSTG can interpret time dependencies into latent trend and seasonal terms. To enable prompt adaptation to the evolving distribution of the dynamic graph, our decoupling training strategy is devised to iteratively update these two types of patterns. Specifically, for learning seasonal patterns, we conduct thorough training for the model using a long time series (e.g., three months of data). To enhance the learning ability of the model, we also introduce the masked auto-encoding mechanism. During this period, we frequently update trend patterns to expand new information from dynamic graphs. Considering both effectiveness and efficiency, we develop a subnet sampling strategy to select a few representative nodes for fine-tuning the weights of the model. These sampled nodes cover unseen patterns and previously learned patterns. Experiments on dynamic spatial-temporal graph datasets further demonstrate the competitive performance, superior efficiency, and strong scalability of the proposed framework.

Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community. Many recent studies have concentrated on meticulously reconciling various advantages, leading to designed models that are neither simple nor practical. To address this issue, this paper presents a systematic study on existing shortcomings faced by off-the-shelf models, including lack of local fidelity, poor prediction performance over long time-steps, low scalability, and inefficiency. To systematically address the aforementioned problems, we propose an EarthFarseer, a concise framework that combines parallel local convolutions and global Fourier-based transformer architectures, enabling dynamically capture the local-global spatial interactions and dependencies. EarthFarseer also incorporates a multi-scale fully convolutional and Fourier architectures to efficiently and effectively capture the temporal evolution. Our proposal demonstrates strong adaptability across various tasks and datasets, with fast convergence and better local fidelity in long time-steps predictions. Extensive experiments and visualizations over eight human society physical and natural physical datasets demonstrates the state-of-the-art performance of EarthFarseer. We release our code at https://github.com/easylearningscores/EarthFarseer.

One of the most important tasks in ride-hailing is order dispatching, i.e., assigning unserved orders to available drivers. Recent order dispatching has achieved a significant improvement due to the advance of reinforcement learning, which has been approved to be able to effectively address sequential decision-making problems like order dispatching. However, most existing reinforcement learning methods require agents to learn the optimal policy by interacting with environments online, which is challenging or impractical for real-world deployment due to high costs or safety concerns. For example, due to the spatiotemporally unbalanced supply and demand, online reinforcement learning-based order dispatching may significantly impact the revenue of the ride-hailing platform and passenger experience during the policy learning period. Hence, in this work, we develop an offline deep reinforcement learning framework called NondBREM for large-scale order dispatching, which learns policy from only the accumulated logged data to avoid costly and unsafe interactions with the environment. In NondBREM, a Nondeterministic Batch-Constrained Q-learning (NondBCQ) module is developed to reduce the algorithm extrapolation error and a Random Ensemble Mixture (REM) module that integrates multiple value networks with multi-head networks is utilized to improve the model generalization and robustness. Extensive experiments on large-scale real-world ride-hailing datasets show the superiority of our design.

Graph neural networks (GNNs) have achieved state-of-the-art results on many graph representation learning tasks by exploiting statistical correlations. However, numerous observations have shown that such correlations may not reflect the true causal mechanisms underlying the data and thus may hamper the ability of the model to generalize beyond the observed distribution. To address this problem, we propose an Information-based Causal Learning (ICL) framework that combines information theory and causality to analyze and improve graph representation learning to transform information relevance to causal dependence. Specifically, we first introduce a multi-objective mutual information optimization objective derived from information-theoretic analysis and causal learning principles to simultaneously extract invariant and interpretable causal information and reduce reliance on non-causal information in correlations. To optimize this multi-objective objective, we enable a causal disentanglement layer that effectively decouples the causal and non-causal information in the graph representations. Moreover, due to the intractability of mutual information estimation, we derive variational bounds that enable us to transform the above objective into a tractable loss function. To balance the multiple information objectives and avoid optimization conflicts, we leverage multi-objective gradient descent to achieve a stable and efficient transformation from informational correlation to causal dependency. Our approach provides important insights into modulating the information flow in GNNs to enhance their reliability and generalization. Extensive experiments demonstrate that our approach significantly improves the robustness and interpretability of GNNs across different distribution shifts. Visual analysis demonstrates how our method converts informative dependencies in representations into causal dependencies.

Data-driven molecular computing has become an increasingly popular topic in AI for molecular and bioinformatic science. Current molecular modeling exploits the Graph Neural Networks (GNNs) to achieve the representation but they mostly fail to generalize to out-of-distribution (OOD) samples. Even though recent advances on OOD-oriented graph learning discovered the invariant rationale on graphs, they still ignore two important issues, i.e., 1) the increasing number and types of molecules expand patterns of environments on graphs, resulting in failures of invariant rationale based models, 2) the associations between discovered molecular subgraphs and corresponding properties are complex where causal substructures cannot fully interpret the labels. To this end, we propose an environment causal learning framework, EMoNet, to tackle the unresolved OOD challenge in molecular science. Specifically, we model the graph environments via bypassing invariant subgraphs. We first incorporate chemistry principle into our graph growth generator to imitate environment growth, and then devise an environment-GIB to squash out environment and finally introduce a cross-attention causal aggregation, allowing dynamic interactions between environments and invariances. We perform experiments on seven datasets and extensive experiments demonstrate strong generalization ability of EMoNet.

Traffic prediction is a crucial task in the Intelligent Transportation System (ITS), receiving significant attention from both industry and academia. Numerous spatio-temporal graph convolutional networks have emerged for traffic prediction and achieved remarkable success. However, these models have limitations in terms of generalization and scalability when dealing with Out-of-Distribution (OOD) graph data with both structural and temporal shifts. To tackle the challenges of spatio-temporal shift, we propose a framework called STONE by learning invariable node dependencies, which achieve stable performance in variable environments. STONE initially employs gated-transformers to extract spatial and temporal semantic graphs. These two kinds of graphs represent spatial and temporal dependencies, respectively. Then we design three techniques to address spatio-temporal shifts. Firstly, we introduce a Fréchet embedding method that is insensitive to structural shifts, and this embedding space can integrate loose position dependencies of nodes within the graph. Secondly, we propose a graph intervention mechanism to generate multiple variant environments by perturbing two kinds of semantic graphs without any data augmentations, and STONE can explore invariant node representation from environments. Finally, we further introduce an explore-to-extrapolate risk objective to enhance the variety of generated environments. We conduct experiments on multiple traffic datasets, and the results demonstrate that our proposed model exhibits competitive performance in terms of generalization and scalability.

Out-of-distribution (OOD) generalization issue is a well-known challenge within deep learning tasks. In dynamic graphs, the change of temporal environments is regarded as the main cause of data distribution shift. While numerous OOD studies focusing on environment factors have achieved remarkable performance, they still fail to systematically solve the two issue of environment inference and utilization. In this work, we propose a novel dynamic graph learning model named EpoD based on prompt learning and structural causal model to comprehensively enhance both environment inference and utilization. Inspired by the superior performance of prompt learning in understanding underlying semantic and causal associations, we first design a self-prompted learning mechanism to infer unseen environment factors. We then rethink the role of environment variable within spatio-temporal causal structure model, and introduce a novel causal pathway where dynamic subgraphs serve as mediating variables. The extracted dynamic subgraph can effectively capture the data distribution shift by incorporating the inferred environment variables into the node-wise dependencies. Theoretical discussions and intuitive analysis support the generalizability and interpretability of EpoD. Extensive experiments on seven real-world datasets across domains showcase the superiority of EpoD against baselines, and toy example experiments further verify the powerful interpretability and rationality of our EpoD.

Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distribution between training and testing sets. However, given that urban systems are usually dynamic, multi-sourced with imbalanced data distributions, current specific task-specific models fail to generalize to new urban conditions and adapt to new domains without explicitly modeling interdependencies across various dimensions and types of urban data. To this end, we argue that there is an essential to propose a Continuous Multi-task Spatio-Temporal learning framework (CMuST) to empower collective urban intelligence, which reforms the urban spatiotemporal learning from single-domain to cooperatively multi-dimensional and multi-task learning. Specifically, CMuST proposes a new multi-dimensional spatiotemporal interaction network (MSTI) to allow cross-interactions between context and main observations as well as self-interactions within spatial and temporal aspects to be exposed, which is also the core for capturing task-level commonality and personalization. To ensure continuous task learning, a novel Rolling Adaptation training scheme (RoAda) is devised, which not only preserves task uniqueness by constructing data summarization-driven task prompts, but also harnesses correlated patterns among tasks by iterative model behavior modeling. We further establish a benchmark of three cities for multi-task spatiotemporal learning, and empirically demonstrate the superiority of CMuST via extensive evaluations on these datasets. The impressive improvements on both few-shot streaming data and new domain tasks against existing SOAT methods are achieved. Code is available at https://github.com/DILab-USTCSZ/CMuST.

Spatiotemporal traffic forecasting plays a critical role in intelligent transportation systems, which empowers diverse urban services. Existing traffic forecasting frameworks usually devise various learning strategies to capture spatiotemporal correlations from the perspective of volume itself. However, we argue that previous traffic predictions are still unreliable due to two aspects. First, the influences of context factor-wise interactions on dynamic region-wise correlations are under exploitation. Second, the dynamics induce the credibility issue of forecasting that has not been well-explored. In this paper, we exploit the informative traffic-related context factors to jointly tackle the dynamic regional heterogeneity and explain the stochasticity, towards a credible uncertainty-aware traffic forecasting. Specifically, to internalize the dynamic contextual influences into learning process, we design a context-cross relational embedding to capture interactions between each context, and generate virtual graph topology to dynamically relate pairwise regions with context embedding. To quantify the prediction credibility, we attribute data-side aleatoric uncertainty to contexts and re-utilize them for aleatoric uncertainty quantification. Then we couple a dual-pipeline learning with the same objective to produce the discrepancy of model outputs and quantify model-side epistemic uncertainty. These two uncertainties are fed through a spatiotemporal network for extracting uncertainty evolution patterns. Finally, comprehensive experiments and model deployments have corroborated the credibility of our framework.

The training and inference of Graph Neural Networks (GNNs) are costly when scaling up to large-scale graphs. Graph Lottery Ticket (GLT) has presented the first attempt to accelerate GNN inference on large-scale graphs by jointly pruning the graph structure and the model weights. Though promising, GLT encounters robustness and generalization issues when deployed in real-world scenarios, which are also long-standing and critical problems in deep learning ideology. In real-world scenarios, the distribution of unseen test data is typically diverse. We attribute the failures on out-of-distribution (OOD) data to the incapability of discerning causal patterns, which remain stable amidst distribution shifts. In traditional spase graph learning, the model performance deteriorates dramatically as the graph/network sparsity exceeds a certain high level. Worse still, the pruned GNNs are hard to generalize to unseen graph data due to limited training set at hand. To tackle these issues, we propose the Resilient Graph Lottery Ticket (RGLT) to find more robust and generalizable GLT in GNNs. Concretely, we reactivate a fraction of weights/edges by instantaneous gradient information at each pruning point. After sufficient pruning, we conduct environmental interventions to extrapolate potential test distribution. Finally, we perform last several rounds of model averages to further improve generalization. We provide multiple examples and theoretical analyses that underpin the universality and reliability of our proposal. Further, RGLT has been experimentally verified across various independent identically distributed (IID) and out-of-distribution (OOD) graph benchmarks.

Diffuse large B-cell lymphoma (DLBCL), a cancer of B cells, has been one of the most challenging and complicated diseases because of its considerable variation in clinical behavior, response to therapy, and prognosis. Radiomic features from medical images, such as PET images, have become one of the most valuable features for disease classification or prognosis prediction using learning-based methods. In this paper, a new flexible ensemble deep learning model is proposed for the prognosis prediction of the DLBCL in$^{18}$F-FDG PET images. This study proposes the multi-R-signature construction through selected pre-trained deep learning models for predicting progression-free survival (PFS) and overall survival (OS). The proposed method is trained and validated on two datasets from different imaging centers. Through analyzing and comparing the results, the prediction models, including Age, Ann abor stage, Bulky disease, SUVmax, TMTV, and multi-R-signature, achieve the almost best PFS prediction performance (C-index: 0.770, 95% CI: 0.705-0.834, with feature adding fusion method and C-index: 0.764, 95% CI: 0.695-0.832, with feature concatenate fusion method) and OS prediction (C-index: 0.770 (0.692-0.848) and 0.771 (0.694-0.849)) on the validation dataset. The developed multiparametric model could achieve accurate survival risk stratification of DLBCL patients. The outcomes of this study will be helpful for the early identification of high-risk DLBCL patients with refractory relapses and for guiding individualized treatment strategies.

Traffic forecasting is a challenging research topic due to the complex spatial and temporal dependencies among different roads. Though great efforts have been made on traffic forecasting, existing works still have the following shortcomings: i) Most methods only directly perform on the original road network topology which cannot accommodate the diverse traffic patterns and multi-granularity traffic forecasting requirements driven by the natural multi-level urban structure and layout, ii) The existing studies based on the spatio-temporal multi-granularity perspective ignore the interactions between the fine-grained information and coarse-grained information, resulting in the spatio-temporal correlation under multi-granularity inaccurately modeled. To solve the problems, we propose an Adaptive and Interactive Multi-level Spatio-Temporal network (AIMST) for traffic forecasting. Specifically, we first devise a learnable adaptive hierarchical clustering method to automatically generate more coarse-grained graphs from the initial road networks and the traffic data. Then, the spatio-temporal graph convolutional networks are executed on the constructed hierarchical traffic graph of each level correspondingly to capture the spatio-temporal patterns. Furthermore, a multi-level bidirectional interaction module is designed to emphasize the multi-grained interaction patterns among different levels. Extensive experiments on two real-world traffic datasets demonstrate that our framework is superior to several state-of-the-art baselines.

Spatio-temporal mobility modeling plays a pivotal role in the advancement of mobile computing. Nowadays, data is frequently held by various distributed silos, which are isolated from each other and confront limitations on data sharing. Given this, there have been some attempts to introduce federated learning into spatio-temporal mobility modeling. Meanwhile, the distributional heterogeneity inherent in the spatio-temporal data also puts forward requirements for model personalization. However, the existing methods tackle personalization in a model-centric manner and fail to explore the data characteristics in various data silos, thus ignoring the fact that the fundamental cause of insufficient personalization in the model is the heterogeneous distribution of data. In this paper, we propose a novel distribution-oriented personalizedFederated learning framework forCross-siloSpatio-Temporal mobility modeling (namedFedCroST), that leverages learnable spatio-temporal prompts to implicitly represent the local data distribution patterns of data silos and guide the local models to learn the personalized information. Specifically, we focus on the potential characteristics within temporal distribution and devise a conditional diffusion module to generate temporal prompts that serve as guidance for the evolution of the time series. Simultaneously, we emphasize the structure distribution inherent in node neighborhoods and propose adaptive spatial structure partition to construct the spatial prompts, augmenting the spatial information representation. Furthermore, we introduce a denoising autoencoder to effectively harness the learned multi-view spatio-temporal features and obtain personalized representations adapted to local tasks. Our proposal highlights the significance of latent spatio-temporal data distributions in enabling personalized federated spatio-temporal learning, providing new insights into modeling spatio-temporal mobility in data silo scenarios. Extensive experiments conducted on real-world datasets demonstrate that FedCroST outperforms the advanced baselines by a large margin in diverse cross-silo spatio-temporal mobility modeling tasks.

Human mobility forecasting is the key to energizing considerable mobile computing services. However, we find that the collective mobility suffers the spatiotemporal heterogeneity issue and therefore leads to inferior performances of conventional homogeneous aggregations. Given two fundamental factors, i.e., data and objectives in machine learning, we propose to counter such heterogeneity by improving data utilization and optimization objectives. 1) From data utilization perspective, we discover that such heterogeneity is inherently induced by mobility-related context factors and thus these factors can be exploited to learn heterogeneous mobility patterns. 2) From the optimization perspective, the dependencies among output elements, which give another prior to learning, can extract heterogeneous correlations within output sequences. Specifically, we propose a novel Context-Directional SpatioTemporal Graph Network (CD-STGNet), which tackles the above-mentioned heterogeneity, for achieving accurate mobility predictions. Firstly, we improve data utilization by inputting the encoded context-wise interactions to a direction field learner, which realizes directional spatial aggregations. Secondly, regarding series learning and optimization objectives, a context-trend highway is designed to enable context-aware temporal learning while two regularization objectives are proposed to keep the correlations among predicted elements consistent with the ground-truth. Experiments demonstrate that CD-STGNet surpasses competitive baselines by 13% to 22% and boosts the interpretability of context-directional learning.

Recently, spatiotemporal graph convolutional networks are becoming popular in the field of traffic flow prediction and significantly improve prediction accuracy. However, the majority of existing traffic flow prediction models are tailored to static traffic networks and fail to model the continuous evolution and expansion of traffic networks. In this work, we move to investigate the challenge of traffic flow prediction on an expanding traffic network. And we propose an efficient and effective continual learning framework to achieve continuous traffic flow prediction without the access to historical graph data, namely Pattern Expansion and Consolidation based on Pattern Matching based (PECPM). Specifically, we first design a pattern bank based on pattern matching to store representative patterns of the road network. With the expansion of the road network, the model configured with such a bank module can achieve continuous traffic prediction by effectively managing patterns stored in the bank. The core idea is to continuously update new patterns while consolidating learned ones. Specifically, we design a pattern expansion mechanism that can detect evolved and new patterns from the updated network, then these unknown patterns are expanded into the pattern bank to adapt to the updated road network. Additionally, we propose a pattern consolidation mechanism that includes both a bank preservation mechanism and a pattern traceability mechanism. This can effectively consolidate the learned patterns in the bank without requiring access to detailed historical graph data. We construct experiments on real-world traffic datasets to demonstrate the competitive performance, superior efficiency, and strong generalization ability of PECPM.

Missing values, which are common in multivariate time series, is most important obstacle towards the utilization and interpretation of those data. Great efforts have been employed on how to accurately impute missing values in multivariate time series, and existing works either use deep learning networks to achieve deterministic imputations or aim at generating different plausible imputations by sampling multiple noises from a same distribution and then denoising them. However, these models either fall short of modeling the uncertainties of imputations due to their deterministic nature or perform poorly in terms of interpretability and imputation accuracy due to their ignorance of the correlations between the latent representations of both observed and missing values which are parts of samples from a same distribution. To this end, in this paper, we explicitly take the correlations between observed and missing values into account, and theoretically re-derive the Evidence Lower BOund (ELBO) of conditional diffusion model in the scenario of multivariate time series imputation. Based on the newly derived ELBO, we further propose a novel multivariate imputation diffusion model (MIDM) which is equipped with novel noise sampling, adding and denoising mechanisms for multivariate time series imputation, and the series of newly designed technologies jointly ensure the involving of the consistency between observed and missing values. Extensive experiments on both the tasks of multivariate time series imputation and forecasting witness the superiority of our proposed MIDM model on generating conditional estimations.

Subgraph learning has received considerable attention in its capacity of interpreting important structural information for predictions. Existing subgraph learning usually exploits statistics on predefined structures e.g., node degrees, occurrence frequency, to extract subgraphs, or refine the contents via only capturing label-relevant information with node-level sampling. Given diverse subgraph patterns, and mutual independence with local correlations on graphs, current solutions on subgraph learning still have two limitations in extraction and refinement stages. 1) The universality of extracting substructure patterns across domains is still lacking, 2) node-level sampling in refinement will distort the original local topology and none explicit guidance eliminating redundant information contribute to inefficiency issue. In this paper, we propose a unified subgraph learning scheme, Poly-Pivot Graph Neural Network (P2GNN) where we designate the centric node of each subgraph as the pivot. In the extraction stage, we present a general subgraph extraction principle, i.e., Local; Asymmetry between the centric and affiliated nodes. To this end, we asymmetrically model the similarity between each pair of nodes with random walk and quantify mutual affiliations in Affinity Propagation architecture, to extract subgraph structures. In the refinement, we devise a subgraph-level exclusion regularization to squash the target-independent information by considering mutual relations across subgraphs, cooperatively preserving a support set of subgraphs and facilitating the refinement process for graph representation. Empirical experiments on diverse web and biological graphs reveal 1.1%~7.3% improvements against best baselines, and visualized case studies prove the universality and interpretability of our P2GNN.

Spatiotemporal (ST) learning has become a crucial technique for urban digitalization. Due to expansions and dynamics of cities, current spatiotemporal models are inclined to suffer distribution shifts between training and testing sets, leading to the OOD delimma. However, few studies focus on such OOD problem in temporal regressions, let alone spatiotemporal learning. Spatiotemporal data usually reveals segment-level heterogeneity within periodicity and complex spatial dependencies, posing challenges to invariance extraction. In this paper, we find that ST relations make sense for generalization and devise a Causal ST learning framework, CauSTG, which enables invariant relation transferred to OOD scenarios. Specifically, we take temporal steps as environments, and transform spatial-temporal relations into learnable parameters. To tackle heterogeneity in periodicity, we partition temporal steps into sub-environments by identifying distinctive trend patterns, enabling re-organized samples trained separately. To extract invariance within ST observations, we propose a spatiotemporal consistency learner and a hierarchical invariance explorer to jointly filter out stable relations. Our spatiotemporal learner quantifies bi-directional spatial consistency and extracts disentangled seasonal-trend patterns via trainable parameters. Further, the hierarchical invariance explorer constructs variation-based filter to achieve both local and global invariances. Experiments reveal that CauSTG can increase at most 10.26% performance against best baselines, and visualized invariant relations can well interpret the physical rationales. The appendix and codes can be available in our Github repository.

Recently, multivariate time series (MTS) forecasting techniques have seen rapid development and widespread applications across various fields. Transformer-based and GNN-based methods have shown promising potential due to their strong ability to model interaction of time and variables. However, by conducting a comprehensive analysis of the real-world data, we observe that the temporal fluctuations and heterogeneity between variables are not well handled by existing methods. To address the above issues, we propose CrossGNN, a linear complexity GNN model to refine the cross-scale and cross-variable interaction for MTS. To deal with the unexpected noise in time dimension, an adaptive multi-scale identifier (AMSI) is leveraged to construct multi-scale time series with reduced noise. A Cross-Scale GNN is proposed to extract the scales with clearer trend and weaker noise. Cross-Variable GNN is proposed to utilize the homogeneity and heterogeneity between different variables. By simultaneously focusing on edges with higher saliency scores and constraining those edges with lower scores, the time and space complexity (i.e., $O(L)$) of CrossGNN can be linear with the input sequence length $L$. Extensive experimental results on 8 real-world MTS datasets demonstrate the effectiveness of CrossGNN compared with state-of-the-art methods.

Spatio-Temporal Graph (STG) forecasting is a fundamental task in many real-world applications. Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments. Concretely, leveraging a causal lens, we first build a structural causal model to decipher the data generation process of STGs. To handle the temporal OoD issue, we employ the back-door adjustment by a novel disentanglement block to separate the temporal environments from input data. Moreover, we utilize the front-door adjustment and adopt edge-level convolution to model the ripple effect of causation. Experiments results on three real-world datasets demonstrate the effectiveness of CaST, which consistently outperforms existing methods with good interpretability. Our source code is available at https://github.com/yutong-xia/CaST.

Spatiotemporal forecasting is an imperative topic in data science due to its critical applications in smart cities. Existing works mostly perform consecutive predictions of following steps with observations continuously obtained, where nearest observations can be exploited as the key knowledge for status estimation. However, the practical issues of early activity planning and sensor failures elicit a new task, non-consecutive forecasting. In this paper, we define spatiotemporal learning systems with missing observations as Grey Spatiotemporal Systems (G2S) and propose a Factor-Decoupled learning framework for G2S to hierarchically decouple multi-level factors, and enable flexible aggregations with uncertainty estimations. We especially select representative sequences to capture periodicity and instantaneous variations, and infer the non-consecutive future statuses under expected exogenous factors, compensating the missing observations. Given the inherent incompleteness and critical applications of G2S, a DisEntangled Uncertainty Quantification is put forward, to identify two types of uncertainty for model interpretations and robustness promotions. Experiments demonstrate that our solution can promote the performance by at least 8.50% on early planning and 2.01%-18.00% on sensor failures. The appendix of this paper can be found at https://github.com/zzyy0929/SDM-G2S.

Spatiotemporal data forecasting is a fundamental task in the field of graph data mining. Typical spatiotemporal data prediction methods usually capture spatial dependencies by directly aggregating features of local neighboring vertices in a fixed graph. However, this kind of aggregators can only capture localized correlations between vertices, and while been stacked for larger receptive field, they fall into the dilemma of over-smoothing. Additional, in temporal perspective, traditional methods focus on fixed graphs, while the correlations among vertexes can be dynamic. And time series components integrated strategies in traditional spatiotemporal learning methods can hardly handle frequently and drastically changed sequences. To overcome those limitations of existing works, in this paper, we propose a novel multi-graph based dynamic learning framework. First, a novel Dynamic Neighbor Search (DNS) mechanism is introduced to model global dynamic correlations between vertices by constructing a feature graph (FG), where the adjacency matrix is dynamically determined by DNS. Then we further alleviate the over-smoothing issue with our newly designed Adaptive Heterogeneous Representation (AHR) module. Both FG and origin graph (OG) are fed into the AHR modules and fused in our proposed Multi-graph Fusion block. Additionally, we design a Differential Vertex Representation (DVR) module which takes advantage of differential information to model temporal trends. Extensive experiments illustrate the superior forecasting performances of our proposed multi-graph based dynamic learning framework on six real-world spatiotemporal datasets from different cities and domains, and this corroborates the solid effectiveness of our proposed framework and its superior generalization ability.

Urban housing price is widely accepted as an economic indicator which is of both business and research interest in urban computing. However, due to the complex nature of influencing factors and the sparse property of transaction records, to implement such a model is still challenging. To address these challenges, in this work, we study an effective and fine-grained model for urban subregion housing price predictions. Compared to existing works, our proposal improves the forecasting granularity from city-level to mile-level, with only publicly released transaction data. We employ a feature selection mechanism to select more relevant features. Then, we propose an integrated model, JGC MMN (Joint Gated Co-attention Based Multi-modal Network), to learn all-level features and capture spatiotemporal correlations in all-time stages with a modified densely connected convolutional network as well as current ingredients and future expectations. Next, we devise a novel JGC based fusion method to better fuse the heterogeneous data of multi-stage models by considering their interactions in temporal dimension. Finally, extensive empirical studies on real datasets demonstrate the effectiveness of our proposal, and this fine-grained housing price forecasting has the potential to support a broad scope of applications, ranging from urban planning to housing market recommendations.

Modern intelligent transportation system (ITS) has greatly benefitted people's daily life. However, the chanciness and suddenness of urban anomalies may greatly restrict the trouble-free operations of ITS. To be aware of future urban anomalies and their possible influences, great efforts have been achieved on these two aspects, but comprehensive predictions of urban anomalies including the predictions of distributions and durations, are still beingless. And the spatiotemporal cascade self/mutual exciting influences among anomalies have never been considered in previous studies. In this paper, we propose a novel Anomaly Distribution and Duration Joint-Prediction (A2DJP) algorithm to simultaneously filtrate urban subregions and estimate the duration of corresponding potential anomalies in the future. To capture the spatiotemporal correlations between urban traffics and anomalies, we use a modified Graph Convolution Network and Long Short-Term Memory integrated network. To learn the cascade correlations among anomalies themselves, we devise a novel Spatiotemporal neural Hawkes Process model, which contains a Hawkes Process (HP) based GCN and HP-based LSTM to extract the anomaly-wise spatiotemporal cascading correlations. By fusing the spatiotemporal correlations between traffics and anomalies, we then simultaneously predict the distributions and durations of future anomalies. Extensive experiments on real-world datasets demonstrate that our proposed method significantly outperforms state-of-the-art solutions.

With increasing population of modern cities, accurate estimation of regional passenger demands is critical to online taxicab services as such platforms aim at a reformation of taxicab scheduling for a more efficient order dispatching. Though great efforts have been made on passenger demand predictions, existing works still have the following shortcomings: i) they mostly performed based on uniform grid partition, which results in the imbalance of demand volumes among regions and even non-vehicle regions in such partition, ii) none of previous demand forecasting efforts have highlighted the important mutual influences between pick-ups and drop-offs, which are of great significance for taxicab scheduling. To this end, we first devise a multi-kernel based clustering to achieve a taxicab-behavior and geographic-aware sub-region partition, hence a more balanced and compact regional division is obtained. Subsequently, we emphasize the essential factors with regard to mutual transition quantification in taxicab predictions, then propose a Transfer-LSTM and an Origin-Destination-based transition matrix to respectively capture the drop-to-pick and pick-to-drop spatiotemporal transition patterns. Hence, a novel mutual-transition-aware co-prediction framework is devised by capturing complex spatiotemporal interactions between pick-ups and drop-offs. Extensive experiments on two real-world taxicab datasets demonstrate our co-prediction framework is superior to state-of-the-art methods, thus providing novel perspectives to urban human mobility understanding and transition-based taxicab scheduling.

Traffic accident has become a significant health and development threat with rapid urbanizations. An accurate urban accident forecasting enables higher-quality police force pre-allocation and safe route planning for both traffic administrations and travelers, maximumly reducing injuries and damages. Off-the-shelf short-term accident forecasting methods, which focus on modeling static region-wise correlations with existing neural networks, mostly performed on hour levels and with single step. However, given the dynamic nature of road networks and expanding urban areas, it is challenging when the spatiotemporal granularity of forecasting improves as the rareness of accident records and complexity of long-term future dependencies. To address these challenges, we propose a unified framework RiskSeq, to foresee sparse urban accidents with finer granularities and multiple steps in spatiotemporal perspective. In particular, we design region-wise proximity measurements and temporal feature differential operations, and embed them into a novel Differential Time-varying Graph Convolution Network to dynamically capture traffic variations. Considering the hierarchical spatial dependencies and obvious context influences, a hierarchical sequence learning structure is devised by introducing contextual factors into a step-wise decoder. The multi-scale spatial risks are learned jointly to boost the risk predictions based on risk-gather and risk-assign networks. Extensive experiments demonstrate our RiskSeq can increase 5 to 15 percent performances on two datasets.

Foreseeing detailed vehicle future trajectories collectively enables a large scope of urban applications such as route planning and commercial advertising. Existing methods focused on predicting future trajectories of urban vehicles with their own fine-grained historical trajectories. Unfortunately, in real-world scenarios, fine-grained trajectories provided by GPS are limited to obtain due to privacy issues and business competitions. In this paper, our solution enables the ubiquitous but coarse-grained location-based surveillance information to predict the fine-grained trajectories of all vehicles with limited number of fine-grained trajectories. We first capture the vectorized semantic representation of trajectories by training the spatiotemporal embedding in large coarse trajectory set. Then, we propose a new measurement to calculate the trajectory similarity, which combines the vehicles' historical behavior similarity and short-term trajectory similarity. The obtained trajectory similarity is then seamlessly embedded into the dynamic graph convolution network in the manner of spatial attention. The dynamic graph convolution sequence-to-sequence module and the fully-connected layer are devised to generate final sequential trajectory predictions. The whole process is to train in a multi-task framework. Extensive experiments on real-world datasets show the excellent performance of our method.

The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such as urban event prediction where fluctuations are of significant interests. Given the fact that uncertainty quantifies the potential variations around prediction results, traditional learning schemes always lack uncertainty labels, and conventional uncertainty quantification approaches mostly rely upon statistical estimations with Bayesian Neural Networks or ensemble methods. However, they have never involved any spatiotemporal evolution of uncertainties under various contexts, and also have kept suffering from the poor efficiency of statistical uncertainty estimation while training models with multiple times. To provide high-quality uncertainty quantification for spatiotemporal forecasting, we propose an uncertainty learning mechanism to simultaneously estimate internal data quality and quantify external uncertainty regarding various contextual interactions. To address the issue of lacking labels of uncertainty, we propose a hierarchical data turbulence scheme where we can actively inject controllable uncertainty for guidance, and hence provide insights to both uncertainty quantification and weak supervised learning. Finally, we re-calibrate and boost the prediction performance by devising a gated-based bridge to adaptively leverage the learned uncertainty into predictions. Extensive experiments on three real-world spatiotemporal mobility sets have corroborated the superiority of our proposed model in terms of both forecasting and uncertainty quantification.

Real-time traffic accident forecasting is increasingly important for public safety and urban management (e.g., real-time safe route planning and emergency response deployment). Previous works on accident forecasting are often performed on hour levels, utilizing existed neural networks with static region-wise correlations taken into account. However, it is still challenging when the granularity of forecasting step improves as the highly dynamic nature of road network and inherent rareness of accident records in one training sample, which leads to biased results and zero-inflated issue. In this work, we propose a novel framework RiskOracle, to improve the prediction granularity to minute levels. Specifically, we first transform the zero-risk values in labels to fit the training network. Then, we propose the Differential Time-varying Graph neural network (DTGN) to capture the immediate changes of traffic status and dynamic inter-subregion correlations. Furthermore, we adopt multi-task and region selection schemes to highlight citywide most-likely accident subregions, bridging the gap between biased risk values and sporadic accident distribution. Extensive experiments on two real-world datasets demonstrate the effectiveness and scalability of our RiskOracle framework.

Urban housing price is widely accepted as an economic indicator of both business and research interest in urban computing. In this work, we propose an effective and fine-grained model for urban subregion housing price predictions. Compared to existing works, our proposal improves the forecasting granularity from city-level to mile-level in spite of data sparsity and complex factors. The fine-grained housing price forecasting has the potential to support a broad scope of applications, ranging from urban planning to housing market recommendations. To achieve that, in this paper, we propose a novel integrated framework, FTD_DenseNet, which incorporates more social and economic features and makes full use of all-level spatiotemporal features. Specifically, the Kalman Filter-based future expection is firstly involved as an influence factor in our model. Extensive empirical studies on real data show the effectiveness of our proposals.

The fine-grained citywide traffic accident prediction is of great significance for urban traffic management. Existing approaches mainly apply classic machine learning methods based on historical accident records. Thus they failed to involve the cross-domain data, which contains spatial and temporal dependency. Recently, with more cross-domain urban data available, leveraging the cross-domain data by deep learning algorithms to predict fine-grained accidents becomes possible, we propose an attention based ResNet framework to model the sophisticated correlation between urban data.