Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more training data. However, most existing approaches focus primarily on replicating statistical distributions and temporal dependencies of real-world data. We argue that fidelity to observed data alone does not guarantee better model performance, as common patterns may dominate, limiting the representation of rare but important conditions. This highlights the need for generate synthetic samples to improve performance of specific clinical models to fulfill their target outcomes. To address this, we propose TarDiff, a novel target-oriented diffusion framework that integrates task-specific influence guidance into the synthetic data generation process. Unlike conventional approaches that mimic training data distributions, TarDiff optimizes synthetic samples by quantifying their expected contribution to improving downstream model performance through influence functions. Specifically, we measure the reduction in task-specific loss induced by synthetic samples and embed this influence gradient into the reverse diffusion process, thereby steering the generation towards utility-optimized data. Evaluated on six publicly available EHR datasets, TarDiff achieves state-of-the-art performance, outperforming existing methods by up to 20.4% in AUPRC and 18.4% in AUROC. Our results demonstrate that TarDiff not only preserves temporal fidelity but also enhances downstream model performance, offering a robust solution to data scarcity and class imbalance in healthcare analytics.
论文检索
输入标题、作者或关键词，从 2,245 篇学术成果中精准定位
Motif counting is fundamental in graph analytic tasks (e.g., clustering and recommendation) but #P-hard. Recent research has focused on exploring and applying deep learning-based solutions to tackle this problem. However, these solutions assume a deterministic graph where edge existence is certain, which may not hold due to the measurement and statistical prediction errors. Meanwhile, existing methods for uncertain graphs still face considerable time costs. To address the above issues, we propose UnG-MoCha, a novel deep-learning approach to efficiently count motifs in uncertain graphs. UnG-MoCha extracts representative subgraphs via graph structure learning and learns graph and motif representations using hierarchical and classic graph neural networks, respectively. Canonical correlation analysis is used to exploit correlations between graph and motif representations, boosting accuracy. Experiments on real-world graphs demonstrate UnG-MoCha's superior performance for scalable motif counting on uncertain graphs.
Prompt learning has emerged as a powerful paradigm for adapting vision-language models such as CLIP to downstream tasks. However, existing methods often overfit to seen data, leading to significant performance degradation when generalizing to novel classes or unseen domains. To address this limitation, we propose DiSa, a Directional Saliency-Aware Prompt Learning framework that integrates two complementary regularization strategies to enhance generalization. First, our Cross-Interactive Regularization (CIR) fosters cross-modal alignment by enabling cooperative learning between prompted and frozen encoders. Within CIR, a saliency-aware masking strategy guides the image encoder to prioritize semantically critical image regions, reducing reliance on less informative patches. Second, we introduce a directional regularization strategy that aligns visual embeddings with class-wise prototype features in a directional manner to prioritize consistency in feature orientation over strict proximity. This approach ensures robust generalization by leveraging stable prototype directions derived from class-mean statistics. Extensive evaluations on 11 diverse image classification benchmarks demonstrate that DiSa consistently outperforms state-of-the-art prompt learning methods across various settings, including base-to-novel generalization, cross-dataset transfer, domain generalization, and few-shot learning.
Survey data are common and invaluable in social science research for understanding population processes and supporting policymaking and planning. Depending on the nature and scale, survey data sharing comes with privacy risks, and data collectors and agencies are constrained by disclosure permissions, limiting usage across research groups and institutes. Previous methods for synthetic data generation and deidentification may not entirely prevent information disclosures, or they may sacrifice data quality and granularity. Using a large-scale national voter file at both national and state levels, this paper introduces an end-to-end pipeline to streamline synthetic data generation and evaluation for survey researchers. This study selects four generative approaches based on different statistical assumptions: the regression-based Synthpop, the generative deep learning-based CTGAN and TVAE, and the large language model-based REaLDTabFormer, and compares them to the baseline synthetic minority oversampling technique (SMOTE). We consider three key dimensions of evaluation (utility, fidelity, and privacy) to highlight the strengths and weaknesses of each approach, and systematically evaluate across various datasets and training sizes. The results reveal that Synthpop is optimized for general utility (i.e., fidelity), while TVAE excels in downstream applications (i.e., target-specific utility) but compromises on general utility and potentially risks data overfitting. REaLDTabFormer demonstrates a balanced performance in both general and target-specific utility, whereas CTGAN offers the best privacy protection. We recommend that future researchers select a generative method by considering the trade-offs between performance across various evaluation dimensions, training size, data type, and computational infrastructure.
Shapley values (Shap) are a popular approach to explaining decisions of black-box models by revealing the importance of individual features. Shap explanations are easy to interpret, but as they do not incorporate feature interactions, they are also incomplete and potentially misleading. Interaction-aware methods such as nShap report the additive importance of all subsets up to n features. These explanations are complete, but in practice excessively large and difficult to interpret. In this paper, we combine the best of both worlds. We partition the features into significantly interacting groups, and use these to compose a succinct, interpretable explanation. To determine which partitioning out of super-exponentially many explains a model best, we derive a criterion that weighs the complexity of an explanation against its representativeness for the model's behavior. To be able to find the best partitioning, we show how to prune sub-optimal solutions using a statistical test. This not only improves runtime but also helps to avoid explaining spurious interactions. Experiments show that iShap represents underlying modeling more accurately than Shap and nShap, and a user study suggests that iShap is perceived as more interpretable and trustworthy.
Vertical federated learning (VFL) enables a privacy-preserving collaboration among various parties to train a global model by melding their geo-distributed data features. Communication has been recognized as the primary bottleneck that impairs training efficiency due to frequent cross-party statistics exchange over wide area network. Existing synchronous VFL works often suffer from excessive communication overhead, while asynchronous schemes may introduce significant model staleness, potentially eroding the learning accuracy. In this paper, we propose BS-VFL, an asynchronous VFL with bounded staleness, to pipeline local computation and statistics transmission, substantially reducing the communication overhead while ensuring favorable model performance. Specifically, all data parties will give precedence to local model updates before generating embeddings to curtail model staleness. By analyzing convergence error, we show that BS-VFL can achieve a comparable result to synchronous VFL. Then, we develop a general framework to derive the closed-form wall-clock time of BS-VFL, offering a measure of its runtime efficiency and highlighting a marked communication reduction. Utilizing this convergence and time analysis, we refine learning parameters to minimize the convergence error for optimizing BS-VFL performance without compromising training efficiency. Extensive experiments on real-world datasets validate the superiority of BS-VFL over leading-edge methods, evidencing a reduction in training duration by 48%-90% while preserving model accuracy.
Adversarial attacks are allegedly unnoticeable. Prior studies have designed attack noticeability measures on graphs, primarily using statistical tests to compare the topology of original and (possibly) attacked graphs. However, we observe two critical limitations in the existing measures. First, because the measures rely on simple rules, attackers can readily enhance their attacks to bypass them, reducing their attack ''noticeability'' and, yet, maintaining their attack performance. Second, because the measures naively leverage global statistics, such as degree distributions, they may entirely overlook attacks until severe perturbations occur, letting the attacks be almost ''totally unnoticeable.'' To address the limitations, we introduce HideNSeek, a learnable measure for graph attack noticeability. First, to mitigate the bypass problem, HideNSeek learns to distinguish the original and (potential) attack edges using a learnable edge scorer (LEO), which scores each edge on its likelihood of being an attack. Second, to mitigate the overlooking problem, HideNSeek conducts imbalance-aware aggregation of all the edge scores to obtain the final noticeability score. Using six real-world graphs, we empirically demonstrate that HideNSeek effectively alleviates the observed limitations, and LEO (i.e., our learnable edge scorer) outperforms eleven competitors in distinguishing attack edges under five different attack methods. For an additional application, we show that LEO boost the performance of robust GNNs by removing attack-like edges.
Traffic prediction is essential for intelligent transportation systems and urban computing. It aims to establish a relationship between historical traffic data X and future traffic states Y by employing various statistical or deep learning methods. However, the relations of X → Y are often influenced by external confounders that simultaneously affect both X and Y, such as weather, accidents, and holidays. Existing deep-learning traffic prediction models adopt the classic front-door and back-door adjustments to address the confounder issue. However, these methods have limitations in addressing continuous or undefined confounders, as they depend on predefined discrete values that are often impractical in complex, real-world scenarios. To overcome this challenge, we propose the Spatial-Temporal sElf-superVised confoundEr learning (STEVE) model. This model introduces a basis vector approach, creating a base confounder bank to represent any confounder as a linear combination of a group of basis vectors. It also incorporates self-supervised auxiliary tasks to enhance the expressive power of the base confounder bank. Afterward, a confounder-irrelevant relation decoupling module is adopted to separate the confounder effects from direct X → Y relations. Extensive experiments across four large-scale datasets validate our model's superior performance in handling spatial and temporal distribution shifts and underscore its adaptability to unseen confounders. Our model implementation is available at https://github.com/bigscity/STEVE_CODE.
Due to the non-stationarity of time series, the distribution shift problem largely hinders the performance of time series forecasting. Existing solutions either rely on using certain statistics to specify the shift, or developing specific mechanisms for certain network architectures. However, the former would fail for the unknown shift beyond simple statistics, while the latter has limited compatibility on different forecasting models. To overcome these problems, we first propose a decoupled formulation for time series forecasting, with no reliance on fixed statistics and no restriction on forecasting architectures. This formulation regards the removing-shift procedure as a special transformation between a raw distribution and a desired target distribution and separates it from the forecasting. Such a formulation is further formalized into a bi-level optimization problem, to enable the joint learning of the transformation (outer loop) and forecasting (inner loop). Moreover, the special requirements of expressiveness and bi-direction for the transformation motivate us to propose instance normalization flow (IN-Flow), a novel invertible network for time series transformation. Different from the classic ''normalizing flow'' models, IN-Flow does not aim for normalizing input to the prior distribution (e.g., Gaussian distribution) for generation, but creatively transforms time series distribution by stacking normalization layers and flow-based invertible networks, which is thus named ''normalization'' flow. Finally, we have conducted extensive experiments on both synthetic data and real-world data, which demonstrate the superiority of our method.
Human trajectory data, which plays a crucial role in various applications such as crowd management and epidemic prevention, is challenging to obtain due to practical constraints and privacy concerns. In this context, synthetic human trajectory data is generated to simulate as close as possible to real-world human trajectories, often under summary statistics and distributional similarities. However, these similarities oversimplify complex human mobility patterns (a.k.a. ''Datasaurus''), resulting in intrinsic biases in both generative model design and benchmarks of the generated trajectories. Against this background, we propose MIRAGE, a huMan-Imitative tRAjectory GenErative model designed as a neural Temporal Point Process integrating an Exploration and Preferential Return model. It imitates the human decision-making process in trajectory generation, rather than fitting any specific statistical distributions as traditional methods do, thus avoiding the Datasaurus issue. We also propose a comprehensive task-based evaluation protocol beyond Datasaurus to systematically benchmark trajectory generative models on four typical downstream tasks, integrating multiple techniques and evaluation metrics for each task, to assess the ultimate utility of the generated trajectories. We conduct a thorough evaluation of MIRAGE on three real-world user trajectory datasets against a sizeable collection of baselines. Results show that compared to the best baselines, MIRAGE-generated trajectory data not only achieves the best statistical and distributional similarities with 59.0-67.7% improvement, but also yields the best performance in the task-based evaluation with 10.9-33.4% improvement. A series of ablation studies also validate the key design choices of MIRAGE.
Medication recommendation (MR) has undergone rapid advancement in recent years, driven by its significant practical implications in healthcare. However, such high-risk scenarios still experience two critical yet overlooked challenges: the prevalent overconfidence in raw confidence for individual medications and the lack of a robust solution for confidence quantification in medication combinations. This paper represents the first in-depth study addressing this gap. We introduce two innovative methodologies tailored to the unique challenges of MR scenarios: 1) A discernible binning-based calibration method with theoretical guarantees for the confidence of individual medication. It guarantees distinct accuracy levels between adjacent bins and maintains consistent statistical reliability across calibration and test data, enabling calibrated confidence to reflect the correctness of medication recommendations distinctively. 2) A sample-based quantification method for the set confidence of medication combination, which is applicable for various existing performance metrics in MR. Utilizing representative deep MR models as backbones and conducting extensive experiments on the widely recognized MIMIC datasets, we empirically prove the effectiveness and robustness of our proposed methods. Our approaches not only improve the reliability of MR but also pave the way for more informed decision-making in clinical settings.
Causal discovery (CD) and Large Language Models (LLMs) have emerged as transformative fields in artificial intelligence that have evolved largely independently. While CD specializes in uncovering cause-effect relationships from data, and LLMs excel at natural language processing and generation, their integration presents unique opportunities for advancing causal understanding. This survey examines how LLMs are transforming CD across three key dimensions: direct causal extraction from text, integration of domain knowledge into statistical methods, and refinement of causal structures. We systematically analyze approaches that leverage LLMs for CD tasks, highlighting their innovative use of metadata and natural language for causal inference. Our analysis reveals both LLMs' potential to enhance traditional CD methods and their current limitations as imperfect expert systems. We identify key research gaps, outline evaluation frameworks and benchmarks for LLM-based causal discovery, and advocate future research efforts for leveraging LLMs in causality research. As the first comprehensive examination of the synergy between LLMs and CD, this work lays the groundwork for future advances in the field.
Accurate trajectory prediction has long been a major challenge for autonomous driving (AD). Traditional data-driven models predominantly rely on statistical correlations, often overlooking the causal relationships that govern traffic behavior. In this paper, we introduce a novel trajectory prediction framework that leverages causal inference to enhance predictive robustness, generalization, and accuracy. By decomposing the environment into spatial and temporal components, our approach identifies and mitigates spurious correlations, uncovering genuine causal relationships. We also employ a progressive fusion strategy to integrate multimodal information, simulating human-like reasoning processes and enabling real-time inference. Evaluations on five real-world datasets—ApolloScape, nuScenes, NGSIM, HighD, and MoCAD—demonstrate our model's superiority over existing state-of-the-art (SOTA) methods, with improvements in key metrics such as RMSE and FDE. Our findings highlight the potential of causal reasoning to transform trajectory prediction, paving the way for robust AD systems.
Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction
PDF ↗Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, GCM outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate representation of complex climate phenomena. Traditional bias correction methods, which rely on historical observation data and statistical techniques, often neglect unobserved confounders, leading to biased results. This paper proposes a novel bias correction approach to utilize both GCM and observational data to learn a factor model that captures multi-cause latent confounders. Inspired by recent advances in causality based time series deconfounding, our method first constructs a factor model to learn latent confounders from historical data and then applies them to enhance the bias correction process using advanced time series forecasting models. The experimental results demonstrate significant improvements in the accuracy of precipitation outputs. By addressing unobserved confounders, our approach offers a robust and theoretically grounded solution for climate model bias correction.
Reasoning under uncertainty is a fundamental challenge in Artificial Intelligence. As with most of these challenges, there is a harsh dilemma between the expressive power of the language used, and the tractability of the computational problem posed by reasoning. Inspired by human reasoning, we introduce a method of first-order relational probabilistic inference that satisfies both criteria, and can handle hybrid (discrete and continuous) variables. Specifically, we extend sum-of-squares logic of expectation to relational settings, demonstrating that lifted reasoning in the bounded-degree fragment for knowledge bases of bounded quantifier rank can be performed in polynomial time, even with an a priori unknown and/or countably infinite set of objects. Crucially, our notion of tractability is framed in proof-theoretic terms, which extends beyond the syntactic properties of the language or queries. We are able to derive the tightest bounds provable by proofs of a given degree and size and establish completeness in our sum-of-squares refutations for fixed degrees.
With the rapid development and deep integration of artificial intelligence and automation technologies, autonomous unmanned swarms dynamically organize into multiplex network structures based on diverse task requirements in adversarial environments. Frequent task variations lead to load imbalances among agents and between network layers, significantly increasing the risk of enemy detection and destruction. Existing approaches typically simplify multiplex networks into single-layer structures for task scheduling, failing to address these load imbalance issues. Moreover, the coupling between task dynamics and network multiplexity dramatically increases the complexity of designing task migration strategies, and it is proven NP-hard to achieve such load balancing. To address these challenges, this paper proposes a risk-aware task migration method that achieves dynamic load balancing by matching task requirements with both intra-layer agent capabilities and inter-layer swarm capabilities. Simulation results demonstrate that our approach significantly outperforms benchmark algorithms in task completion cost, task completion proportion, and system robustness. In particular, the algorithm achieves solutions statistically indistinguishable from the optimal solutions computed by the CPLEX solver, while exhibiting significantly reduced computational overhead.
Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern
PDF ↗Accurate forecasting of time series is crucial for many applications in the real world. Conventional methods primarily rely on statistical analysis of historical data, often leading to overfitting and failing to account for background information and constraints imposed by external events. Therefore, introducing large language models (LLMs) with robust textual capabilities holds significant potential. However, due to the inherent limitations of LLMs in handling numerical data, they do not exhibit advantages in precise numerical prediction tasks. Therefore, we propose a framework to integrate LLMs with conventional methods synergistically. Rather than directly outputting numerical predictions, we leverage the capabilities of the LLMs to generate textual temporal patterns, thereby fully utilizing their inherent knowledge and reasoning abilities. Additionally, we introduce a memory network designed to decode these textual representations into a format that numerical models can effectively interpret. This approach not only capitalizes on the strengths of the LLM in text processing but also bridges the gap between textual and numerical data, enhancing the overall predictive performance of the model. Our experimental results demonstrate the framework's effectiveness, achieving state-of-the-art performance on various benchmark datasets.
This paper presents an evolvable conditional diffusion method such that black-box, non-differentiable multi-physics models, as are common in domains like computational fluid dynamics and electromagnetics, can be effectively used for guiding the generative process to facilitate autonomous scientific discovery. We formulate the guidance as an optimization problem where one optimizes for a desired fitness function through updates to the descriptive statistic for the denoising distribution, and derive an evolution-guided approach from first principles through the lens of probabilistic evolution. Interestingly, the final derived update algorithm is analogous to the update as per common gradient-based guided diffusion models, but without ever having to compute any derivatives. We validate our proposed evolvable diffusion algorithm in two AI for Science scenarios: the automated design of fluidic topology and meta-surface. Results demonstrate that this method effectively generates designs that better satisfy specific optimization objectives without reliance on differentiable proxies, providing an effective means of guidance-based diffusion that can capitalize on the wealth of black-box, non-differentiable multi-physics numerical models common across Science.
SCNNs: Spike-based Coupling Neural Networks for Understanding Structural-Functional Relationships in the Human Brain
PDF ↗Structural-functional coupling (SC-FC coupling) offers an effective approach for analyzing structural-functional relationships, capable of revealing the dependency of functional activity on the underlying white matter architecture. However, extant SC-FC coupling analysis methods primarily center on disclosing the statistical association between the topological patterns of structural connectivity (SC) and functional connectivity (FC), while often neglecting the neurobiological mechanisms by which the brain typically transmits and processes information in the form of spikes. To address this, we propose a biologically inspired deep-learning model called spike-based coupling neural networks (SCNNs). It can simulate spiking neural activity to more realistically reproduce the interaction between brain regions and the dynamic behavior of neuronal networks. Specifically, we first use spike neurons to capture the FC temporal characteristics of the original functional magnetic resonance imaging (fMRI) time series and the SC spatial characteristics of the structural brain network. Then, we use synaptic and neuronal filter effects to simulate the coupling mechanism of SC and FC in the brain at different temporal and spatial scales, thereby quantifying SC-FC coupling and providing support for the identification of brain diseases. The results on real datasets show that the proposed method can identify brain diseases and provide a new perspective for understanding SC-FC relationships.
FedCM: Client Clustering and Migration in Federated Learning via Gradient Path Similarity and Update Direction Deviation
PDF ↗Federated learning (FL) enables collaborative training among multiple clients while preserving data privacy. However, its practical application is significantly limited by two major challenges: statistical heterogeneity and data distribution drift. Statistical heterogeneity causes the direction of local model updates to deviate from the global training objective, while data distribution drift leads to a mismatch between local models and their cluster models. To address these challenges, this paper proposes an adaptive clustered federated learning framework, Fed-CM. Initially, by capturing the dynamic patterns of personalized layer parameters in clients' models, Fed-CM effectively characterizes the correlations and distributional similarities among clients, reflecting the underlying statistical heterogeneity. Subsequently, this framework leverages client similarities to construct an undirected graph and adaptively performs effective cluster discovery with minimal dependence on hyperparameters. Furthermore, a monitoring strategy tracks the deviation between clients’ update directions and the dominant update direction of their clusters and then adaptively migrates clients experiencing data drift. Such a dynamic strategy helps maintain intra-cluster homogeneity and addresses the mismatch between local models and their cluster models. Compared to other state-of-the-art methods, experimental results on multiple datasets demonstrate that the proposed Fed-CM framework effectively addresses the challenges posed by statistical heterogeneity and data drift, significantly improving the performance and robustness of federated learning models.