Missing values are prevalent in multivariate time series, compromising the integrity of analyses and degrading the performance of downstream tasks. Consequently, research has focused on multivariate time series imputation, aiming to accurately impute the missing values based on available observations. A key research question is how to ensure imputation consistency, i.e., intra-consistency between observed and imputed values, and inter-consistency between adjacent windows after imputation. However, previous methods rely solely on the inductive bias of the imputation targets to guide the learning process, ignoring imputation consistency and ultimately resulting in poor performance. Diffusion models, known for their powerful generative abilities, prefer to generate consistent results based on available observations. Therefore, we propose a conditional diffusion model for Multivariate Time Series Consistent Imputation (MTSCI). Specifically, MTSCI employs a contrastive complementary mask to generate dual views during the forward noising process. Then, the intra contrastive loss is calculated to ensure intra-consistency between the imputed and observed values. Meanwhile, MTSCI utilizes a mixup mechanism to incorporate conditional information from adjacent windows during the denoising process, facilitating the inter-consistency between imputed samples. Extensive experiments on multiple real-world datasets demonstrate that our method achieves the state-of-the-art performance on multivariate time series imputation task under different missing scenarios. Code is available at https://github.com/JeremyChou28/MTSCI.
6 June 2025 in ACM Transactions on Knowledge Discovery From Data
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noise. Moreover, we observe prevalent over-smoothed interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose M
ask-
a
ware
g
raph
i
mputation
Net
work
: MagiNet . Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothed imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE under Missing Completely At Random (MCAR) pattern. Code is available at https://github.com/JeremyChou28/MagiNet .
With the advent of big data science, the field of geoscience has undergone a paradigm shift toward data-driven scientific discovery. However, the abundance of geoscience data distributed across multiple sources poses significant challenges to researchers in terms of data compilation, which includes data collection, collation, and database construction. To streamline the data compilation process, we present GeoKnowledgeFusion, a publicly accessible platform for the fusion of text, visual, and tabular knowledge extracted from the geoscience literature. GeoKnowledgeFusion leverages a powerful network of models that provide a joint multimodal understanding of text, image, and tabular data, enabling researchers to efficiently curate and continuously update their databases. To demonstrate the practical applications of GeoKnowledgeFusion, we present two scenarios: the compilation of Sm-Nd isotope data for constructing a domain-specific database and geographic analysis, and the data extraction process for debris flow disasters. The data compilation process for these use cases encompasses various tasks, including PDF pre-processing, target element recognition, human-in-the-loop annotation, and joint multimodal knowledge understanding. The findings consistently reveal patterns that align with manually compiled data, thus affirming the credibility and dependability of our automated data processing tool. To date, GeoKnowledgeFusion has supported forty geoscience research teams within the program by processing over 40,000 documents uploaded by geoscientists.
18 July 2024 in IEEE Transactions on Audio, Speech and Language Processing
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially in real-world applications with limited resources. To mitigate the limitation of insufficient labeled data, we propose a novel framework: Adapt-Knowledge-to-Generate (AKG). The core insight of AKG is to adapt unlabeled domain-specific knowledge into the model, which brings at least three benefits: (1) it injects representation of normal table-related descriptions to bridge the topological gap between tabular data and texts; (2) it enables us to use large amounts of unlabeled domain-specific knowledge fully, which can alleviate the PLMs' inherent shortcomings of lacking domain knowledge; (3) it allows us to design various tasks to employ the domain-specific knowledge. Extensive experiments and analyses are conducted on three open-domain, few-shot natural language generation (NLG) data sets: Humans, Songs, and Books. Compared to previous state-of-the-art approaches, our model achieves superior performance in terms of both fluency and accuracy as judged by human and automatic evaluations.
16 March 2026 in IEEE Transactions on Knowledge and Data Engineering
The deployment of sensors enables data-driven urban management, but necessitates inductive spatio-temporal kriging to infer unmonitored areas. Existing methods impute these unknown observations by smoothing temporal features based on spatial dependencies, overlooking the decoupling of inherent properties and dynamic correlations in message passing. In particular, the inherent properties reveal non-transitive signals, and current coupled aggregation leads to inaccurate results. To this end, we propose TempoRAl deCoupled Kriging, named TRACK, to decouple two factors with the help of node-specific inherency. Specifically, we first construct a node-specific profile to represent its inherency including geographical and periodic features, which is subsequently transformed into decoupling prompts. Secondly, the coupled temporal features are separated through querying each prompt embedding, facilitating precise temporal aggregation for inherent properties and spatial aggregation for dynamic correlations. Finally, a multi-task training strategy is further adopted to mimic the inductive scenarios during testing. We evaluate TRACK on four real-world datasets spanning urban traffic and air quality prediction tasks. TRACK achieves state-of-the-art performance, with average improvements of 3.10% in MAE and 4.45% in RMSE over strong baselines. Moreover, we further demonstrated its robust generalization in a challenging cross-city inductive setting.