Recent advances in neural Granger causal methods have shown promise in modeling temporal nonlinear dependencies. However, existing approaches remain confined to raw time-series data, inherently lacking contextual semantics and tending to overfit, which undermines their real-world applicability. To address these challenges, we propose LLM-GC, a novel LLM-empowered multimodal Granger causality discovery framework that enriches unimodal temporal dynamics with semantic priors and world knowledge distilled from large language models (LLMs). LLM-GC leverages dual-modality encoding to capture and align temporal and contextual dynamics by Cross-Modal Dual Retrieval while avoiding causal entanglement across modalities. To extract multimodal causal features, we introduce a causality-aware self-attention mechanism by simply inverting the conventional self-attention structure, enabling a shared causality augmenter to effectively highlight consistent causal patterns across modalities. LLM-GC is the first to bridge LLMs and Granger causality, and experiments on synthetic and real-world benchmark datasets demonstrate that LLM-GC outperforms existing state-of-the-art methods in Granger causal discovery.

Discovering Granger causality from time series data is fundamental to understanding dynamic systems, yet most existing methods struggle with unknown intervention targets or causal structures in real-world scenarios. In this paper, we propose DiffuGC, a novel diffusion-based framework that unifies observational and interventional causal discovery through a generative denoising process. By introducing diffusive interventions, which apply progressive interventions without any prior knowledge, DiffuGC amplifies causal signals while preserving structural information. Furthermore, we introduce a denoising NoiFormer with adaptive attention to both short- and long-term causal dependencies, which disentangles trend and seasonal components to enable accurate reconstruction of causal structures from interventional data. To the best of our knowledge, we are the first to integrate diffusion models with interventional Granger causal discovery. Extensive experiments on synthetic, quasi-real, and real-world benchmarks demonstrate that DiffuGC consistently outperforms state-of-the-art baselines in both observational and interventional data. Moreover, we introduce an intriguing notion, Causality Acceleration, characterized by the early emergence of informative causal patterns within the diffusion path, which may open up promising directions for future research on efficient and adaptive causal discovery.

Length of Stay (LoS) estimation is important for efficient healthcare resource management. Since the distribution of LoS is highly skewed, some previous works frame the LoS estimation as a multi-class classification problem by dividing the range of LoS into buckets. However, they ignore the ordinal relationship between labels. The distribution of bucketed LoS, with a heavy head and a heavy tail, is still imbalanced since the long tail is grouped into the last bucket. This paper proposes a Deep Ordinal neural network for Length of stay Estimation in the intensive care units (DOSE). DOSE can exploit the ordinal relationship and mitigate the skewness. The ordinal classification problem is decomposed into a series of binary classification sub-problems by using multiple binary classifiers. To maintain consistency among binary classifiers, the monotonicity constraint penalty is proposed. The number of samples whose labels are higher or lower than a given threshold is at the same level due to the heavy head and tail of the distribution. Therefore, the training data of each binary classifier are balanced. Experiments are conducted on the real-world healthcare dataset. DOSE outperforms all baseline methods in all metrics. The distribution of the prediction of DOSE is more aligned with the ground truth.

In the real world, the class of a time series is usually labeled at the final time, but many applications require to classify time series at every time point. e.g. the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. Thus, we propose a new concept: Continuous Classification of Time Series (CCTS). It requires the model to learn data in different time stages. But the time series evolves dynamically, leading to different data distributions. When a model learns multi-distribution, it always forgets or overfits. We suggest that meaningful learning scheduling is potential due to an interesting observation: Measured by confidence, the process of model learning multiple distributions is similar to the process of human learning multiple knowledge. Thus, we propose a novel Confidence-guided method for CCTS (C3TS). It can imitate the alternating human confidence described by the Dunning-Kruger Effect. We define the objective-confidence to arrange data, and the self-confidence to control the learning duration. Experiments on four real-world datasets show that C3TS is more accurate than all baselines for CCTS.

Electronic Health Records (EHR) is the repository of patients' involved medical codes in the hospital, including diagnosis codes, medication codes, procedure codes, lab codes, and so on. EHR inherently contains various kinds of relationships such as the code-code, the patient-patient, and the patient-code relationship. Recent research shows that graph representation learning can be an effective tool for capturing complex relationships. However, none of the existing methods considered high-order interactions between patients and medical codes or considered the three relationships together. In this paper, we propose Hypergraph Contrastive Learning (HCL), to jointly learn patient embeddings and code embeddings from the combination of the above three relationships. HCL first constructs a hypergraph from the EHR data. Then, the medical code graph and the patient graph are constructed based on the hypergraph. Empowered with hypergraph attention network, Transformer, and graph attention network, HCL learns representations from three graphs respectively. Next, contrastive learning is applied to aggregate information from these graphs. Finally, the learned representations can support downstream tasks in supervised learning settings and self-supervised learning settings. Experiments are conducted on eICU and MIMIC-III datasets with mortality prediction and readmission prediction tasks. Results show that our method outperforms almost all compared methods on all evaluation metrics and HCL can learn patient representations from medical codes even without labeled data.

Since data is presented long-tailed in reality, it is challenging for Federated Learning (FL) to train across decentralized clients as practical applications. We present Global-Regularized Personalization (GRP-FED) to tackle the data imbalanced issue by considering a single global model and multiple local models for each client. With adaptive aggregation, the global model treats multiple clients fairly and mitigates the global long-tailed issue. Each local model is learned from the local data and aligns with its distribution for customization. To prevent the local model from just overfitting, GRP-FED applies an adversarial discriminator to regularize between the learned global-local features. Extensive results show that our GRP-FED improves under both global and local scenarios on real-world MIT-BIH and synthesis CIFAR-10 datasets, achieving comparable performance and addressing client imbalance.

Pattern management is an important task in data stream mining and has attracted increasing attention recently. Variations of data stream patterns typically imply some fundamental changes of underlying objects and possess significant domain meanings. Many database applications require investigating the history information to get the knowledge about the evolving process of data streams. However, in most circumstances, the data stream patterns are unstructured: limited memory space cannot record all the patterns discovered online, no training sets or predefined models are available, and large numbers of noises bring another non-trivial challenge. This paper presents our research effort in online pattern management over such streams. A novel algorithm is proposed to detect stream changes, organize meaningful patterns and distinguish useful variations from noises. It extracts new trends from unstructured data heuristically, and involves a special parameter to identify whether the current event should be treated as significant. Several experiments are performed and the results prove this new method feasible and efficient.

Widely applied in many domains, data stream processing has attracted more and more attention in database and sensor network communities. In this demo, we present our system PEDS-VM, a real-time surveillance system for managing pattern variation over evolving medical streams. PEDS-VM utilizes an effective strategy and a state-based window framework to extract the evolving patterns. After extraction, PEDS-VM uses a novel storage structure called PGG to efficiently record these incremental patterns. Moreover, several important application scenarios of PEDS-VM are also discussed in this demonstration.

Many database applications require the analysis and processing of data streams. In such systems, huge amounts of data arrive rapidly and their values change over time. The variations on streams typically imply some fundamental changes of the underlying objects and possess significant domain meanings. In some data streams, successive events seem to recur in a certain time interval, but the data indeed evolves with tiny differences as time elapses. This feature is called pseudo periodicity, which poses a non-trivial challenge to variation management in data streams. This paper presents our research effort in online variation management over such streams, and the idea can be applied to the problem domain of medical applications, such as patient vital signal monitoring. We propose a new method named Pattern Growth Graph (PGG) to detect and manage variations over pseudo periodical streams. PGG adopts the wave-pattern to capture the major information of data evolution and represent them compactly. With the help of wave-pattern matching algorithm, PGG detects the stream variations in a single pass over the stream data. PGG only stores the different segments of the pattern for incoming stream, and hence it can substantially compress the data without losing important information. The statistical information of PGG helps to distinguish meaningful data changes from noise and to reconstruct the stream with acceptable accuracy. Extensive experiments on real datasets containing millions of data items demonstrate the feasibility and effectiveness of the proposed scheme.