Standard tokenizers over-fragment domain terms, disrupting morpheme semantics.We characterize this representational misalignment as Structural Knowledge Collapse (SKC), where attention mechanisms fail to reconstruct coherent concepts from fragmented inputs.While existing input-centric solutions like vocabulary expansion address this, they necessitate expensive embedding retraining and neglect internal attention compositionality.To this end, we introduce Morphemeaware KV-aggregation Attention (MorphKA), a lightweight adapter that dynamically consolidates fragments without tokenizer changes.Bypassing tokenizer retraining, MorphKA employs a dual-phase strategy-Input-Level Morpheme Aggregation (IMA) and Context-Aware KV-Aggregation (AMRF)-to stabilize morpheme spans and synthesize higher-order concepts.Experiments on medical and legal benchmarks show MorphKA outperforms vocabulary adaptation baselines by 3.2-4.6%,reaching 7.9% on high-fragmentation terms.Moreover, MorphKA reduces catastrophic interference on general capabilities by 18-22% with ∼80% fewer parameters than embedding retraining approaches.

The rapid accumulation of large-scale Electronic Health Records (EHR) presents considerable opportunities to generate real-world evidence to inform clinical decision-making and accelerate drug development. However, the complexity of EHR has turned them into a formidable testing ground for cutting-edge AI algorithms. Furthermore, a significant gap still exists between algorithm development in the computer science community and clinical translation within the healthcare community. This tutorial aims to bridge this divide by fostering mutual understanding between the two communities by discussing using advanced machine learning and data mining technologies tailored to tackle real-world healthcare challenges, including 1) using EHR and trial emulation for understanding Long Covid and drug repurposing for Alzheimer's disease, and 2) risk prediction and associated fairness, interpretability, generalizability, etc., issues. We will conclude this tutorial by delving into potential opportunities for future research and unveiling the prospects of a career as a health data scientist.

Contrastive learning has demonstrated promising performance in image and text domains either in a self-supervised or a supervised manner. In this work, we extend the supervised contrastive learning framework to clinical risk prediction problems based on longitudinal electronic health records (EHR). We propose a general supervised contrastive loss $\mathcal{L}$Contrastive Cross Entropy+$\lambda \mathcal{L}$Supervised Contrastive Regularizerfor learning both binary classification (e.g. in-hospital mortality prediction) and multi-label classification (e.g. phenotyping) in a unified framework. Our supervised contrastive loss practices the key idea of contrastive learning, namely, pulling similar samples closer and pushing dissimilar ones apart from each other, simultaneously by its two components: $\mathcal{L}$Contrastive Cross Entropytries to contrast samples with learned anchors which represent positive and negative clusters, and $\mathcal{L}$Supervised Contrastive Regularizertries to contrast samples with each other according to their supervised labels. We propose two versions of the above supervised contrastive loss and our experiments on real-world EHR data demonstrate that our proposed loss functions show benefits in improving the performance of strong baselines and even state-of-the-art models on benchmarking tasks for clinical risk predictions. Our loss functions work well with extremely imbalanced data which are common for clinical risk prediction problems. Our loss functions can be easily used to replace (binary or multi-label) cross-entropy loss adopted in existing clinical predictive models. The Pytorch code is released at https://github.com/calvin-zcx/SCEHR.

Graph is a natural representation encoding both the features of the data samples and relationships among them. Analysis with graphs is a classic topic in data mining and many techniques have been proposed in the past. In recent years, because of the rapid development of data mining and knowledge discovery, many novel graph analytics algorithms have been proposed and successfully applied in a variety of areas. The goal of this tutorial is to summarize the graph analytics algorithms developed recently and how they have been applied in healthcare. In particular, our tutorial will cover both the technical advances and the application in healthcare. On the technical aspect, we will introduce deep network embedding techniques, graph neural networks, knowledge graph construction and inference, graph generative models and graph neural ordinary differential equation models. On the healthcare side, we will introduce how these methods can be applied in predictive modeling of clinical risks (e.g., chronic disease onset, in-hospital mortality, condition exacerbation, etc.) and disease subtyping with multi-modal patient data (e.g., electronic health records, medical image and multi-omics), knowledge discovery from biomedical literature and integration with data-driven models, as well as pharmaceutical research and development (e.g., de-novo chemical compound design and optimization, patient similarity for clinical trial recruitment and pharmacovigilance). We will conclude the whole tutorial with a set of potential issues and challenges such as interpretability, fairness and security. In particular, considering the global pandemic of COVID-19, we will also summarize the existing research that have already leveraged graph analytics to help with the understanding the mechanism, transmission, treatment and prevention of COVID-19, as well as point out the available resources and potential opportunities for future research.

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two steps: learning latent representations and generation of molecular graphs. However, to generate novel and chemically-valid molecular graphs from latent representations is very challenging because of the chemical constraints and combinatorial complexity of molecular graphs. In this paper, we propose MoFlow, a flow-based graph generative model to learn invertible mappings between molecular graphs and their latent representations. To generate molecular graphs, our MoFlow first generates bonds (edges) through a Glow based model, then generates atoms (nodes) given bonds by a novel graph conditional flow, and finally assembles them into a chemically valid molecular graph with a posthoc validity correction. Our MoFlow has merits including exact and tractable likelihood training, efficient one-pass embedding and generation, chemical validity guarantees, 100% reconstruction of training data, and good generalization ability. We validate our model by four tasks: molecular graph generation and reconstruction, visualization of the continuous latent space, property optimization, and constrained property optimization. Our MoFlow achieves state-of-the-art performance, which implies its potential efficiency and effectiveness to explore large chemical space for drug discovery.

Learning continuous-time dynamics on complex networks is crucial for understanding, predicting, and controlling complex systems in science and engineering. However, this task is very challenging due to the combinatorial complexities in the structures of high dimensional systems, their elusive continuous-time nonlinear dynamics, and their structural-dynamic dependencies. To address these challenges, we propose to combine Ordinary Differential Equation Systems (ODEs) and Graph Neural Networks (GNNs) to learn continuous-time dynamics on complex networks in a data-driven manner. We model differential equation systems by GNNs. Instead of mapping through a discrete number of neural layers in the forward process, we integrate GNN layers over continuous time numerically, leading to capturing continuous-time dynamics on graphs. Our model can be interpreted as a Continuous-time GNN model or a Graph Neural ODEs model. Our model can be utilized for continuous-time network dynamics prediction, structured sequence prediction (a regularly-sampled case), and node semi-supervised classification tasks (a one-snapshot case) in a unified framework. We validate our model by extensive experiments in the above three scenarios. The promising experimental results demonstrate our model's capability of jointly capturing the structure and dynamics of complex systems in a unified framework.

A social network is an ecosystem, and one of its ultimate goals is to maintain itself sustainable, namely keeping users generating information and being informed. However, the reasons why some social ecosystems can keep self-sustaining and others end up with non-active or dead states are largely unknown.

Recent years witness the merge of social networks and user-generated content (UGC) platforms. In these new platforms, users establish links to others not only driven by their social relationships in the physical world but also driven by the contents published by others. During this merging process, social networks gradually integrate both social and content links and become unprecedentedly complicated, with the motivation to exploit both the advantages of social viscosity and content attractiveness to reach the best customer retention situation. However, due to the lack of fine-grained data recording such merging phenomena, the co-driven mechanism of social and content links in churn remains unexplored. How do social and content factors jointly influence customers' churn? What is the best ratio of social and content links for retention? Is there a model to capture this co-driven mechanism in churn phenomena? In this paper, we collect a real-world dataset with more than 5.77 million users and 1.15 billion links, with each link being tagged as a social one or a content one. We find that both social and content links have a significant impact on users' churn and they work jointly as a complicated mixture effect. As a result, we propose a novel survival model, which incorporates both social and content factors, to predict churn probability over time. Our model successfully fits the churn distribution in reality and accurately predicts the churn rate of different subpopulations in the future. By analyzing the modeling parameters, we try to strike a balance between social-driven and content-driven links in a user's social network to reach the lowest churn rate. Our model and findings may have potential implications for the design of future social media.

Pattern formation is a ubiquitous phenomenon that describes the generation of orderly outcomes by self-organization. In both physical society and online social media, patterns formed by social interactions are mainly driven by information flow. Despite an increasing number of studies aiming to understand the spreads of information flow, little is known about the geometry of these spreading patterns and how they were formed during the spreading. In this paper, by exploring 432 million information flow patterns extracted from a large-scale online social media dataset, we uncover a wide range of complex geometric patterns characterized by a three-dimensional metric space. In contrast, the existing understanding of spreading patterns are limited to fanning-out or narrow tree-like geometries. We discover three key ingredients that govern the formation of complex geometric patterns of information flow. As a result, we propose a stochastic process model incorporating these ingredients, demonstrating that it successfully reproduces the diverse geometries discovered from the empirical spreading patterns. Our discoveries provide a theoretical foundation for the microscopic mechanisms of information flow, potentially leading to wide implications for prediction, control and policy decisions in social media.

Many real-world problems are time-evolving in nature, such as the progression of diseases, the cascading process when a post is broadcasting in a social network, or the changing of climates. The observational data characterizing these complex problems are usually only available at discrete time stamps, this makes the existing research on analyzing these problems mostly based on a cross-sectional analysis. In this paper, we try to model these time-evolving phenomena by a dynamic system and the data sets observed at different time stamps are probability distribution functions generated by such a dynamic system. We propose a theorem which builds a mathematical relationship between a dynamical system modeled by differential equations and the distribution function (or survival function) of the cross-sectional states of this system. We then develop a survival analysis framework to learn the differential equations of a dynamical system from its cross-sectional states. With such a framework, we are able to capture the continuous-time dynamics of an evolutionary system.We validate our framework on both synthetic and real-world data sets. The experimental results show that our framework is able to discover and capture the generative dynamics of various data distributions accurately. Our study can potentially facilitate scientific discoveries of the unknown dynamics of complex systems in the real world.

The collective behavior, describing spontaneously emerging social processes and events, is ubiquitous in both physical society and online social media. The knowledge of collective behavior is critical in understanding and predicting social movements, fads, riots and so on. However, detecting, quantifying and modeling the collective behavior in online social media at large scale are seldom unexplored. In this paper, we examine a real-world online social media with more than 1.7 million information spreading records, which explicitly document the detailed human behavior in this online information cascading system. We observe evident collective behavior in information cascading, and then propose metrics to quantify the collectivity. We find that previous information cascading models cannot capture the collective behavior in the real-world and thus never utilize it. Furthermore, we propose a generative framework with a latent user interest layer to capture the collective behavior in cascading system. Our framework achieves high accuracy in modeling the information cascades with respect to popularity, structure and collectivity. By leveraging the knowledge of collective behavior, our model shows the capability of making predictions without temporal features or early-stage information. Our framework can serve as a more generalized one in modeling cascading system, and, together with empirical discovery and applications, advance our understanding of human behavior.

To fit empirical data distributions and then interpret them in a generative way is a common research paradigm to understand the structure and dynamics underlying the data in various disciplines. However, previous works mainly attempt to fit or interpret empirical data distributions in a case-by-case way. Faced with complex data distributions in the real world, can we fit and interpret them by a unified but parsimonious parametric model? In this paper, we view the complex empirical data as being generated by a dynamic system which takes uniform randomness as input. By modeling the generative dynamics of data, we showcase a four-parameter dynamic model together with inference and simulation algorithms, which is able to fit and generate a family of distributions, ranging from Gaussian, Exponential, Power Law, Stretched Exponential (Weibull), to their complex variants with multi-scale complexities. Rather than a black box, our model can be interpreted by a unified differential equation, which captures the underlying generative dynamics. More powerful models can be constructed by our framework in a principled way. We validate our model by various synthetic datasets. We then apply our model to $16$ real-world datasets from different disciplines. We show the systematic biases of fitting these datasets by the most widely used methods and show the superiority of our model. In short, our model potentially provides a framework to fit complex distributions in empirical data, and more importantly, to understand their generative mechanisms.

What is the growth dynamics of social networks, like Facebook or WeChat? Does it truly exhibit exponential early-growth, as predicted by the celebrated models, like the Bass model? How about the dynamics of links, for which there are few published models? For the first time, we examine the growth of WeChat which is the largest online social network in China, together with several other real social networks. We observe Power-Law growth dynamics for both nodes and links, a fact that breaks the textbook models featuring Sigmoid curves. We propose NETTIDE, along with differential equations for the growth of nodes and links. Our model fits the growth dynamics of real social networks well; it encompasses many traditional growth dynamics as special cases, while remaining parsimonious in parameters. The NETTIDE for link growth is the first one of its kind, accurately fitting real data, and capturing densification phenomenon. We further formulate two stochastic generators, which interpret the growth of nodes and links through survival analysis and micro-level interactions within a social network, respectively. The proposed generators reproduce realistic growth dynamics of social networks. When applied on the WeChat data, our NETTIDE forecasted > 730 days ahead with 3 percent error.

How do people make friends dynamically in social networks? What are the temporal patterns for an individual increasing its social connectivity? What are the basic mechanisms governing the formation of these temporal patterns? No matter cyber or physical social systems, their structure and dynamics are mainly driven by the connectivity dynamics of each individual. However, due to the lack of empirical data, little is known about the empirical dynamic patterns of social connectivity at microscopic level, let alone the regularities or models governing these microscopic dynamics.

What is the growth pattern of social networks, like Facebook and WeChat? Does it truly exhibit exponential early growth, as predicted by textbook models like the Bass model, SI, or the Branching Process? How about the count of links, over time, for which there are few published models?