Sparse Data Research Articles

Compiling Recurrences over Dense and Sparse Arrays

We present a framework for compiling recurrence equations into native code. In our framework, users specify a system of recurrences, the types of data structures that store inputs and outputs, and scheduling commands for optimization. Our compiler then lowers these specifications into native code that respects the dependencies in the recurrence equations. Our compiler can generate code over both sparse and dense data structures, and determines if the recurrence system is solvable with the provided scheduling primitives. We evaluate the performance and correctness of the generated code on several recurrences, from domains as diverse as dense and sparse matrix solvers, dynamic programming, graph problems, and sparse tensor algebra. We demonstrate that the generated code has competitive performance to hand-optimized implementations in libraries. However, these handwritten libraries target specific recurrences, specific data structures, and specific optimizations. Our system, on the other hand, automatically generates implementations from recurrences, data formats, and schedules, giving our system more generality than library approaches.

Beyond Relevance: Factor-level Causal Explanation for User Travel Decisions with Counterfactual Data Augmentation

Point-of-Interest (POI) recommendation, an important research hotspot in the field of urban computing, plays a crucial role in urban construction. While understanding the process of users’ travel decisions and exploring the causality of POI choosing is not easy due to the complex and diverse influencing factors in urban travel scenarios. Moreover, the spurious explanations caused by severe data sparsity, i.e., misrepresenting universal relevance as causality, may also hinder us from understanding users’ travel decisions. To this end, in this article, we propose a factor-level causal explanation generation framework based on counterfactual data augmentation for user travel decisions, named Factor-level Causal Explanation for User Travel Decisions (FCE-UTD), which can distinguish between true and false causal factors and generate true causal explanations. Specifically, we first assume that a user decision is composed of a set of several different factors. Then, by preserving the user decision structure with a joint counterfactual contrastive learning paradigm, we learn the representation of factors and detect the relevant factors. Next, we further identify true causal factors by constructing counterfactual decisions with a counterfactual representation generator, in particular, it can not only augment the dataset and mitigate the sparsity but also contribute to clarifying the causal factors from other false causal factors that may cause spurious explanations. Besides, a causal dependency learner is proposed to identify causal factors for each decision by learning causal dependency scores. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our approach in terms of check-in rate, fidelity, and downstream tasks under different behavior scenarios. The extra case studies also demonstrate the ability of FCE-UTD to generate causal explanations in POI choosing.

UniSparse: An Intermediate Language for General Sparse Format Customization

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by utilizing sparsity pattern- or target-aware data structures and layouts to enhance memory access latency and bandwidth utilization. However, existing sparse tensor programming models and compilers offer little or no support for productively customizing the sparse formats. Additionally, because these frameworks represent formats using a limited set of per-dimension attributes, they lack the flexibility to accommodate numerous new variations of custom sparse data structures and layouts. To overcome this deficiency, we propose UniSparse, an intermediate language that provides a unified abstraction for representing and customizing sparse formats. Unlike the existing attribute-based frameworks, UniSparse decouples the logical representation of the sparse tensor (i.e., the data structure) from its low-level memory layout, enabling the customization of both. As a result, a rich set of format customizations can be succinctly expressed in a small set of well-defined query, mutation, and layout primitives. We also develop a compiler leveraging the MLIR infrastructure, which supports adaptive customization of formats, and automatic code generation of format conversion and compute operations for heterogeneous architectures. We demonstrate the efficacy of our approach through experiments running commonly-used sparse linear algebra operations with specialized formats on multiple different hardware targets, including an Intel CPU, an NVIDIA GPU, an AMD Xilinx FPGA, and a simulated processing-in-memory (PIM) device.

A Dual Perspective Framework of Knowledge-correlation for Cross-domain Recommendation

Recommender System provides users with online services in a personalized way. The performance of traditional recommender systems may deteriorate because of problems such as cold-start and data sparsity. Cross-domain Recommendation System utilizes the richer information from auxiliary domains to guide the task in the target domain. However, direct knowledge transfer may lead to a negative impact due to data heterogeneity and feature mismatch between domains. In this article, we innovatively explore the cross-domain correlation from the perspectives of content semanticity and structural connectivity to fully exploit the information of Knowledge Graph. First, we adopt domain adaptation that automatically extracts transferable features to capture cross-domain semantic relations. Second, we devise a knowledge-aware graph neural network to explicitly model the high-order connectivity across domains. Third, we develop feature fusion strategies to combine the advantages of semantic and structural information. By simulating the cold-start scenario on two real-world datasets, the experimental results show that our proposed method has superior performance in accuracy and diversity compared with the SOTA methods. It demonstrates that our method can accurately predict users’ expressed preferences while exploring their potential diverse interests.

Dual Homogeneity Hypergraph Motifs with Cross-view Contrastive Learning for Multiple Social Recommendations

Social relations are often used as auxiliary information to address data sparsity and cold-start issues in social recommendations. In the real world, social relations among users are complex and diverse. Widely used graph neural networks (GNNs) can only model pairwise node relationships and are not conducive to exploring higher-order connectivity, while hypergraph provides a natural way to model high-order relations between nodes. However, recent studies show that social recommendations still face the following challenges: 1) a majority of social recommendations ignore the impact of multifaceted social relationships on user preferences; 2) the item homogeneity is often neglected, mainly referring to items with similar static attributes have similar attractiveness when exposed to users that indicating hidden links between items; and 3) directly combining the representations learned from different independent views cannot fully exploit the potential connections between different views. To address these challenges, in this article, we propose a novel method DH-HGCN++ for multiple social recommendations. Specifically, dual homogeneity (i.e., social homogeneity and item homogeneity) is introduced to mine the impact of diverse social relations on user preferences and enrich item representations. Hypergraph convolution networks with motifs are further exploited to model the high-order relations between nodes. Finally, cross-view contrastive learning is proposed as an auxiliary task to jointly optimize the DH-HGCN++. Real-world datasets are used to validate the effectiveness of the proposed model, where we use sentiment analysis to extract comment relations and employ the k-means clustering algorithm to construct the item-item correlation graph. Experiment results demonstrate that our proposed method consistently outperforms the state-of-the-art baselines on Top-N recommendations.

Unveiling Antarctica's Heat: A Review of Geothermal Heat Flow Estimation and the Rise of Machine Learning

Antarctica, characterized by its extreme environment and sparse data availability, presents a formidable challenge for estimating geothermal heat flow, a key parameter influencing its geological and glaciological processes. This review paper analyzes existing literature surveys on predicting geothermal heat flow in Antarctica, focusing on various methodologies employed, data sources utilized, and challenges encountered. Highlight the transition from traditional techniques reliant on sparse direct measurements to adopting machine learning (ML) approaches leveraging diverse datasets. The review synthesizes insights from studies utilizing geological, geophysical, and remote sensing data, alongside advancements in ML algorithms, to improve the spatial resolution and accuracy of heat flow predictions. Through a comprehensive examination of the literature, identify key trends, knowledge gaps, and future directions for research in this critical domain.

A Survey of Various Recommendation Systems

Geolocation-based recommender systems have gained significant traction in recent years due to their ability to provide personalized recommendations tailored to users' geographical locations [1]. This survey paper explores the landscape of food recommendation systems with a specific focus on geographical aspects. It examines existing frameworks, solutions, and challenges in the field, highlighting key research contributions and methodologies [2]. By incorporating spatial context into the recommendation process, these systems can identify nearby food establishments, consider regional culinary preferences, and recommend dishes that are popular or highly rated in the vicinity [1]. The paper also discusses the potential of location-aware recommendation systems and proposes a novel approach for food recommendation based on geographical location [3]. Various methodologies employed in geolocation-based food recommendation systems, including collaborative filtering, content-based filtering, and hybrid approaches, are explored, along with their advantages and limitations [5]. Challenges associated with developing geolocation-based recommendation systems, such as data privacy concerns and data sparsity in certain regions, are also addressed [4]. The proposed approach aims to provide more accurate and personalized recommendations by integrating geolocation data with user preferences and contextual information, thereby enriching the overall dining experience for users worldwide [3].

Clinician perspectives regarding CYP2C19 genotype testing in patients with critical limb ischemia: A Delphi approach.

Antiplatelet therapy is an essential element in the management of patients with arterial vascular disease. In peripheral arterial disease (PAD), dual antiplatelet therapy (DAPT), primarily clopidogrel and aspirin, is routinely prescribed following intervention. There is sparse data regarding the need for DAPT, the appropriate duration, or the heterogeneity of treatment effects for antiplatelet regimens across patients, leading to potential uncertainty and heterogeneity around treatment practices. An example of heterogeneity of treatment effects is a patients' metabolizer status for the use of clopidogrel. The aim of the study was to (1) assess clinicians' knowledge of and attitudes toward managing patients with CYP2C19 mutations, (2) identify barriers to implementation of CYP2C19 testing and management policies, and (3) reach consensus for CYP2C19 testing and management strategies for patients with PAD who undergo peripheral vascular interventions (PVI). A modified Delphi method was used to establish consensus amongst PAD interventionalists around CYP2C19 testing. All practicing Yale New Haven Hospital PAD interventionalists with backgrounds in interventional cardiology, vascular surgery, or interventional radiology were approached by email for participation. Round 1 included the collection of baseline demographic questions, knowledge questions, and three statements for consensus. Knowledge questions were rated on a 0-10 Likert scale with the following anchors: 0 ("Not at all"), 5 ("Neutral), and 10 ("Very Much"). Participants were asked to rate the importance of the three consensus statements on a 9-point Likert scale from 1 ("Strongly Disagree") to 10 ("Strongly Agree"). In Round 2, participants were shown the same consensus statements, the median response of the group from the previous round, and their previous answers. Participants were instructed to revise their rating using the results from the previous round. This process was repeated for Round 3. Of the 28 experts invited to participate, 13 agreed (46%). Participants were predominantly male (92.3%) and white (61.5%) with representation from interventional cardiology (46.2%) and vascular surgery (53.8%). Most participants reported more than 10+ years in practice (61.5%). PAD interventionalists felt they would benefit from more education regarding CYP2C19 mutations (median score 8.0, interquartile range 5.0-8.5). They indicated some familiarity with CYP2C19 mutations (7.0, 6.0-9.5) but did not feel strongly that CYP2C19 was important to their practice (6.0, 5.5-7.5). In each round, the median responses for the three consensus statements were 5, 6, and 9, respectively. With each successive round the interquartile range narrowed indicative of evolving consensus but did not reach the prespecified interquartile range for consensus of 1 for any of the statements. PAD interventionalists practicing at an academic health system recognize the heterogenous response of their patients to clopidogrel therapy but are unsure when to leverage genetic testing to improve outcomes for their patients. Our study identified gaps regarding PAD interventionalists' knowledge, perceived barriers, and attitudes toward CYP2C19 testing in PAD. This information highlights the need for randomized data on genetic testing for clopidogrel responsiveness in peripheral vascular disease following intervention to help guide antiplatelet management.

Revisiting the Thornthwaite Mather procedure for baseflow and groundwater storage predictions in sloping and mountainous regions

Hillslope aquifers regulate streamflow and are a critical potable and irrigation water source, especially in developing countries. Knowing recharge and baseflow is essential for managing these aquifers. Methods using available data to calculate recharge and baseflow from aquifers are not valid for uplands. This paper adapts the Thornthwaite and Mather (T-M) procedure from plains to sloping and mountainous regions by replacing the linear reservoir with a zero-order aquifer. The revised T-M procedure was tested over four years in two contrasting watersheds in the humid Ethiopian highlands: the 57 km2 Dangishta with a perennial stream and the nine km2 Robit Bata, where the flow ceased four months after the end of the rain phase. The monthly average groundwater tables were predicted with an accuracy ranging from satisfactory to good for both watersheds. Baseflow predictions were “very good” after considering the evaporation from shallow groundwater in the valley bottom during the dry phase in Dangishta. We conclude that the T-M procedure is ideally suited for calculating recharge, baseflow and groundwater storage in upland regions with sparse hydrological data since the procedure uses as input only rainfall and potential evaporation data that are readily available together with an estimate of the aquifer travel time.

Multi-Source and Multi-modal Deep Network Embedding for Cross-Network Node Classification

In recent years, to address the issue of networked data sparsity in node classification tasks, cross-network node classification (CNNC) leverages the richer information from a source network to enhance the performance of node classification in the target network, which typically has sparser information. However, in real-world applications, labeled nodes may be collected from multiple sources with multiple modalities (e.g., text, vision, and video). Naive application of single-source and single-modal CNNC methods may result in sub-optimal solutions. To this end, in this article, we propose a model called Multi-source and Multi-modal Cross-network Deep Network Embedding (M 2 CDNE) for cross-network node classification. In M 2 CDNE, we propose a deep multi-modal network embedding approach that combines the extracted deep multi-modal features to make the node vector representations network invariant. In addition, we apply dynamic adversarial adaptation to assess the significance of marginal and conditional probability distributions between each source and target network to make node vector representations label discriminative. Furthermore, we devise to classify nodes in the target network through the related source classifier and aggregate different predictions utilizing respective network weights, corresponding to the discrepancy between each source and target network. Extensive experiments performed on real-world datasets demonstrate that the proposed M 2 CDNE significantly outperforms the state-of-the-art approaches.

Research on 3D Visualization of Drone Scenes Based on Neural Radiance Fields

Neural Radiance Fields (NeRFs), as an innovative method employing neural networks for the implicit representation of 3D scenes, have been able to synthesize images from arbitrary viewpoints and successfully apply them to the visualization of objects and room-level scenes (<50 m2). However, due to the capacity limitations of neural networks, the rendering of drone-captured scenes (>10,000 m2) often appears blurry and lacks detail. Merely increasing the model’s capacity or the number of sample points can significantly raise training costs. Existing space contraction methods, designed for forward-facing trajectory or the 360° object-centric trajectory, are not suitable for the unique trajectories of drone footage. Furthermore, anomalies and cloud fog artifacts, resulting from complex lighting conditions and sparse data acquisition, can significantly degrade the quality of rendering. To address these challenges, we propose a framework specifically designed for drone-captured scenes. Within this framework, while using a feature grid and multi-layer perceptron (MLP) to jointly represent 3D scenes, we introduce a Space Boundary Compression method and a Ground-Optimized Sampling strategy to streamline spatial structure and enhance sampling performance. Moreover, we propose an anti-aliasing neural rendering model based on Cluster Sampling and Integrated Hash Encoding to optimize distant details and incorporate an L1 norm penalty for outliers, as well as entropy regularization loss to reduce fluffy artifacts. To verify the effectiveness of the algorithm, experiments were conducted on four drone-captured scenes. The results show that, with only a single GPU and less than two hours of training time, photorealistic visualization can be achieved, significantly improving upon the performance of the existing NeRF approaches.

Fault Diagnosis Based on Tensor Computing and Meta-Learning for Smart Grid and Power Communication Network

Fault diagnosis (FD) is a critical challenge for the smart grid and the power communication network, especially when both heterogeneous networks are exponentially becoming enormous and complicated. Consequently, some conventional FD schemes based on labor seem inefficient, even disabled, because they usually cannot efficiently utilize multi-dimensional and heterogeneous big data from both networks. To deal with this challenging technical problem, a novel FD scheme based on tensor computing and meta-learning is proposed for the smart grid and the power communication network. In the proposed scheme, tensor computing is used to process tensor big data from both networks, and a new data fusion scheme is designed to complete and analyze the incomplete and sparse big data. Based on the fused data, a meta-learning approach is used to construct the FD scheme, especially when the target fault samples are inadequate and sparse. In meta-learning, the convolutional neural network is employed as a base learner to generate an FD training model, and the model-agnostic meta-learning algorithm is utilized to fine-tune and further train the pre-trained model. Simulation results and theoretical analysis indicate that the proposed DF scheme based on tensor computing can efficiently process sparse and heterogeneous big data from both networks. Furthermore, the meta-learning-based FD scheme provides an efficient way to diagnose faults with inadequate target samples. The proposed FD scheme based on tensor computing and meta-learning provides a novel solution to detect and analyze the potential faults for smart grid and power communication networks.

Application of Grey Prediction Models for Efficient Traffic Flow Prediction

Traffic flow prediction is crucial in transportation management and optimizing control strategies and infrastructure planning. However, traditional prediction methods often need help handling traffic data's inherent uncertainty and complexity. This paper explores the application of Grey prediction models as a promising approach for efficient traffic flow prediction. Grey prediction models, rooted in Grey systems theory, offer a robust framework for modelling systems with incomplete and uncertain information. The paper provides a comprehensive overview of Grey prediction models, including the Grey Verhulst, Grey-Markov, and Grey differential equation models. It discusses the process of data collection, pre-processing, and model application in traffic flow prediction. Case studies and experimental results demonstrate the effectiveness of Grey prediction models in accurately forecasting traffic flow patterns. Despite challenges such as data sparsity and model complexity, Grey prediction models offer significant advantages over traditional methods, including improved prediction accuracy and adaptability to dynamic traffic conditions. The paper concludes with recommendations for practitioners and researchers interested in leveraging Grey prediction models for efficient traffic management.

WindSeer: real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle

Real-time high-resolution wind predictions are beneficial for various applications including safe crewed and uncrewed aviation. Current weather models require too much compute and lack the necessary predictive capabilities as they are valid only at the scale of multiple kilometers and hours – much lower spatial and temporal resolutions than these applications require. Our work demonstrates the ability to predict low-altitude time-averaged wind fields in real time on limited-compute devices, from only sparse measurement data. We train a deep neural network-based model, WindSeer, using only synthetic data from computational fluid dynamics simulations and show that it can successfully predict real wind fields over terrain with known topography from just a few noisy and spatially clustered wind measurements. WindSeer can generate accurate predictions at different resolutions and domain sizes on previously unseen topography without retraining. We demonstrate that the model successfully predicts historical wind data collected by weather stations and wind measured by drones during flight.

Recency-based spatio-temporal similarity exploration for POI recommendation in location-based social networks

Point-of-interest (POI) recommendation is one of the primary tasks of location-based social networks (LBSNs). With user data in bulk, extracting useful information and addressing issues such as data sparsity and cold-start problems looming large in collaborative filtering become difficult. One of the plausible solutions is to incorporate contextual information into the recommendation process. In this article, we propose a Recency-based Spatio-Temporal Similarity Exploration (RSTSE) for POI recommendation that utilizes the recency-based trust estimation among the prospective neighbors of the target user. The trust level is categorized into two heads: direct trust, which can be extracted from the peer group information of the user, and indirect trust, which is measured based on venue popularity, temporal recency, radial proximity, and transitivity. The approach consists of two phases. In the incipient phase, POIs are extracted based on the preferences of potential neighbors, including the users who are recognized peers, the users with similar visiting histories in the spatial and temporal context, and the users with friend-of-friend relations. The telic phase involves Neural Collaborative Filtering (NCF) to capture the linear and non-linear user–POI interactions better. RSTSE has been evaluated on three real-world datasets, namely, Gowalla, Foursquare, and Weeplaces, and the results suggest efficacy over other state-of-the-art approaches.

Multimorbidity in middle-aged women and COVID-19: binary data clustering for unsupervised binning of rare multimorbidity features and predictive modeling

BackgroundMultimorbidity is typically associated with deficient health-related quality of life in mid-life, and the likelihood of developing multimorbidity in women is elevated. We address the issue of data sparsity in non-prevalent features by clustering the binary data of various rare medical conditions in a cohort of middle-aged women. This study aims to enhance understanding of how multimorbidity affects COVID-19 severity by clustering rare medical conditions and combining them with prevalent features for predictive modeling. The insights gained can guide the development of targeted interventions and improved management strategies for individuals with multiple health conditions.MethodsThe study focuses on a cohort of 4477 female patients, (aged 45-60) in Piedmont, Italy, and utilizes their multimorbidity data prior to the COVID-19 pandemic from their medical history from 2015 to 2019. The COVID-19 severity is determined by the hospitalization status of the patients from February to May 2020. Each patient profile in the dataset is depicted as a binary vector, where each feature denotes the presence or absence of a specific multimorbidity condition. By clustering the sparse medical data, newly engineered features are generated as a bin of features, and they are combined with the prevalent features for COVID-19 severity predictive modeling.ResultsFrom sparse data consisting of 174 input features, we have created a low-dimensional feature matrix of 17 features. Machine Learning algorithms are applied to the reduced sparsity-free data to predict the Covid-19 hospital admission outcome. The performance obtained for the corresponding models are as follows: Logistic Regression (accuracy 0.72, AUC 0.77, F1-score 0.69), Linear Discriminant Analysis (accuracy 0.7, AUC 0.77, F1-score 0.67), and Ada Boost (accuracy 0.7, AUC 0.77, F1-score 0.68).ConclusionMapping higher-dimensional data to a low-dimensional space can result in information loss, but reducing sparsity can be beneficial for Machine Learning modeling due to improved predictive ability. In this study, we addressed the issue of data sparsity in electronic health records and created a model that incorporates both prevalent and rare medical conditions, leading to more accurate and effective predictive modeling. The identification of complex associations between multimorbidity and the severity of COVID-19 highlights potential areas of focus for future research, including long COVID and intervention efforts.

Generation of intra-community roads based on human-flow modeling (HFM)

Community roads are crucial for efficient navigation in residential areas. However, current navigation maps often lack comprehensive coverage of these roads. To address this issue, we present a Human-Flow Model (HFM) to identify roads within residential communities by utilizing abundant low-frequency trajectory data from human movements. First, the HFM leverages human movement density in residential zones to estimate the likelihood of road existence. Using the probability distribution of human movement and neighboring building footprints, we construct a Human-Flow Probability Field (HFPF), which serves as a distribution representation for modeling human movement within densely populated built-up areas. Then, the flow paths are extracted from the HFPF using hydrological analysis techniques, which facilitates the identification of main paths and smaller branches within the community road network. Finally, the road network is refined using morphological methods. Our model was tested using six residential communities located in Wuhan, China. It consistently outperformed other methods by detecting more roads with higher accuracy, especially intricate branches. By incorporating flow semantics, our model capitalizes on sparse trajectory data to enhance the fine-scale community road networks. This improvement enhances the last-mile navigation experience in sustainable cities, contributing to overall urban mobility and convenience for residents.

Spectral imaging based on custom-made multi-strip filter arrays

Spectral imaging technology based on on-chip spectroscopy can find applications in areas including aerospace, industrial and consumer electronics, and so on. Since each application normally requires a different set and number of spectral bands, the development of customized spectroscopy solutions with more compact size and lower cost becomes quite important. In this paper, we demonstrate a compact, highly customizable imaging spectrometer scheme based on custom-made multi-strip filter arrays, which maintains an average high transmission of ∼85%, narrow bandwidth of ∼30nm, and high optical density of ∼OD2 in the blocking regions across the visible to near-infrared waveband. Spectral imaging experiments are conducted, and the accurate reconstruction of sparse spectral image data is demonstrated as well to prove the validity of the proposed scheme. As a result, the work reported in this paper allows researchers to develop customized spectral imaging equipment in a relatively easy way and also has a great potential to be engineered further for scalable production with a quite low cost.

Travel Time Reliability Estimation in Urban Road Networks: Utilization of Statistics Distribution and Tensor Decomposition

The travel time reliability (TTR) is crucial for evaluating the reliability of road networks, but real traffic data is often incomplete and sparse. This study validates that road network TTR conforms to a normal distribution and devises a quantification approach for road network TTR. Two reliability estimation methods are tailored for two data sources: section detectors and mobile detectors. Simulation experiments have confirmed the effectiveness of these methods. The study emphasizes that the TTR estimation method using traffic section data (S-TTR), which is based on the verified normal distribution assumption, maintains average absolute errors below 10%. On the other hand, the TTR estimation method that utilizes sparse trajectory data (T-TTR), which relies on tensor decomposition, proficiently fills in all missing data with an average error of 0.0059.

OntoMedRec: Logically-pretrained model-agnostic ontology encoders for medication recommendation

Recommending medications with electronic health records (EHRs) is a challenging task for data-driven clinical decision support systems. Most existing models learnt representations for medical concepts based on EHRs and make recommendations with the learnt representations. However, most medications appear in EHR datasets for limited times (the frequency distribution of medications follows power law distribution), resulting in insufficient learning of their representations of the medications. Medical ontologies are the hierarchical classification systems for medical terms where similar terms will be in the same class on a certain level. In this paper, we propose OntoMedRec, the logically-pretrained and model-agnostic medical Ontology Encoders for Medication Recommendation that addresses data sparsity problem with medical ontologies. We conduct comprehensive experiments on real-world EHR datasets to evaluate the effectiveness of OntoMedRec by integrating it into various existing downstream medication recommendation models. The result shows the integration of OntoMedRec improves the performance of various models in both the entire EHR datasets and the admissions with few-shot medications. We provide the GitHub repository for the source code. (https://github.com/WaicongTam/OntoMedRec)