Differentiating between cardiac and pulmonary diseases in emergency settings presents a significant challenge due to overlapping symptoms like dyspnea and chest pain, where misdiagnosis can lead to inappropriate interventions and increased morbidity. While electrocardiograms (ECGs) and chest X-rays (CXRs) provide complementary diagnostic information, existing multimodal fusion approaches fail to fully capture the complex relationships between these fundamentally different data modalities. To address these limitations, we propose DDMF-Net, a Dual-Domain Multimodal Fusion Network that explicitly unifies multi-domain features—from both frequency and spatial/temporal perspectives—and conducts cross-modality fusion of ECG, CXR signals and clinical parameters in hyperbolic space, thereby enhancing the modeling of complex cardiopulmonary pathophysiology. Our framework contains three innovations: (1) a frequency fusion module that captures complementary spectral patterns across modalities, (2) an inter-domain fusion module that dynamically balances domain-specific features, and (3) a hyperbolic cross-attention module with soft-entailment loss that effectively models hierarchical relationships between low-level imaging/signal data and high-level clinical parameters. Evaluated on four MIMIC datasets, DDMF-Net achieves state-of-the-art performance with over 2.9% improvement in micro-AUC, enabling more accurate differentiation of cardiac and pulmonary conditions in time-sensitive emergency settings. Code is publicly available at https://github.com/kknankk/DDMF_Net.

Rapid advances in positioning and monitoring technologies have significantly enhanced the ability to track dynamic moving objects for studying movement patterns. As an emerging field in spatiotemporal data mining, a well-established taxonomy of movement patterns facilitates tasks that mine movement patterns. In this study, we proposed a novel classification framework with the 5W1H1R (who, what, when, where, why, how, and relationships) principle and a bottom-up multi-level cognitive model to support the taxonomy of movement patterns. Guided by first principles thinking and combinatorics, we differentiated basic patterns categorized along spatial, temporal, and motion attribute dimensions from compound patterns composed of these basic patterns. We summarized five key constraints to refine movement patterns over recently studied pattern types. We validated our framework in three domains and compared it with four existing frameworks in five aspects. The results demonstrate the broader coverage, extensibility, and adaptability of the framework. Our classification framework can adapt to various moving objects, application domains, and movement data at different scales and resolutions. It can serve as a conceptual and ontological foundation for guiding the mining and analysis of movement patterns and, especially, for developing models to detect multimodal movement patterns.

Despite recent advancements, most computational methods for molecule optimization are constrained to single-or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks.Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks.To demonstrate LLMs' potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on complex multi-property molecule optimization tasks.Leveraging MuMOInstruct, we develop GeLLM 3 Os, a series of instruction-tuned LLMs for molecule optimization.Extensive evaluations across 5 in-domain and 5 outof-domain tasks demonstrate that GeLLM 3 Os consistently outperform state-of-the-art baselines.GeLLM 3 Os also exhibit outstanding zeroshot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs.Such strong generalizability demonstrates the tremendous potential of GeLLM 3 Os as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining.

Target-Oriented Dialogue (TOD) remains a significant challenge in the LLM era, where strategic dialogue planning is crucial for directing conversations toward specific targets. However, existing dialogue planning methods generate dialogue plans in a step-by-step sequential manner, and may suffer from compounding errors and myopic actions. To address these limitations, we introduce a novel dialogue planning framework, DiffTOD, which leverages diffusion models to enable non-sequential dialogue planning. DiffTOD formulates dialogue planning as a trajectory generation problem with conditional guidance, and leverages a diffusion language model to estimate the likelihood of the dialogue trajectory. To optimize the dialogue action strategies, DiffTOD introduces three tailored guidance mechanisms for different target types, offering flexible guidance toward diverse TOD targets at test time. Extensive experiments across three diverse TOD settings show that DiffTOD can effectively perform non-myopic lookahead exploration and optimize action strategies over a long horizon through non-sequential dialogue planning, and demonstrates strong flexibility across complex and diverse dialogue scenarios. Our code and data are accessible through https://github.com/ninglab/DiffTOD.

. By leveraging the reasoning capabilities of large language models, LIDDiA serves as a low-cost and highly-adaptable tool for autonomous drug discovery. We comprehensively examine LIDDiA, demonstrating that (1) it can generate molecules meeting key pharmaceutical criteria on over 70% of 30 clinically relevant targets, (2) it intelligently balances exploration and exploitation in the chemical space, and (3) it identifies one promising novel candidate on AR/NR3C4, a critical target for both prostate and breast cancers. Code and dataset are available at https://github.com/ninglab/LIDDiA.

Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

The advancements of language language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about the true capabilities of such agents. In this work, we argue that for an agent to fully automate scientific discovery, it must be able to complete all essential tasks in the workflow. Thus, we call for rigorous assessment of agents on individual tasks in a scientific workflow before making bold claims on end-to-end automation. To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery. To ensure the scientific authenticity and real-world relevance of our benchmark, we extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them. We unify the target output for every task to a self-contained Python program file and employ an array of evaluation metrics to examine the generated programs, execution results, and costs. Each task goes through multiple rounds of manual validation by annotators and subject matter experts to ensure its annotation quality and scientific plausibility. We also propose two effective strategies to mitigate data contamination concerns. Using our benchmark, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands, and self-debug. Given three attempts for each task, the best-performing agent can only solve 32.4% of the tasks independently and 34.3% with expert-provided knowledge. These results underscore the limited capacities of current language agents in generating code for data-driven discovery, let alone end-to-end automation for scientific research.

Reza Averly, Xia Ning. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Hanwen Du, Bo Peng, Xia Ning. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent models that rely on powerful pretrained vision encoders and LLMs. A common approach to connect the pretrained vision encoder and LLM is through a projector applied after the vision encoder. However, the projector is often trained to enable the LLM to generate captions, and hence the mechanism by which LLMs understand each vision token remains unclear. In this work, we first investigate the role of the projector in compressing vision embeddings and aligning them with word embeddings. We show that the projector significantly compresses visual information, removing redundant details while preserving essential elements necessary for the LLM to understand visual content. We then examine patch-level alignment---the alignment between each vision patch and its corresponding semantic words---and propose a $\textit{multi-semantic alignment hypothesis}$. Our analysis indicates that the projector trained by caption loss improves patch-level alignment but only to a limited extent, resulting in weak and coarse alignment. To address this issue, we propose $\textit{patch-aligned training}$ to efficiently enhance patch-level alignment. Our experiments show that patch-aligned training (1) achieves stronger compression capability and improved patch-level alignment, enabling the MLLM to generate higher-quality captions, (2) improves the MLLM's performance by 16% on referring expression grounding tasks, 4% on question-answering tasks, and 3% on modern instruction-following benchmarks when using the same supervised fine-tuning (SFT) setting. The proposed method can be easily extended to other multimodal models.

Trajectory clustering is a fundamental yet challenging data mining task that aims to group similar trajectories. Due to the inherent nature and implicit patterns of trajectories, existing methods often struggle to cluster trajectories with varying densities and noise, and automatically determine cluster numbers. We propose an adaptive two-stage trajectory cluster (ATSTC) algorithm considering the intra-cluster trajectory distance distributions. In the first stage, peak trajectories with the highest local densities, and their adaptively estimated k-nearest neighbors, are initialized as candidate clusters. Trajectories in multiple peak neighborhoods are assigned to clusters with minimal relative distances while remaining trajectories are merged with the nearest cluster or labeled as noise depending on the resultant changes in intra-cluster distance standard deviation. In the second stage, a hierarchical agglomerative strategy is employed to merge clusters by analyzing changes in the average distance and standard deviation of intra-cluster trajectories before and after merging. Experiments on four simulated datasets, with comparisons to eight baselines, demonstrate the superior performance (e.g. ARI) of ATSTC in detecting trajectory clusters under different scenarios. Case studies involving route extraction from ship trajectories and bird tracks with clusters of different sizes, densities, and noise underscore the potential and efficacy of ATSTC in real-world applications.

With tremendous efforts on developing effective e-commerce models, conventional e-commerce models show limited success in generalist e-commerce modeling, and suffer from unsatisfactory performance on new users and new products – a typical out-of-domain generalization challenge. Meanwhile, large language models (LLMs) demonstrate outstanding performance in generalist modeling and out-of-domain generalizability in many fields. Toward fully unleashing their power for e-commerce, in this paper, we construct ECInstruct, the first open-sourced, large-scale, and high-quality benchmark instruction dataset for e-commerce. Leveraging ECInstruct, we develop eCeLLM, a series of e-commerce LLMs, by instruction-tuning general-purpose LLMs. Our comprehensive experiments and evaluation demonstrate that eCeLLM models substantially outperform baseline models, including the most advanced GPT-4, and the state-of-the-art task-specific models in in-domain evaluation. Moreover, eCeLLM exhibits excellent generalizability to out-of-domain settings, including unseen products and unseen instructions, highlighting its superiority as a generalist e-commerce model. Both the ECInstruct dataset and the eCeLLM models show great potential in empowering versatile and effective LLMs for e-commerce. ECInstruct and eCeLLM models are publicly accessible through this link.

Abstract Session-based recommendation aims to generate recommendations for the next item of users’ interest based on a given session. In this manuscript, we develop intention enhanced mixed attentive model () to generate session-based recommendations using two important factors: temporal patterns and estimates of users’ intentions. Unlike existing methods which primarily leverage complicated gated recurrent units to model the temporal patterns, models the temporal patterns using a light-weight while effective position-sensitive attention mechanism. In , we also leverage the estimate of users’ prospective preferences to signify important items, and generate better recommendations. Our experimental results demonstrate that models significantly outperform the state-of-the-art methods in six benchmark datasets, with an improvement as much as 19.2%. In addition, our run-time performance comparison demonstrates that during testing, models are much more efficient than the best baseline method, with a significant average speedup of 47.7 folds.

Self-attention (SA) mechanisms have been widely used in developing sequential recommendation (SR) methods, and demonstrated state-of-the-art performance. However, in this article, we show that self-attentive SR methods substantially suffer from the over-smoothing issue that item embeddings within a sequence become increasingly similar across attention blocks. As widely demonstrated in the literature, this issue could lead to a loss of information in individual items, and significantly degrade models’ scalability and performance. To address the over-smoothing issue, in this article, we view items within a sequence constituting a star graph and develop a method, denoted as \(\mathop{\mathtt{MSSG}}\limits\) , for SR. Different from existing self-attentive methods, \(\mathop{\mathtt{MSSG}}\limits\) introduces an additional internal node to specifically capture the global information within the sequence, and does not require information propagation among items. This design fundamentally addresses the over-smoothing issue and enables \(\mathop{\mathtt{MSSG}}\limits\) a linear time complexity with respect to the sequence length. We compare \(\mathop{\mathtt{MSSG}}\limits\) with eleven state-of-the-art baseline methods on six public benchmark datasets. Our experimental results demonstrate that \(\mathop{\mathtt{MSSG}}\limits\) significantly outperforms the baseline methods, with an improvement of as much as 10.10%. Our analysis shows the superior scalability of \(\mathop{\mathtt{MSSG}}\limits\) over the state-of-the-art self-attentive methods. Our complexity analysis and runtime performance comparison together show that \(\mathop{\mathtt{MSSG}}\limits\) is both theoretically and practically more efficient than self-attentive methods. Our analysis of the attention weights learned in SA-based methods indicates that on sparse recommendation data, modeling dependencies in all item pairs using the SA mechanism yields limited information gain, and thus, might not benefit the recommendation performance. Our source code and data are publicly accessible through GitHub .

Sequential recommendation aims to identify and recommend the next few items of users’ interest. It becomes an effective tool to help users select their favorite items from a variety of options. A key challenge in sequential recommendation is to learn the patterns and dynamics, which are most pertinent to inform future interactions of users. With the prosperity of deep learning, many deep models, particularly based on recurrent neural networks [1] and with attention mechanisms [2] , [3] , have been developed for sequential recommendation purposes. However, our analysis demonstrates that, these deep models, particularly those with attention mechanisms, may not always learn meaningful attention weights from the extremely sparse recommendation data, and thus, could degrade the recommendation performance. Therefore, in this study, instead of deep models, we develop novel, effective and efficient hybrid associations models (HAM) to better learn from the sparse and limited recommendation data. This study has been published in IEEE Transactions on Knowledge and Data Engineering. Please refer to the full manuscript [4] for more details.

MOTIVATION: MHC Class I protein plays an important role in immunotherapy by presenting immunogenic peptides to anti-tumor immune cells. The repertoires of peptides for various MHC Class I proteins are distinct, which can be reflected by their diverse binding motifs. To characterize binding motifs for MHC Class I proteins, in vitro experiments have been conducted to screen peptides with high binding affinities to hundreds of given MHC Class I proteins. However, considering tens of thousands of known MHC Class I proteins, conducting in vitro experiments for extensive MHC proteins is infeasible, and thus a more efficient and scalable way to characterize binding motifs is needed. RESULTS: We presented a de novo generation framework, coined PepPPO, to characterize binding motif for any given MHC Class I proteins via generating repertoires of peptides presented by them. PepPPO leverages a reinforcement learning agent with a mutation policy to mutate random input peptides into positive presented ones. Using PepPPO, we characterized binding motifs for around 10 000 known human MHC Class I proteins with and without experimental data. These computed motifs demonstrated high similarities with those derived from experimental data. In addition, we found that the motifs could be used for the rapid screening of neoantigens at a much lower time cost than previous deep-learning methods. AVAILABILITY AND IMPLEMENTATION: The software can be found in https://github.com/minrq/pMHC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions ($\mathop {\mathtt {M^2}}\limits$) for the next-basket recommendation. This method models three important factors in next-basket generation process: 1) users’ general preferences, 2) items’ global popularities and 3) transition patterns among items. Unlike existing recurrent neural network-based approaches,$\mathop {\mathtt {M^2}}\limits$does not use the complicated networks to model the transitions among items, or generate embeddings for users. Instead, it has a simple encoder-decoder based approach ($\mathop {\mathtt {ed\text{-}Trans}}\limits$) to better model the transition patterns among items. We compared$\mathop {\mathtt {M^2}}\limits$with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket. Our experimental results demonstrate that$\mathop {\mathtt {M^2}}\limits$significantly outperforms the state-of-the-art methods on all the datasets in all the tasks, with an improvement of up to 22.1%. In addition, our ablation study demonstrates that the$\mathop {\mathtt {ed\text{-}Trans}}\limits$is more effective than recurrent neural networks in terms of the recommendation performance. We also have a thorough discussion on various experimental protocols and evaluation metrics for next-basket recommendation evaluation.

Alzheimer's disease (AD) is one of the most common and severe forms of Senile Dementia. Genome-wide association studies (GWAS) have identified dozens of AD susceptible loci. To better understand potential mechanism-of-action for AD, quantitative brain imaging features have been studied as mediators linking genetic variants to AD outcomes. In this study, Mediation analysis, Chow test and Mixed-effects Models are used to investigate the biological pathways by which genetic variants affect both brain structures/functions and disease diagnosis. We analyzed the imaging and genetics data collected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) project, including a Polygenic Hazard Score (PHS) and 13 imaging quantitative traits (QTs) extracted from the AV45 PET scans quantifying the amyloid deposition in different brain regions of subjects from four separate diagnostic groups. Mediation analysis assessed the mediating effects of image QTs between PHS and diagnosis, whereas Chow test and Linear Mixed-Effects models were used to characterize intra-group differences in the associations between genetic scores and imaging QTs for different disease stages. Results show that promising stage-specific imaging QTs that mediate the genetic effect of the studied PHS on disease status have been identified, providing novel insights into the predictive power of the PHS and the mediating power of amyloid imaging QTs with respect to multiple stages over the AD progression.

Electronic health record (EHR) data are increasingly used to develop prediction models to support clinical care, including the care of patients with common chronic conditions. A key challenge for individual healthcare systems in developing such models is that they may not be able to achieve the desired degree of robustness using only their own data. A potential solution-combining data from multiple sources-faces barriers such as the need for data normalization and concerns about sharing patient information across institutions. To address these challenges, we evaluated three alternative approaches to using EHR data from multiple healthcare systems in predicting the outcome of pharmacotherapy for type 2 diabetes mellitus(T2DM). Two of the three approaches, named Selecting Better (SB) and Weighted Average(WA), allowed the data to remain within institutional boundaries by using pre-built prediction models; the third, named Combining Data (CD), aggregated raw patient data into a single dataset. The prediction performance and prediction coverage of the resulting models were compared to single-institution models to help judge the relative value of adding external data and to determine the best method to generate optimal models for clinical decision support. The results showed that models using WA and CD achieved higher prediction performance than single-institution models for common treatment patterns. CD outperformed the other two approaches in prediction coverage, which we defined as the number of treatment patterns predicted with an Area Under Curve of 0.70 or more. We concluded that 1) WA is an effective option for improving prediction performance for common treatment patterns when data cannot be shared across institutional boundaries and 2) CD is the most effective approach when such sharing is possible, especially for increasing the range of treatment patterns that can be predicted to support clinical decision making.

Sequential recommendation aims to identify and recommend the next few items for a user that the user is most likely to purchase/review, given the user's purchase/rating trajectories. It becomes an effective tool to help users select favorite items from a variety of options. In this manuscript, we developed hybrid associations models (HAM) to generate sequential recommendations. using three factors: 1) users' long-term preferences, 2) sequential, high-order and low-order association patterns in the users' most recent purchases/ratings, and 3) synergies among those items. HAM uses simplistic pooling to represent a set of items in the associations, and element-wise product to represent item synergies of arbitrary orders. We compared HAM models with the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings. Our experimental results demonstrate that HAM models significantly outperform the state of the art in all the experimental settings. with an improvement as much as 46.6%. In addition, our run-time performance comparison in testing demonstrates that HAM models are much more efficient than the state-of-the-art methods. and are able to achieve significant speedup as much as 139.7 folds.

With increasing and extensive use of electronic health records (EHR), clinicians are often challenged in retrieving relevant patient information efficiently and effectively to arrive at a diagnosis. While using the search function built into an EHR can be more useful than browsing in a voluminous patient record, it is cumbersome and repetitive to search for the same or similar information on similar patients. To address this challenge, there is a critical need to build effective recommender systems that can recommend search terms to clinicians accurately. In this study, we developed a hybrid collaborative filtering model to recommend search terms for a specific patient to a clinician. The model draws on information from patients' clinical encounters and the searches that were performed during them. To generate recommendations, the model uses search terms which are (1) frequently co-occurring with the ICD codes recorded for the patient and (2) highly relevant to the most recent search terms. In one variation of the model (Hybrid Collaborative Filtering Method for Healthcare, or HCFMH), we use only the most recent ICD codes assigned to the patient, and in the other (Co-occurrence Pattern based HCFMH, or cpHCFMH), all ICD codes. We have conducted comprehensive experiments to evaluate the proposed model. These experiments demonstrate that our model outperforms state-of-the-art baseline methods for top-N search term recommendation on different data sets.

Selecting the right drugs for the right patients is a primary goal of precision medicine. In this article, we consider the problem of cancer drug selection in a learning-to-rank framework. We have formulated the cancer drug selection problem as to accurately predicting 1) the ranking positions of sensitive drugs and 2) the ranking orders among sensitive drugs in cancer cell lines based on their responses to cancer drugs. We have developed a new learning-to-rank method, denoted as pLETORg, that predicts drug ranking structures in each cell line via using drug latent vectors and cell line latent vectors. The pLETORg method learns such latent vectors through explicitly enforcing that, in the drug ranking list of each cell line, the sensitive drugs are pushed above insensitive drugs, and meanwhile the ranking orders among sensitive drugs are correct. Genomics information on cell lines is leveraged in learning the latent vectors. Our experimental results on a benchmark cell line-drug response dataset demonstrate that the new pLETORg significantly outperforms the state-of-the-art method in prioritizing new sensitive drugs.

Over the past decade low graduation and retention rates has plagued higher education institutions. To assist students in choosing a sequence of courses, choosing majors and successful academic pathways; many institutions provide several on-site academic advising services supported by data driven educational technologies. Accurate performance prediction can serve as the backbone for degree planning software, personalized advising systems and early warning systems that can identify students at-risk of dropping from their field of study. In this work, we present a deep learning based recommender system approach called Neural Collaborative Filtering (NCF) for predicting the grade a student will earn in a course that he/she plans to take in the next-term. Prior grade prediction methods are based on matrix factorization (MF) where students and courses are represented in a latent "knowledge" space. The deep learning inspired approach provides added flexibility in learning the latent spaces in comparison to MF approaches. The proposed approach also incorporates instructor information besides student and course information. Moreover, for proper analysis of the learned model parameters, we assume the embeddings obtained for students, courses and instructors should be non-negative. This non-negative NCF model referred by NCFnn model adds a rectified linear units (ReLU) on the embedding layer of NCF. The experimental results on datasets from George Mason University, a large, public university in the United States, demonstrate that the proposed NCF approaches significantly outperform competitive baselines across different test sets.

Mining high-order drug-drug interaction (DDI) induced adverse drug effects from electronic health record databases is an emerging area, and very few studies have explored the relationships between high-order drug combinations. We investigate a novel pharmacovigilance problem for mining directional DDI effects on myopathy using the FDA Adverse Event Reporting System (FAERS) database. Our paper provides information on the risk of myopathy associated with adding new drugs on the already prescribed medication, and visualizes the identified directional DDI patterns as user-friendly graphical representation. We utilize the Apriori algorithm to extract frequent drug combinations from the FAERS database. We use odds ratio to estimate the risk of myopathy associated with directional DDI. We create a tree-structured graph to visualize the findings for easy interpretation. Our method confirmed myopathy association with previously reported HMG-CoA reductase inhibitors like rosuvastatin, fluvastatin, simvastatin, and atorvastatin. New, previously unidentified but mechanistically plausible associations with myopathy were also observed, such as the DDI between pamidronate and levofloxacin. Additional top findings are gadolinium-based imaging agents, which however are often used in myopathy diagnosis. Other DDIs with no obvious mechanism are also reported, such as that of sulfamethoxazole with trimethoprim and potassium chloride. This study shows the feasibility to estimate high-order directional DDIs in a fast and accurate manner. The results of the analysis could become a useful tool in the specialists' hands through an easy-to-understand graphic visualization.

The past decade has seen a growth in the development and deployment of educational technologies for assisting college-going students in choosing majors, selecting courses and acquiring feedback based on past academic performance. Grade prediction methods seek to estimate a grade that a student may achieve in a course that she may take in the future (e.g., next term). Accurate and timely prediction of students' academic grades is important for developing effective degree planners and early warning systems, and ultimately improving educational outcomes. Existing grade prediction methods mostly focus on modeling the knowledge components associated with each course and student, and often overlook other factors such as the difficulty of each knowledge component, course instructors, student interest, capabilities and effort. In this paper, we propose additive latent effect models that incorporate these factors to predict the student next-term grades. Specifically, the proposed models take into account four factors: (i) student's academic level, (ii) course instructors, (iii) student global latent factor, and (iv) latent knowledge factors. We compared the new models with several state-of-the-art methods on students of various characteristics (e.g., whether a student transferred in or not). The experimental results demonstrate that the proposed methods significantly outperform the baselines on grade prediction problem. Moreover, we perform a thorough analysis on the importance of different factors and how these factors can practically assist students in course selection, and finally improve their academic performance.

Sparse models have demonstrated substantial success in applications for data analysis such as clustering, classification and denoising. However, most of the current work is built upon the assumption that data is distributed in a union of subspaces, whereas limited work has been conducted on nonlinear datasets where data reside in a union of manifolds rather than a union of subspaces. To understand data nonlinearity using sparse models, in this paper, we propose to exploit the self-representation property of nonlinear data in an implicit feature space using kernel methods. We propose a kernelized sparse self-representation model, denoted as KSSR, and a novel Kernelized Fast Iterative Soft-Thresholding Algorithm, denoted as K-FISTA, to recover the underlying nonlinear structure among the data. We evaluate our method for clustering problems on both synthetic and real-world datasets, and demonstrate its superior performance compared to the other state-of-the-art methods. We also apply our method for collaborative filtering in recommender systems, and demonstrate its great potential for novel applications beyond clustering.

Reducing attack surface is an effective preventive measure to strengthen security in large systems. However, it is challenging to apply this idea in an enterprise environment where systems are complex and evolving over time. In this paper, we empirically analyze and measure a real enterprise to identify unused services that expose attack surface. Interestingly, such unused services are known to exist and summarized by security best practices, yet such solutions require significant manual effort.

Fully-observable high-order Boltzmann Machines are capable of identifying explicit high-order feature interactions theoretically. However, they have never been used in practice due to their prohibitively high computational cost for inference and learning. In this paper, we propose an efficient approach for learning a fully observable high-order Boltzmann Machine based on sparse learning and contrastive divergence, resulting in an interpretable Sparse High-order Boltzmann Machine, denoted as SHBM. Experimental results on synthetic datasets and a real dataset demonstrate that SHBM can produce higher pseudo-log-likelihood and better reconstructions on test data than the state-of-the-art methods. In addition, we apply SHBM to a challenging bioinformatics problem of discovering complex Transcription Factor interactions. Compared to conventional Boltzmann Machine and directed Bayesian Network, SHBM can identify much more biologically meaningful interactions that are supported by recent biological studies. To the best of our knowledge, SHBM is the first working Boltzmann Machine with explicit high-order feature interactions applied to real-world problems.

The effectiveness of existing top-N recommendation methods decreases as the sparsity of the datasets increases. To alleviate this problem, we present an item-based method for generating top-N recommendations that learns the item-item similarity matrix as the product of two low dimensional latent factor matrices. These matrices are learned using a structural equation modeling approach, wherein the value being estimated is not used for its own estimation. A comprehensive set of experiments on multiple datasets at three different sparsity levels indicate that the proposed methods can handle sparse datasets effectively and outperforms other state-of-the-art top-N recommendation methods. The experimental results also show that the relative performance gains compared to competing methods increase as the data gets sparser.

The increasing amount of side information associated with the items in E-commerce applications has provided a very rich source of information that, once properly exploited and incorporated, can significantly improve the performance of the conventional recommender systems. This paper focuses on developing effective algorithms that utilize item side information for top-N recommender systems. A set of sparse linear methods with side information (SSLIM) is proposed, which involve a regularized optimization process to learn a sparse aggregation coefficient matrix based on both user-item purchase profiles and item side information. This aggregation coefficient matrix is used within an item-based recommendation framework to generate recommendations for the users. Our experimental results demonstrate that SSLIM outperforms other methods in effectively utilizing side information and achieving performance improvement.

This paper focuses on developing effective and efficient algorithms for top-N recommender systems. A novel Sparse Linear Method (SLIM) is proposed, which generates top-N recommendations by aggregating from user purchase/rating profiles. A sparse aggregation coefficient matrix W is learned from SLIM by solving an ℓ1-norm and ℓ2-norm regularized optimization problem. W is demonstrated to produce high quality recommendations and its sparsity allows SLIM to generate recommendations very fast. A comprehensive set of experiments is conducted by comparing the SLIM method and other state-of-the-art top-N recommendation methods. The experiments show that SLIM achieves significant improvements both in run time performance and recommendation quality over the best existing methods.

Extracting semantic relations between entities is an important step towards automatic text understanding. In this paper, we propose a novel Semi-supervised Convolution Graph Kernel (SCGK) method for semantic Relation Extraction (RE) from natural language. By encoding English sentences as dependence graphs among words, SCGK computes kernels (similarities) between sentences using a convolution strategy, i.e., calculating similarities over all possible short single paths from two dependence graphs. Furthermore, SCGK adds three semi-supervised strategies in the kernel calculation to incorporate soft-matches between (1) words, (2) grammatical dependencies, and (3) entire sentences, respectively. From a large unannotated corpus, these semi-supervision steps learn to capture contextual semantic patterns of elements in natural sentences, which therefore alleviate the lack of annotated examples in most RE corpora. Through convolutions and multi-level semi-supervisions, SCGK provides a powerful model to encode both syntactic and semantic evidence existing in natural English sentences, which effectively recovers the target relational patterns of interest. We perform extensive experiments on five RE benchmark datasets which aim to identify interaction relations from biomedical literature. Our results demonstrate that SCGK achieves the state-of-the-art performance on the task of semantic relation extraction.

This paper focuses on developing classification algorithms for problems in which there is a need to predict the class based on multiple observations (examples) of the same phenomenon (class). These problems give rise to a new classification problem, referred to as set classification, that requires the prediction of a set of instances given the prior knowledge that all the instances of the set belong to the same unknown class. This problem falls under the general class of problems whose instances have class label dependencies. Four methods for solving the set classification problem are developed and studied. The first is based on a straightforward extension of the traditional classification paradigm whereas the other three are designed to explicitly take into account the known dependencies among the instances of the unlabeled set during learning or classification. A comprehensive experimental evaluation of the various methods and their underlying parameters shows that some of them lead to significant gains in performance.

In this paper, we present our efforts to parallelize an unstructured quadrilateral mesh generator. Its serial version is based on the divider-and-conquer idea, and mainly includes two stages, i.e. geometry decomposition and mesh generation. Both stages are parallelized separately. A highly efficient fine-grain level parallel scheme is presented to parallelize the stage of geometry decomposition. A SubDomain Graph (SDG), which represents the connections of subdomains, is constructed. The task of parallel mesh generation is then reduced to that of the SDG partitioning. Since the number of elements in subdomains could be pre-computed before meshing, a static load balancing scheme to partition the SDG performs well with the aid of Metis tools. Numerical results show that scalable timing performance could be achieved by using the parallel mesh generator with resulting meshes nicely partitioned among processors, which enables a fast parallel simulation environment by eliminating the traditional I/O-busy process of mesh repartitioning.