Latent Interaction Research Articles

Data-driven model selections of second-order particle dynamics via integrating Gaussian processes with low-dimensional interacting structures

In this paper, we focus on the data-driven discovery of a general second-order particle-based model that contains many state-of-the-art models for modeling the aggregation and collective behavior of interacting agents of similar size and body type. This model takes the form of a high-dimensional system of ordinary differential equations parameterized by two interaction kernels that appraise the alignment of positions and velocities. We propose a Gaussian Process-based approach to this problem, where the unknown model parameters are marginalized by using two independent Gaussian Process (GP) priors on latent interaction kernels constrained to dynamics and observational data. This results in a nonparametric model for interacting dynamical systems that accounts for uncertainty quantification. We also show that our estimators can be efficiently derived through the use of preconditioned techniques, ensuring scalability. Moreover, we perform a theoretical analysis to interpret the methodology and investigate the conditions under which the kernels can be recovered. We demonstrate the effectiveness of the proposed approach on various prototype systems, including the selection of the order of the systems and the types of interactions. In particular, we present applications to modeling two real-world fish motion datasets that display flocking and milling patterns up to 248 dimensions. Despite the use of small datasets, the GP-based approach learns an effective representation of the nonlinear dynamics in these spaces and outperforms competitor methods.

Optimizing Session-Aware Recommenders: A Deep Dive into GRU-Based Latent Interaction Integration

This study introduces session-aware recommendation models, leveraging GRU (Gated Recurrent Unit) and attention mechanisms for advanced latent interaction data integration. A primary advancement is enhancing latent context, a critical factor for boosting recommendation accuracy. We address the existing models’ rigidity by dynamically blending short-term (most recent) and long-term (historical) preferences, moving beyond static period definitions. Our approaches, pre-combination (LCII-Pre) and post-combination (LCII-Post), with fixed (Fix) and flexible learning (LP) weight configurations, are thoroughly evaluated. We conducted extensive experiments to assess our models’ performance on public datasets such as Amazon and MovieLens 1M. Notably, on the MovieLens 1M dataset, LCII-PreFix achieved a 1.85% and 2.54% higher Recall@20 than II-RNN and BERT4Rec+st+TSA, respectively. On the Steam dataset, LCII-PostLP outperformed these models by 18.66% and 5.5%. Furthermore, on the Amazon dataset, LCII showed a 2.59% and 1.89% improvement in Recall@20 over II-RNN and CAII. These results affirm the significant enhancement our models bring to session-aware recommendation systems, showcasing their potential for both academic and practical applications in the field.

TryonCM2: Try-on-Enhanced Fashion Compatibility Modeling Framework.

Recently, fashion compatibility modeling, which can score the matching degree of several complementary fashion items, has gained increasing research attention. Previous studies have primarily learned the features of fashion items and utilize their interaction as the fashion compatibility. However, the try-on looking of an outfit help us to learn the fashion compatibility in a combined manner, where items are spatially distributed and partially covered by other items. Inspired by this, we design a try-on-enhanced fashion compatibility modeling framework, named TryonCM2, which incorporates the try-on appearance with the item interaction to enhance the fashion compatibility modeling. Specifically, we treat each outfit as a sequence of items and adopt the bidirectional long short-term memory (LSTM) network to capture the latent interaction of fashion items. Meanwhile, we synthesize a try-on template image to depict the try-on appearance of an outfit. And then, we regard the outfit as a sequence of multiple image stripes, i.e., local content, of the try-on template, and adopt the bidirectional LSTM network to capture the contextual structure in the try-on appearance. Ultimately, we combine the fashion compatibility lying in the item interaction and try-on appearance as the final compatibility of the outfit. Both the objective and subjective experiments on the existing FOTOS dataset demonstrate the superiority of our framework over the state-of-the-art methods.

Hierarchical Graph Interaction Transformer With Dynamic Token Clustering for Camouflaged Object Detection.

Camouflaged object detection (COD) aims to identify the objects that seamlessly blend into the surrounding backgrounds. Due to the intrinsic similarity between the camouflaged objects and the background region, it is extremely challenging to precisely distinguish the camouflaged objects by existing approaches. In this paper, we propose a hierarchical graph interaction network termed HGINet for camouflaged object detection, which is capable of discovering imperceptible objects via effective graph interaction among the hierarchical tokenized features. Specifically, we first design a region-aware token focusing attention (RTFA) with dynamic token clustering to excavate the potentially distinguishable tokens in the local region. Afterwards, a hierarchical graph interaction transformer (HGIT) is proposed to construct bi-directional aligned communication between hierarchical features in the latent interaction space for visual semantics enhancement. Furthermore, we propose a decoder network with confidence aggregated feature fusion (CAFF) modules, which progressively fuses the hierarchical interacted features to refine the local detail in ambiguous regions. Extensive experiments conducted on the prevalent datasets, i.e. COD10K, CAMO, NC4K and CHAMELEON demonstrate the superior performance of HGINet compared to existing state-of-the-art methods. Our code is available at https://github.com/Garyson1204/HGINet.

Residual-aware deep attention graph convolutional network via unveiling data latent interactions for product quality prediction in industrial processes

Data-driven modeling based on deep learning is crucial for online product quality prediction in industrial processes. Extracting latent data interactions from sensor variables lies at the core of various data-driven modeling applications. Typically, the observed variables exhibit non-stationary properties due to changes in operating conditions and sensor tuning issues. These fluctuations inevitably affect the reliability of traditional feature extraction methods, thus hindering their applications. Hence, this paper proposes a novel method named residual-aware deep attention graph convolutional network (RaDA-GCN) to explore potential interactions among sensor variables. RaDA-GCN ingeniously incorporates an attention mechanism into the graph convolution layer to extract nonlinear variable-related features according to their importance. Then, a novel residual-aware connection module is designed to reduce data uncertainty and alleviate over-smoothing. By skillfully stacking multiple attention map convolutional layers with the integration of residual-aware connections, deep structural features are obtained to facilitate the effective quantification and revelation of potential relationships among data variables. Finally, the application of the predictive modeling framework based on the proposed method is used to validate its effectiveness in actual industrial process data. The experimental results demonstrate that the proposed RaDA-GCN method exhibits a 23% improvement in the R-squared (R2) indicator and a 13% reduction in the root mean square error (RMSE) compared to the traditional graph convolutional network method.

TF-YOLO: A Transformer–Fusion-Based YOLO Detector for Multimodal Pedestrian Detection in Autonomous Driving Scenes

Recent research demonstrates that the fusion of multimodal images can improve the performance of pedestrian detectors under low-illumination environments. However, existing multimodal pedestrian detectors cannot adapt to the variability of environmental illumination. When the lighting conditions of the application environment do not match the experimental data illumination conditions, the detection performance is likely to be stuck significantly. To resolve this problem, we propose a novel transformer–fusion-based YOLO detector to detect pedestrians under various illumination environments, such as nighttime, smog, and heavy rain. Specifically, we develop a novel transformer–fusion module embedded in a two-stream backbone network to robustly integrate the latent interactions between multimodal images (visible and infrared images). This enables the multimodal pedestrian detector to adapt to changing illumination conditions. Experimental results on two well-known datasets demonstrate that the proposed approach exhibits superior performance. The proposed TF-YOLO drastically improves the average precision of the state-of-the-art approach by 3.3% and reduces the miss rate of the state-of-the-art approach by about 6% on the challenging multi-scenario multi-modality dataset.

Exploring the Entropy Complex Networks with Latent Interaction.

In the present work, we study the introduction of a latent interaction index, examining its impact on the formation and development of complex networks. This index takes into account both observed and unobserved heterogeneity per node in order to overcome the limitations of traditional compositional similarity indices, particularly when dealing with large networks comprising numerous nodes. In this way, it effectively captures specific information about participating nodes while mitigating estimation problems based on network structures. Furthermore, we develop a Shannon-type entropy function to characterize the density of networks and establish optimal bounds for this estimation by leveraging the network topology. Additionally, we demonstrate some asymptotic properties of pointwise estimation using this function. Through this approach, we analyze the compositional structural dynamics, providing valuable insights into the complex interactions within the network. Our proposed method offers a promising tool for studying and understanding the intricate relationships within complex networks and their implications under parameter specification. We perform simulations and comparisons with the formation of Erdös-Rényi and Barabási-Alber-type networks and Erdös-Rényi and Shannon-type entropy. Finally, we apply our models to the detection of microbial communities.

Distinguishing latent interaction types from implicit feedbacks for recommendation

For privacy considerations, many recommendation algorithms are only based on a kind of implicit feedbacks, where various user behaviors, like view, purchase and etc., are simplified as binary interactions. As side information is assumed not available, these algorithms mainly focus on how to encode users and items via a bipartite graph (viz. the user-item interaction matrix), while ignoring to encode edges for distinguishing the interaction types. In this paper, we argue that implicit feedbacks can be classified into a few user-item relations (viz., latent interaction types) via encoding the edges of a bipartite graph. In particular, we design an edge distinguishment module (EDM) into our neural recommendation model, called Relation-Aware Neural Model (RANM). Based on the latent interaction types, we divide the bipartite graph into a few subgraphs, each consisting of only edges of the same relation and their connected user and item nodes. We propose a Relation-Aware Graph Neural Network (RAGNN) for learning user and item representations. For encoding items, we apply the RAGNN on the relation-aware bipartite graph; While for encoding a user, we first encode several latent interests each on one subgraph and then fuse these interest encodings as the user representation. Experiments on three public datasets validate that our approach of edge classification and representation learning help improving recommendation performance compared with the state-of-the-art competitors. The implementations are available at https://github.com/lulu0913/RAGNN.

Structure-informed clustering for population stratification in association studies

BackgroundIdentifying variants associated with complex traits is a challenging task in genetic association studies due to linkage disequilibrium (LD) between genetic variants and population stratification, unrelated to the disease risk. Existing methods of population structure correction use principal component analysis or linear mixed models with a random effect when modeling associations between a trait of interest and genetic markers. However, due to stringent significance thresholds and latent interactions between the markers, these methods often fail to detect genuinely associated variants.ResultsTo overcome this, we propose CluStrat, which corrects for complex arbitrarily structured populations while leveraging the linkage disequilibrium induced distances between genetic markers. It performs an agglomerative hierarchical clustering using the Mahalanobis distance covariance matrix of the markers. In simulation studies, we show that our method outperforms existing methods in detecting true causal variants. Applying CluStrat on WTCCC2 and UK Biobank cohorts, we found biologically relevant associations in Schizophrenia and Myocardial Infarction. CluStrat was also able to correct for population structure in polygenic adaptation of height in Europeans.ConclusionsCluStrat highlights the advantages of biologically relevant distance metrics, such as the Mahalanobis distance, which captures the cryptic interactions within populations in the presence of LD better than the Euclidean distance.

Multimodal transformer network for incomplete image generation and diagnosis of Alzheimer’s disease

Multimodal images such as magnetic resonance imaging (MRI) and positron emission tomography (PET) could provide complementary information about the brain and have been widely investigated for the diagnosis of neurodegenerative disorders such as Alzheimer’s disease (AD). However, multimodal brain images are often incomplete in clinical practice. It is still challenging to make use of multimodality for disease diagnosis with missing data. In this paper, we propose a deep learning framework with the multi-level guided generative adversarial network (MLG-GAN) and multimodal transformer (Mul-T) for incomplete image generation and disease classification, respectively. First, MLG-GAN is proposed to generate the missing data, guided by multi-level information from voxels, features, and tasks. In addition to voxel-level supervision and task-level constraint, a feature-level auto-regression branch is proposed to embed the features of target images for an accurate generation. With the complete multimodal images, we propose a Mul-T network for disease diagnosis, which can not only combine the global and local features but also model the latent interactions and correlations from one modality to another with the cross-modal attention mechanism. Comprehensive experiments on three independent datasets (i.e., ADNI-1, ADNI-2, and OASIS-3) show that the proposed method achieves superior performance in the tasks of image generation and disease diagnosis compared to state-of-the-art methods.

The Predictive Effect of Depression on Self-Injury: Positive Youth Development as a Moderator

While findings have documented the association between adolescent depression and self-injury, few studies have investigated the moderating effect of positive youth development (PYD) qualities on the association. This study examined concurrent and longitudinal predictive effects of depression and PYD qualities on nonsuicidal self-injury (NSSI) and suicidal self-injury (SSI) among Chinese adolescents. The moderating effects of PYD qualities were also studied. Two waves of data with an approximate 6-month interval were collected from five primary and secondary schools in Chengdu, China. A total of 6,948 adolescents aged 10 to 16 (Mage = 12.91, SD = 1.69 at the first wave, 51.17% boys) formed the working sample. Latent moderated structural equation modeling revealed that depression was a positive concurrent and longitudinal predictor of both NSSI and SSI whereas PYD qualities showed adverse concurrent and longitudinal predictive effects. The latent interaction effects were also significant in both cross-sectional and longitudinal models, with PYD qualities mitigating the positive effects of depression on NSSI and SSI. The results suggest that PYD qualities did not only directly reduce the risk of NSSI and SSI among adolescents but also attenuated the influence of depression on self-injury. These findings provide additional evidence for the protective role of PYD qualities in adolescent development and imply that improving PYD qualities may be a promising way to prevent and treat adolescent self-injury.

Adverse COVID-19 experiences and health-related quality of life in cancer survivors: indirect effects of COVID-19-related depression and financial burden

BackgroundCancer survivors are at greater risk for poor health outcomes due to COVID-19. However, the pandemic's impact on patients’ health-related quality of life (HRQoL) is not well known. This study hypothesized that cancer survivors' adverse COVID-19 experiences would be associated with worse HRQoL. Further, this association would be moderated by psychosocial resiliency factors (perceived social support, benefits, and ability to manage stress) and mediated by psychosocial risk factors (anxiety, depression; health, financial and social concerns).Methods1,043 cancer survivors receiving care at Northwestern Medicine completed a cross-sectional survey on COVID-19 practical and psychosocial concerns from 6/2021 to 3/2022. Participants reported on 21 adverse COVID-19 experiences (e.g., COVID-19 hospitalization, death of family/friends, loss of income, medical delays). The survey assessed 9 psychosocial factors related to COVID-19: anxiety, depression; health care, financial, and social disruptions; health care satisfaction; social support, perceived benefits, and stress management skills. The FACT-G7 assessed HRQoL. Hypotheses were tested in a structural equation model. The number of reported adverse COVID-19 experiences was the primary (observed) independent variable. The dependent variable of HRQoL, and the proposed mediating and moderating factors, were entered as latent variables indicated by their respective survey items. Latent interaction terms between the independent variable and each resiliency factor tested moderation effects. Analyses were adjusted for demographic and COVID-specific variables.ResultsParticipants were, on average, aged 58 years and diagnosed with cancer 4.9 years prior. They were majority female (73.3%), White (89.6%), non-Hispanic/Latino (94.5%), college-educated (81.7%), and vaccinated for COVID-19 (95.5%). An average of 3.8 adverse COVID-19 experiences were reported. Results of structural equation modeling demonstrated that the association between adverse COVID-19 experiences and HRQoL was explained by indirect effects through COVID-19-related depression (β = − 0.10, percentile bootstrap 95% CI − 0.15 to − 0.07) and financial concerns (β = − 0.04, percentile bootstrap 95% CI − 0.07 to − 0.01). Hypotheses testing moderation by resiliency factors were not significant.ConclusionsAdverse COVID-19 experiences were associated with higher depression symptoms and financial concerns about COVID-19, and in turn, worse HRQoL. Oncology clinics should be cognizant of the experience of adverse COVID-19 events when allocating depression and financial support resources.

Investigating Latent Interactions between Students' Affective Cognition and Learning Performance: Meta-Analysis of Affective and Cognitive Factors.

Affective and cognitive factors play significant roles in influencing students' learning performance. However, limited studies exist that examine the latent interactions between these factors and students' learning performance. This study applied a meta-analytic approach to examine the relationships between affective and cognitive factors and students' learning performance through the selected publications. We identified 18 affective and cognitive influencing factors related to student learning achievement/performance. It was found that academic performance was significantly impacted by learning scores, future aspirations and goals, peer support for learning, and family support for learning. A moderate impact was observed for cognitive benefits, skill development, self-regulation, values, knowledge, character, self-belief, attitudes and beliefs, affective benefits, motivation, optimism, and behavioral engagement. A weak influence was observed for control and relevance of schoolwork and self-efficacy. The discussion and limitations of this study have also been provided in the last sections.

Covariate-Informed Latent Interaction Models: Addressing Geographic & Taxonomic Bias in Predicting Bird–Plant Interactions

Reductions in natural habitats urge that we better understand species’ interconnection and how biological communities respond to environmental changes. However, ecological studies of species’ interactions are limited by their geographic and taxonomic focus which can distort our understanding of interaction dynamics. We focus on bird–plant interactions that refer to situations of potential fruit consumption and seed dispersal. We develop an approach for predicting species’ interactions that accounts for errors in the recorded interaction networks, addresses the geographic and taxonomic biases of existing studies, is based on latent factors to increase flexibility and borrow information across species, incorporates covariates in a flexible manner to inform the latent factors, and uses a meta-analysis dataset from 85 individual studies. We focus on interactions among 232 birds and 511 plants in the Atlantic Forest, and identify 5% of pairs of species with an unrecorded interaction, but posterior probability that the interaction is possible over 80%. Finally, we develop a permutation-based variable importance procedure for latent factor network models and identify that a bird’s body mass and a plant’s fruit diameter are important in driving the presence of species interactions, with a multiplicative relationship that exhibits both a thresholding and a matching behavior. Supplementary materials for this article are available online.

Learning theory for inferring interaction kernels in second-order interacting agent systems

Modeling the complex interactions of systems of particles or agents is a fundamental problem across the sciences, from physics and biology, to economics and social sciences. In this work, we consider second-order, heterogeneous, multivariable models of interacting agents or particles, within simple environments. We describe a nonparametric inference framework to efficiently estimate the latent interaction kernels which drive these dynamical systems. We develop a learning theory which establishes strong consistency and optimal nonparametric min–max rates of convergence for the estimators, as well as provably accurate predicted trajectories. The optimal rates only depends on intrinsic dimension of interactions, which is typically much smaller than the ambient dimension. Our arguments are based on a coercivity condition which ensures that the interaction kernels can be estimated in stable fashion. The numerical algorithm presented to build the estimators is parallelizable, performs well on high-dimensional problems, and its performance is tested on a variety of complex dynamical systems.

Spatiotemporal Interaction Pattern Recognition and Risk Evolution Analysis During Lane Changes

In complex lane change (LC) scenarios, semantic interpretation and safety analysis of dynamic interaction pattern are necessary for autonomous vehicles to make appropriate decisions. This study proposes a learning framework that combines primitive-based interaction pattern recognition and risk analysis. The Hidden Markov Model with the Gaussian mixture model (GMM-HMM) approach is developed to decompose the LC scenarios into primitives. Then K-means clustering with Dynamic Time Warping (DTW) is applied to gather the primitives into 13 LC interaction patterns. Finally, this study considers time-to-collision (TTC) of two conflict types involved in the LC process. And the TTC is used to analyze the risk of interaction patterns and extract high-risk LC interaction patterns. The LC events obtained from the Highway Drone Dataset (highD) demonstrate that the identified LC interaction patterns contain interpretable semantic information. This study identifies the dynamic spatiotemporal characteristics and risk formation mechanism of the LC interaction patterns. The findings are useful to comprehensively understand the latent interaction patterns, which can then be used to design and improve the decision-making process during lane changes and enhance the safety of autonomous vehicle.

Estimating Latent Baseline-by-Treatment Interactions in Statistical Mediation Analysis

Statistical mediation analysis is used to uncover intermediate variables, known as mediators [M], that explain how a treatment [X] changes an outcome [Y]. Often, researchers examine whether baseline levels of M and Y moderate the effect of X on posttest M or Y. However, there is limited guidance on how to estimate baseline-by-treatment interaction (BTI) effects when M and Y are latent variables, which entails the estimation of latent interaction effects. In this paper, we discuss two general approaches for estimating latent BTI effects in mediation analysis: using structural models or scoring latent variables prior to estimating observed BTIs and correcting for unreliability. We present simulation results describing bias, power, type 1 error rates, and interval coverage of the latent BTIs and mediated effects estimated using these approaches. These methods are also illustrated with an applied example. R and Mplus syntax are provided to facilitate the implementation of these approaches.

Quaternion-Valued Correlation Learning for Few-Shot Semantic Segmentation

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Encouraging progress has been made for FSS by leveraging semantic features learned from base classes with sufficient training samples to represent novel classes. The correlation-based methods lack the ability to consider interaction of the two subspace matching scores due to the inherent nature of the real-valued 2D convolutions. In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra. Specifically, our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace when considering the hidden relationship of the support sub-dimension in the quaternion space. Extensive experiments on the PASCAL-5 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>i</i></sup> and COCO-20 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>i</i></sup> datasets demonstrate that our method outperforms the existing state-of-the-art methods effectively.

Unsupervised relational inference using masked reconstruction

Problem settingStochastic dynamical systems in which local interactions give rise to complex emerging phenomena are ubiquitous in nature and society. This work explores the problem of inferring the unknown interaction structure (represented as a graph) of such a system from measurements of its constituent agents or individual components (represented as nodes). We consider a setting where the underlying dynamical model is unknown and where different measurements (i.e., snapshots) may be independent (e.g., may stem from different experiments).MethodOur method is based on the observation that the temporal stochastic evolution manifests itself in local patterns. We show that we can exploit these patterns to infer the underlying graph by formulating a masked reconstruction task. Therefore, we propose GINA (Graph Inference Network Architecture), a machine learning approach to simultaneously learn the latent interaction graph and, conditioned on the interaction graph, the prediction of the (masked) state of a node based only on adjacent vertices. Our method is based on the hypothesis that the ground truth interaction graph—among all other potential graphs—allows us to predict the state of a node, given the states of its neighbors, with the highest accuracy.ResultsWe test this hypothesis and demonstrate GINA’s effectiveness on a wide range of interaction graphs and dynamical processes. We find that our paradigm allows to reconstruct the ground truth interaction graph in many cases and that GINA outperforms statistical and machine learning baseline on independent snapshots as well as on time series data.

Executive functions predict the trajectories of rumination in middle-aged and older adults: A latent growth curve analysis.

Previous studies suggest that executive functions (EF)-a set of domain-general cognitive control processes that contribute to the regulation of emotion-are generally associated with ruminative tendencies. However, there is a dearth of research that examines how EF influences changes in rumination over time, especially in middle-aged and older adults who typically experience a decline in EF. To fill this gap in the literature, we analyzed a large-scale combined dataset from the MIDUS Refresher, Daily Diary, and Cognitive Projects. We examined the impact of EF on the trajectory of rumination across 8 days using latent growth curve analysis. We also examined age as a moderator using a latent interaction term in our structural equation model. Higher executive functioning predicted lower levels of baseline rumination and faster rates of decline in rumination over time, which reflect the successful regulation of maladaptive rumination. The age x EF interaction term was not significant, indicating that the impact of EF on the trajectory of rumination was not modulated by age. Our study offers new insights into the cognitive underpinnings of rumination and underscores the beneficial role of EF for effective regulation of ruminative tendencies in middle and late adulthood. (PsycInfo Database Record (c) 2022 APA, all rights reserved).