Powerful Representation Research Articles

When latent features meet side information: A preference relation based graph neural network for collaborative filtering

As recommender systems shift from rating-based to interaction-based models, graph neural network-based collaborative filtering models are gaining popularity due to their powerful representation of user-item interactions. However, these models may not produce good item ranking since they focus on explicit preference predictions. Further, these models do not consider side information since they only capture latent feature information of user-item interactions. This study proposes an approach to overcome these two issues by employing preference relation in the graph neural network model for collaborative filtering. Using preference relation ensures the model will generate a good ranking of items. The item side information is integrated into the model through a trainable matrix, which is crucial when the data is highly sparse. The main advantage of this approach is that the model can be generalized to any recommendation scenario where a graph neural network is used for collaborative filtering. Experimental results obtained using the recent RS datasets show that the proposed model outperformed the related baselines.

Generating pregnant patient biological profiles by deconvoluting clinical records with electronic health record foundation models.

Translational biology posits a strong bi-directional link between clinical phenotypes and a patient's biological profile. By leveraging this bi-directional link, we can efficiently deconvolute pre-existing clinical information into biological profiles. However, traditional computational tools are limited in their ability to resolve this link because of the relatively small sizes of paired clinical-biological datasets for training and the high dimensionality/sparsity of tabular clinical data. Here, we use state-of-the-art foundation models (FMs) for electronic health record (EHR) data to generate proteomics profiles of pregnant patients, thereby deconvoluting pre-existing clinical information into biological profiles without the cost and effort of running large-scale traditional omics studies. We show that FM-derived representations of a patient's EHR data coupled with a fully connected neural network prediction head can generate 206 blood protein expression levels. Interestingly, these proteins were enriched for developmental pathways, while proteins not able to be generated from EHR data were enriched for metabolic pathways. Finally, we show a proteomic signature of gestational diabetes that includes proteins with established and novel links to gestational diabetes. These results showcase the power of FM-derived EHR representations in efficiently generating biological states of pregnant patients. This capability can revolutionize disease understanding and therapeutic development, offering a cost-effective, time-efficient, and less invasive alternative to traditional methods of generating proteomics.

Robust self-supervised learning strategy to tackle the inherent sparsity in single-cell RNA-seq data.

Single-cell RNA sequencing (scRNA-seq) is a powerful tool for elucidating cellular heterogeneity and tissue function in various biological contexts. However, the sparsity in scRNA-seq data limits the accuracy of cell type annotation and transcriptomic analysis due to information loss. To address this limitation, we present scRobust, a robust self-supervised learning strategy to tackle the inherent sparsity of scRNA-seq data. Built upon the Transformer architecture, scRobust employs a novel self-supervised learning strategy comprising contrastive learning and gene expression prediction tasks. We demonstrated the effectiveness of scRobust using nine benchmarks, additional dropout scenarios, and combined datasets. scRobust outperformed recent methods in cell-type annotation tasks and generated cell embeddings that capture multi-faceted clustering information (e.g. cell types and HbA1c levels). In addition, cell embeddings of scRobust were useful for detecting specific marker genes related to drug tolerance stages. Furthermore, when we applied scRobust to scATAC-seq data, high-quality cell embedding vectors were generated. These results demonstrate the representational power of scRobust.

NsDCC: dual-level contrastive clustering with nonuniform sampling for scRNA-seq data analysis.

Dimensionality reduction and clustering are crucial tasks in single-cell RNA sequencing (scRNA-seq) data analysis, treated independently in the current process, hindering their mutual benefits. The latest methods jointly optimize these tasks through deep clustering. However, contrastive learning, with powerful representation capability, can bridge the gap that common deep clustering methods face, which requires pre-defined cluster centers. Therefore, a dual-level contrastive clustering method with nonuniform sampling (nsDCC) is proposed for scRNA-seq data analysis. Dual-level contrastive clustering, which combines instance-level contrast and cluster-level contrast, jointly optimizes dimensionality reduction and clustering. Multi-positive contrastive learning and unit matrix constraint are introduced in instance- and cluster-level contrast, respectively. Furthermore, the attention mechanism is introduced to capture inter-cellular information, which is beneficial for clustering. The nsDCC focuses on important samples at category boundaries and in minority categories by the proposed nearest boundary sparsest density weight assignment algorithm, making it capable of capturing comprehensive characteristics against imbalanced datasets. Experimental results show that nsDCC outperforms the six other state-of-the-art methods on both real and simulated scRNA-seq data, validating its performance on dimensionality reduction and clustering of scRNA-seq data, especially for imbalanced data. Simulation experiments demonstrate that nsDCC is insensitive to "dropout events" in scRNA-seq. Finally, cluster differential expressed gene analysis confirms the meaningfulness of results from nsDCC. In summary, nsDCC is a new way of analyzing and understanding scRNA-seq data.

Language-model-based patient embedding using electronic health records facilitates phenotyping, disease forecasting, and progression analysis.

Current studies regarding the secondary use of electronic health records (EHR) predominantly rely on domain expertise and existing medical knowledge. Though significant efforts have been devoted to investigating the application of machine learning algorithms in the EHR, efficient and powerful representation of patients is needed to unleash the potential of discovering new medical patterns underlying the EHR. Here, we present an unsupervised method for embedding high-dimensional EHR data at the patient level, aimed at characterizing patient heterogeneity in complex diseases and identifying new disease patterns associated with clinical outcome disparities. Inspired by the architecture of modern language models-specifically transformers with attention mechanisms, we use patient diagnosis and procedure codes as vocabularies and treat each patient as a sentence to perform the patient embedding. We applied this approach to 34,851 unique medical codes across 1,046,649 longitudinal patient events, including 102,739 patients from the electronic Medical Records and GEnomics (eMERGE) Network. The resulting patient vectors demonstrated excellent performance in predicting future disease events (median AUROC = 0.87 within one year) and bulk phenotyping (median AUROC = 0.84). We then illustrated the utility of these patient vectors in revealing heterogeneous comorbidity patterns, exemplified by disease subtypes in colorectal cancer and systemic lupus erythematosus, and capturing distinct longitudinal disease trajectories. External validation using EHR data from the University of Washington confirmed robust model performance, with median AUROCs of 0.83 and 0.84 for bulk phenotyping tasks and disease onset prediction, respectively. Importantly, the model reproduced the clustering results of disease subtypes identified in the eMERGE cohort and uncovered variations in overall mortality among these subtypes. Together, these results underscore the potential of representation learning in EHRs to enhance patient characterization and associated clinical outcomes, thereby advancing disease forecasting and facilitating personalized medicine.

Ship target detection in SAR images based on SimAM attention YOLOv8

AbstractDeep learning has been widely applied in ship detection in synthetic aperture radar (SAR) imagery due to their powerful feature representation capabilities. However, YOLOv8 models treat all regions of the image equally during convolutional feature processing, resulting in less‐than‐ideal outcomes. To address this limitation, this study proposes a simple, parameter‐free attention module (SimAM) attention‐based YOLOv8 algorithm for ship detection in SAR images. The proposed algorithm first passes through a backbone network, which incorporates SimAM attention modules. The SimAM attention mechanism successfully allocates the convolutional neural network's 3D weights effectively using an energy function method, without introducing additional parameters. This mechanism enables the network to automatically emphasize key features in the image, enhancing its ability to represent target areas and suppress background interference. Subsequently, deep features are upsampled and fused with relatively shallow features to extract features at three different scales and achieve target detection, ultimately outputting classification and positional information of the targets. The effectiveness of the model on the SAR‐ship‐dataset is experimentally validated achieving an mAP50 value of 97.72% and an mAP50‐95 value of 68.99%, confirming the superiority of the proposed model.

Reading ideological power representations through space: the tale of two cities Berlin and Ankara

The study explores the entangled relationship between power dynamics and urban spaces particularly governmental spaces. Drawing from Foucault's conceptualization of power as a nuanced interplay of social processes, the research explores Berlin and Ankara's governmental structures and regarding urban plans while unveiling how power is manifested in built environments. However, rather than a comparative analysis, the study presents narratives of these cities since each reflects a unique historical contexts and power dynamics i.e. Berlin, is a historical centre of power, contrasting with Ankara, which presents republic's capital as a modernisation shift. The study uses, descriptive analysis and reveals how power is articulated within urban spaces and societal structures, while crystalising the shifts in political ideologies and their impact on governance structures. Therefore, study aims to investigate the role of urban planning and architecture in shaping power dynamics in relation to ideologies whether represented openly or subtle within the urban realm. The research, following descriptive analysis for the subjected cities, draws on secondary data as its primary source, and interprets the data through the lens of Lefebvre's dialectic of production of space and Dovey's investigations into power dynamics within the built environment, along with other contributions to the urban space and power literature. Ultimately, urban planning and architecture serve as representations of power, shaping societal narratives and identities. The study underscores the significance of understanding these narratives to comprehend the societal impacts of governance structures and power dynamics over time.

You’re doing it wrong: the governance of motherhood through mommy blogs

ABSTRACT Mommy blog communities have been established by mothers who publish their stories online with the stated purpose to empower themselves and their peers by offering a seemingly unfiltered representation of motherhood. While this benefit has been felt by many readers, there are invisible governing discourses that have prevented such blogs from becoming authentic spaces of resistance to the hegemonic ideals of motherhood. To understand the governing forces placed upon mothers through “mommy blogs,” we explored the question: How is motherhood shaped through narratives (re)presented in mommy blogs? Critical discourse analysis, informed by a governmentality perspective, was used to analyze mommy blog entries to illuminate representations of power and knowledge within the blog entries. The findings suggest that a governmentality perspective is useful in understanding how mommy blogs enact power over mothers using mechanisms of governance through 1) sameness and imperfection, 2) perceived self-compassion, 3) advice and support, and 4) the scientification of motherhood. As more people turn to online communities for support with the experience of mothering, it is important to garner a critical understanding of how mommy blogs continue to influence contemporary experiences of motherhood.

CCM-Net: Color compensation and coordinate attention guided underwater image enhancement with multi-scale feature aggregation

Due to the light scattering and wavelength absorption in water, underwater images exhibit blurred details, low contrast, and color deviation. Existing underwater image enhancement methods are divided into traditional methods and deep learning-based methods. Traditional methods either rely on scene prior and lack robustness, or are not flexible enough resulting in poor enhancement effects. Deep learning methods have achieved good results in the field of underwater image enhancement due to their powerful feature representation ability. However, these methods cannot enhance underwater images with various degradations because they do not consider the inconsistent attenuation of different color channels and spatial regions. In this paper, we propose a novel asymmetric encoder-decoder network for underwater image enhancement, called CCM-Net. Concretely, we first introduce the prior knowledge-based encoder, which includes color compensation (CC) modules and feature extraction modules that consist of depth-wise separable convolution and global-local coordinate attention (GLCA). Then, we design a multi-scale feature aggregation (MFA) module to integrate shallow, middle, and deep features. Finally, we deploy a decoder to reconstruct the underwater images with the extracted features. Extensive experiments on publicly available datasets demonstrate that our CCM-Net effectively improves the visual quality of underwater images and achieves impressive performance.

Piecewise Developable Modeling via Implicit Neural Deformation and Feature-Guided Cutting.

We propose a novel and automatic method to model shapes using a small set of discrete developable patches. Central to our approach is using implicit neural shape representation that makes our algorithm independent of tessellation and allows us to obtain the Gaussian curvature of each point analytically. With this powerful representation, we first deform the input shape to be an almost developable shape with clear and sparse salient feature curves. Then, we convert the deformed implicit field to a triangle mesh, which is further cut to disk topology along parts of the sparse feature curves. Finally, we achieve the resulting piecewise developable mesh by alternatingly optimizing discrete developability, enforcing manufacturability constraints, and merging patches. The feasibility and practicability of our method are demonstrated over various shapes. Compared to the state-of-the-art methods, our method achieves a better tradeoff between the number of developable patches and the approximation error.

Sang-e-Mah (2022): Hamlet , Gendered Violence, and Female Identity on Pakistani Television

Abstract: This article analyzes the Urdu drama serial Sang-e-Mah 2022, broadcast on Pakistani television, arguing that it relocates William Shakespeare’s Hamlet within cultural, regional, and national identities in Pakistan’s Khyber Pakhtunkhwa (KPK) province. The serial draws on Shakespeare’s play to offer a social commentary on female identity and gender-based violence in relation to the cultural practice of ghag in KPK. Examining the representation of female oppression, power, and agency on Pakistani television in the context of KPK, the article argues that the serial both disrupts the power dynamics of Hamlet and challenges gender roles in KPK in its attempt to redefine attitudes towards women in Pakistan.Ultimately, this article illustrates that Sang-e-Mah “localizes” Shakespeare’s play to allow it to participate in global conversations about the violation of women’s rights, the violation of law and order, and the valorization of gun cultures.

3D Reconstruction of Indoor Scenes Based on 3DGS Models

Abstract Abstract With the rapid development of computer vision and artificial intelligence technologies, indoor scene reconstruction has been more and more widely used in the fields of virtual reality, augmented reality and architectural design. In this paper, we study an indoor scene reconstruction method based on the 3DGS model, which has been widely used in computer graphics and vision processing with powerful scene representation and rendering capabilities. In this study, we optimize the 3DGS model to enhance the detail preservation and realism of the reconstruction results by adjusting the opacity of the Gaussian function. We used the Replica dataset and the self-harvested dataset for model training. Through experimental validation, the peak signal-to-noise ratio as well as the structural similarity ratio of the reconstruction results of the optimized model have an improvement effect of more than 1%, which indicates that the optimized model has a significant improvement in detail retention and realism, and the reconstructed scene performs more realistically in terms of texture details and light and shadow effects.

Self-supervised learning for efficient seismic facies classification

Seismic facies classification is an important task in seismic interpretation that allows the identification of rock bodies with similar physical characteristics. Manual labeling of seismic data is immensely time consuming, given the recent surge in data volumes. Self-supervised learning (SSL) enables models to learn powerful representations from unlabeled data, thereby improving performance in downstream tasks using limited labeled data. We investigate the effectiveness of SSL for efficient facies classification by evaluating various convolutional and vision transformer-based models. We pretrain the models on image reconstruction and fine-tune them on facies segmentation. Results on the southern North Sea F3 seismic block in the Netherlands and the Penobscot seismic volume in the Sable Subbasin, offshore Nova Scotia, Canada, show that SSL has comparable performance to supervised learning using only 5%–10% labeled data. Further, SSL exhibits stable domain adaptation on the Penobscot data set even with 5% labeled data, indicating an improved generalization compared with the supervised learning setup. The findings demonstrate that SSL significantly enhances model accuracy and data efficiency for seismic facies classification.

The Research on Intelligent News Advertisement Recommendation Algorithm Based on Prompt Learning in End-to-End Large Language Model Architecture

With the explosive growth of information on the internet, users are increasingly facing the problem of information overload, making precise news and ad recommendations an important area of research. While traditional recommendation algorithms can meet user needs to some extent, they still have limitations in dealing with complex and changing user behaviors and dynamic content environments. This paper addresses the shortcomings of existing news and ad recommendation systems by proposing an intelligent recommendation algorithm based on an end-to-end large language model architecture. Firstly, we utilize the BERT model as the foundation, leveraging its powerful text representation capabilities to achieve deep semantic understanding of news and ad content, thereby capturing more detailed content features. Secondly, we apply prompt learning to fine-tune the BERT model, designing specific prompts for the model to better understand the implicit needs and preferences of users. Finally, we integrate these steps into an end-to-end architecture, enabling the model to achieve automated learning and optimization throughout the entire process from input to output, thus improving the precision and efficiency of recommendations. Experimental results demonstrate that the proposed method significantly outperforms traditional methods in the task of news and ad recommendation, not only enhancing the accuracy and relevance of recommendations but also effectively improving the model's interpretability and flexibility. This research explores new possibilities for the application of large language models in recommendation systems.

A Lockean Analysis of the Problem of Sovereignty and Legitimacy in Shakespeare’s King John

This article examines the representation of authority, political power, and legitimacy in William Shakespeare’s King John through relating them to John Locke’s Second Treatise of Government to put forth that such concepts have parallels within the two works. King John provides a means to examine the dynamics of political power and ambition, as the king has doubtful claims to the English throne when examined from Locke’s point of view. In relation to Shakespeare’s work, Locke’s Second Treatise of Government establishes a philosophical foundation for the principles of political authority and its legitimacy in which there is the possibility of resistance to the King. Locke’s ideas on property rights, consent, and the social contract had an impact on political theory during the Enlightenment. This article, therefore, discusses the impact of Locke’s theories on the political discussion of the era by juxtaposing them with the plot and characters in King John. Finally, the study establishes a correlation between the play and Locke’s work by demonstrating their similarities through an examination of both works which in the end puts forth the basic principles of the idea of resisting the King.

Quantum-classical separations in shallow-circuit-based learning with and without noises

An essential problem in quantum machine learning is to find quantum-classical separations between learning models. However, rigorous and unconditional separations are lacking for supervised learning. Here we construct a classification problem defined by a noiseless constant depth (i.e., shallow) quantum circuit and rigorously prove that any classical neural network with bounded connectivity requires logarithmic depth to output correctly with a larger-than-exponentially-small probability. This unconditional near-optimal quantum-classical representation power separation originates from the quantum nonlocality property that distinguishes quantum circuits from their classical counterparts. We further characterize the noise regimes for demonstrating such a separation on near-term quantum devices under the depolarization noise model. In addition, for quantum devices with constant noise strength, we prove that no super-polynomial classical-quantum separation exists for any classification task defined by Clifford circuits, independent of the structures of the circuits that specify the learning models.

Towards a neuro-symbolic cycle for human-centered explainability

Deep learning is being very successful in supporting humans in the interpretation of complex data (such as images and text) for critical decision tasks. However, it still remains difficult for human experts to understand how such results are achieved, due to the “black box” nature of the deep models used. In high-stake decision making scenarios such as the interpretation of medical imaging for diagnostics, such a lack of transparency still hinders the adoption of these techniques in practice. In this position paper we present a conceptual methodology for the design of a neuro-symbolic cycle to address the need for explainability and confidence (including trust) of deep learning models when used to support human experts in high-stake decision making, and we discuss challenges and opportunities in the implementation of such cycle as well as its adoption in real world scenarios. We elaborate on the need to leverage the potential of hybrid artificial intelligence combining neural learning and symbolic reasoning in a human-centered approach to explainability. We advocate that the phases of such a cycle should include i) the extraction of knowledge from a trained network to represent and encode its behaviour, ii) the validation of the extracted knowledge through commonsense and domain knowledge, iii) the generation of explanations for human experts, iv) the ability to map human feedback into the validated representation from i), and v) the injection of some of this knowledge in a non-trained network to enable knowledge-informed representation learning. The holistic combination of causality, expressive logical inference, and representation learning, would result in a seamless integration of (neural) learning and (cognitive) reasoning that makes it possible to retain access to the inherently explainable symbolic representation without losing the power of the deep representation. The involvement of human experts in the design, validation and knowledge injection process is crucial, as the conceptual approach paves the way for a new human–ai paradigm where the human role goes beyond that of labeling data, towards the validation of neural-cognitive knowledge and processes.

URINet: Unsupervised point cloud rotation invariant representation learning via semantic and structural reasoning

In recent years, many rotation-invariant networks have been proposed to alleviate the interference caused by point cloud arbitrary rotations. These networks have demonstrated powerful representation learning capabilities. However, most of those methods rely on costly manually annotated supervision for model training. Moreover, they fail to reason the structural relations and lose global information. To address these issues, we present an unsupervised method for achieving comprehensive rotation invariant representations without human annotation. Specifically, we propose a novel encoder–decoder architecture named URINet, which learns a point cloud representation by combining local semantic and global structural information, and then reconstructs the input without rotation perturbation. In detail, the encoder is a two-branch network where the graph convolution based structural branch models the relationships among local regions to learn global structural knowledge and the semantic branch learns rotation invariant local semantic features. The two branches derive complementary information and explore the point clouds comprehensively. Furthermore, to avoid the self-reconstruction ambiguity brought by uncertain poses, a bidirectional alignment is proposed to measure the quality of reconstruction results without orientation knowledge. Extensive experiments on downstream tasks show that the proposed method significantly surpasses existing state-of-the-art methods on both synthetic and real-world datasets.

Postcolonial Empowerment and Resilience: Female Protagonists in Groff’s Matrix (2021) and Azar’s Greengage Tree (2020)

This study examines Lauren Groff’s Matrix (2021) and Shokoofeh Azar’s The Enlightenment of the Greengage Tree (2020) through the lens of Postcolonial Theory, focusing on themes of empowerment, resilience, and self-discovery within distinct historical and cultural settings. The main question addresses how these novels portray power dynamics, identity, representation, and resistance. The aim is to uncover how each protagonist—Marie de France in medieval Europe and Bahar in post-revolutionary Iran—navigates and challenges their respective social structures. Key findings reveal that Matrix delves into the power struggles within the Catholic Church and its colonial ambitions, while The Enlightenment of the Greengage Tree explores the impact of Western influence on Iranian society. The significance of this study lies in its contribution to understanding the complexities of female agency in different cultural contexts. Recommendations include further research on similar themes in contemporary literature.

Blinding the Male Gaze with Gaze: Exploring the Agency of Gaze in Amrita Sher-Gil’s Paintings as Statements Against Masculine Stereotypes

Amrita Sher-Gil’s paintings deploy ocular symbolism that serves as potent tools in dismantling and redefining prevailing masculine stereotypes of Indian society. Her distinctive approach to paintings turns her canvases into eloquent statements against patriarchal paradigms and norms regarding the role and position of women. Sher-Gil adeptly reclaims female subjectivity, proposes incisive discourses disrupting gender-centric power dynamics, delves into the inner recesses of the female psyche, and, notably, provides a poignantly realistic depiction of the emotional struggles faced by subaltern Indian women, as illustrated in her notable works such as Hill Women and Self-Portrait as a Tahitian where the motif of paired eyes functions as the conduit to convey these sentiments and statements. Her paintings like Two Women challenge the male gaze on nudity and celebrate female confidence and autonomy, subverting traditional gender expectations. She further challenges societal norms surrounding marriage in her painting Bride, where defiant gazes question prescribed roles for women. Overall, ‘gaze’ stands as a central motif in Sher-Gil’s paintings that serves as a device to expose, question, and challenge the stereotypical male gaze. The current research aims to underscore the way Sher-Gil, through her representation of women incorporating a bold execution of the motif of gaze, provides statements against the oppressive aspects of Indian patriarchy and attempts to defy the repressive male perspective. This study, through a critical virtual culture analysis of the relevant artworks, intends to reveal the gender-based socio-cultural implications embedded in Sher-Gil’s oeuvre primarily using Griselda Pollock’s idea of the power dynamics, gaze, and representation proposed in Vision and Difference and Laura Mulvey’s notion of the male gaze.