PyTorchKR Papers

최신 논문

총 697편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2311.06130공식 코드 · Papers with Code

High-dimensional mixed-categorical Gaussian processes with application to multidisciplinary design optimization for a green aircraft

Recently, there has been a growing interest in mixed-categorical metamodels based on Gaussian Process (GP) for Bayesian optimization. In this context, different approaches can be used to build the mixed-categorical GP. Many of these approaches involve a high number of hyperparameters; in fact, the more general and precise the strategy used to build the GP, the greater the number of hyperparameters to estimate. This paper introduces an innovative dimension reduction algorithm that relies on partial least squares regression to reduce the number of hyperparameters used to build a mixed-variable GP. Our goal is to generalize classical dimension reduction techniques commonly used within GP (for continuous inputs) to handle mixed-categorical inputs. The good potential of the proposed method is demonstrated in both structural and multidisciplinary application contexts. The targeted applications include the analysis of a cantilever beam as well as the optimization of a green aircraft, resulting in a significant 439-kilogram reduction in fuel consumption during a single mission.

arXiv:2311.04855공식 코드 · Papers with Code

Algorithms for Non-Negative Matrix Factorization on Noisy Data With Negative Values

Non-negative matrix factorization (NMF) is a dimensionality reduction technique that has shown promise for analyzing noisy data, especially astronomical data. For these datasets, the observed data may contain negative values due to noise even when the true underlying physical signal is strictly positive. Prior NMF work has not treated negative data in a statistically consistent manner, which becomes problematic for low signal-to-noise data with many negative values. In this paper we present two algorithms, Shift-NMF and Nearly-NMF, that can handle both the noisiness of the input data and also any introduced negativity. Both of these algorithms use the negative data space without clipping, and correctly recover non-negative signals without any introduced positive offset that occurs when clipping negative data. We demonstrate this numerically on both simple and more realistic examples, and prove that both algorithms have monotonically decreasing update rules.

arXiv:2311.03409공식 코드 · Papers with Code

Visualizing DNA reaction trajectories with deep graph embedding approaches

Synthetic biologists and molecular programmers design novel nucleic acid reactions, with many potential applications. Good visualization tools are needed to help domain experts make sense of the complex outputs of folding pathway simulations of such reactions. Here we present ViDa, a new approach for visualizing DNA reaction folding trajectories over the energy landscape of secondary structures. We integrate a deep graph embedding model with common dimensionality reduction approaches, to map high-dimensional data onto 2D Euclidean space. We assess ViDa on two well-studied and contrasting DNA hybridization reactions. Our preliminary results suggest that ViDa's visualization successfully separates trajectories with different folding mechanisms, thereby providing useful insight to users, and is a big improvement over the current state-of-the-art in DNA kinetics visualization.

arXiv:2311.03411공식 코드 · Papers with Code

ViDa: Visualizing DNA hybridization trajectories with biophysics-informed deep graph embeddings

Visualization tools can help synthetic biologists and molecular programmers understand the complex reactive pathways of nucleic acid reactions, which can be designed for many potential applications and can be modelled using a continuous-time Markov chain (CTMC). Here we present ViDa, a new visualization approach for DNA reaction trajectories that uses a 2D embedding of the secondary structure state space underlying the CTMC model. To this end, we integrate a scattering transform of the secondary structure adjacency, a variational autoencoder, and a nonlinear dimensionality reduction method. We augment the training loss with domain-specific supervised terms that capture both thermodynamic and kinetic features. We assess ViDa on two well-studied DNA hybridization reactions. Our results demonstrate that the domain-specific features lead to significant quality improvements over the state-of-the-art in DNA state space visualization, successfully separating different folding pathways and thus providing useful insights into dominant reaction mechanisms.

arXiv:2311.03313공식 코드 · Papers with Code

Practical considerations for variable screening in the super learner

Estimating a prediction function is a fundamental component of many data analyses. The super learner ensemble, a particular implementation of stacking, has desirable theoretical properties and has been used successfully in many applications. Dimension reduction can be accomplished by using variable screening algorithms (screeners), including the lasso, within the ensemble prior to fitting other prediction algorithms. However, the performance of a super learner using the lasso for dimension reduction has not been fully explored in cases where the lasso is known to perform poorly. We provide empirical results that suggest that a diverse set of candidate screeners should be used to protect against poor performance of any one screener, similar to the guidance for choosing a library of prediction algorithms for the super learner. These results are further illustrated through the analysis of HIV-1 antibody data.

arXiv:2311.01840공식 코드 · Papers with Code

Spectral Clustering of Attributed Multi-relational Graphs

Graph clustering aims at discovering a natural grouping of the nodes such that similar nodes are assigned to a common cluster. Many different algorithms have been proposed in the literature: for simple graphs, for graphs with attributes associated to nodes, and for graphs where edges represent different types of relations among nodes. However, complex data in many domains can be represented as both attributed and multi-relational networks. In this paper, we propose SpectralMix, a joint dimensionality reduction technique for multi-relational graphs with categorical node attributes. SpectralMix integrates all information available from the attributes, the different types of relations, and the graph structure to enable a sound interpretation of the clustering results. Moreover, it generalizes existing techniques: it reduces to spectral embedding and clustering when only applied to a single graph and to homogeneity analysis when applied to categorical data. Experiments conducted on several real-world datasets enable us to detect dependencies between graph structure and categorical attributes, moreover, they exhibit the superiority of SpectralMix over existing methods.

arXiv:2311.00768공식 코드 · Papers with Code

Language Model Training Paradigms for Clinical Feature Embeddings

In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and blood pressure. We use self-supervised training paradigms for language models to learn high-quality clinical feature embeddings, achieving a finer granularity than existing time-step and patient-level representation learning. We visualize the learnt embeddings via unsupervised dimension reduction techniques and observe a high degree of consistency with prior clinical knowledge. We also evaluate the model performance on the MIMIC-III benchmark and demonstrate the effectiveness of using clinical feature embeddings. We publish our code online for replication.

arXiv:2310.19845공식 코드 · Papers with Code

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

Recently, spam on online social networks has attracted attention in the research and business world. Twitter has become the preferred medium to spread spam content. Many research efforts attempted to encounter social networks spam. Twitter brought extra challenges represented by the feature space size, and imbalanced data distributions. Usually, the related research works focus on part of these main challenges or produce black-box models. In this paper, we propose a modified genetic algorithm for simultaneous dimensionality reduction and hyper parameter optimization over imbalanced datasets. The algorithm initialized an eXtreme Gradient Boosting classifier and reduced the features space of tweets dataset; to generate a spam prediction model. The model is validated using a 50 times repeated 10-fold stratified cross-validation, and analyzed using nonparametric statistical tests. The resulted prediction model attains on average 82.32\% and 92.67\% in terms of geometric mean and accuracy respectively, utilizing less than 10\% of the total feature space. The empirical results show that the modified genetic algorithm outperforms $Chi^2$ and $PCA$ feature selection methods. In addition, eXtreme Gradient Boosting outperforms many machine learning algorithms, including BERT-based deep learning model, in spam prediction. Furthermore, the proposed approach is applied to SMS spam modeling and compared to related works.

arXiv:2310.20601공식 코드 · Papers with Code

Modular Boundaries in Recurrent Neural Networks

Recent theoretical and experimental work in neuroscience has focused on the representational and dynamical character of neural manifolds --subspaces in neural activity space wherein many neurons coactivate. Importantly, neural populations studied under this "neural manifold hypothesis" are continuous and not cleanly divided into separate neural populations. This perspective clashes with the "modular hypothesis" of brain organization, wherein neural elements maintain an "all-or-nothing" affiliation with modules. In line with this modular hypothesis, recent research on recurrent neural networks suggests that multi-task networks become modular across training, such that different modules specialize for task-general dynamical motifs. If the modular hypothesis is true, then it would be important to use a dimensionality reduction technique that captures modular structure. Here, we investigate the features of such a method. We leverage RNNs as a model system to study the character of modular neural populations, using a community detection method from network science known as modularity maximization to partition neurons into distinct modules. These partitions allow us to ask the following question: do these modular boundaries matter to the system? ...

arXiv:2310.11736공식 코드 · Papers with Code

Layered Models can "Automatically" Regularize and Discover Low-Dimensional Structures via Feature Learning

Layered models like neural networks appear to extract key features from data through empirical risk minimization, yet the theoretical understanding for this process remains unclear. Motivated by these observations, we study a two-layer nonparametric regression model where the input undergoes a linear transformation followed by a nonlinear mapping to predict the output, mirroring the structure of two-layer neural networks. In our model, both layers are optimized jointly through empirical risk minimization, with the nonlinear layer modeled by a reproducing kernel Hilbert space induced by a rotation and translation invariant kernel, regularized by a ridge penalty. Our main result shows that the two-layer model can "automatically" induce regularization and facilitate feature learning. Specifically, the two-layer model promotes dimensionality reduction in the linear layer and identifies a parsimonious subspace of relevant features -- even without applying any norm penalty on the linear layer. Notably, this regularization effect arises directly from the model's layered structure, independent of optimization dynamics. More precisely, assuming the covariates have nonzero explanatory power for the response only through a low dimensional subspace (central mean subspace), the linear layer consistently estimates both the subspace and its dimension. This demonstrates that layered models can inherently discover low-complexity solutions relevant for prediction, without relying on conventional regularization methods. Real-world data experiments further demonstrate the persistence of this phenomenon in practice.

arXiv:2310.11186공식 코드 · Papers with Code

Efficiently Visualizing Large Graphs

Most existing graph visualization methods based on dimension reduction are limited to relatively small graphs due to performance issues. In this work, we propose a novel dimension reduction method for graph visualization, called t-Distributed Stochastic Graph Neighbor Embedding (t-SGNE). t-SGNE is specifically designed to visualize cluster structures in the graph. As a variant of the standard t-SNE method, t-SGNE avoids the time-consuming computations of pairwise similarity. Instead, it uses the neighbor structures of the graph to reduce the time complexity from quadratic to linear, thus supporting larger graphs. In addition, to suit t-SGNE, we combined Laplacian Eigenmaps with the shortest path algorithm in graphs to form the graph embedding algorithm ShortestPath Laplacian Eigenmaps Embedding (SPLEE). Performing SPLEE to obtain a high-dimensional embedding of the large-scale graph and then using t-SGNE to reduce its dimension for visualization, we are able to visualize graphs with up to 300K nodes and 1M edges within 5 minutes and achieve approximately 10% improvement in visualization quality. Codes and data are available at https://github.com/Charlie-XIAO/embedding-visualization-test.

arXiv:2310.02954공식 코드 · Papers with Code

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning

Recent advances in natural language processing, primarily propelled by Large Language Models (LLMs), have showcased their remarkable capabilities grounded in in-context learning. A promising avenue for guiding LLMs in intricate reasoning tasks involves the utilization of intermediate reasoning steps within the Chain-of-Thought (CoT) paradigm. Nevertheless, the central challenge lies in the effective selection of exemplars for facilitating in-context learning. In this study, we introduce a framework that leverages Dual Queries and Low-rank approximation Re-ranking (DQ-LoRe) to automatically select exemplars for in-context learning. Dual Queries first query LLM to obtain LLM-generated knowledge such as CoT, then query the retriever to obtain the final exemplars via both question and the knowledge. Moreover, for the second query, LoRe employs dimensionality reduction techniques to refine exemplar selection, ensuring close alignment with the input question's knowledge. Through extensive experiments, we demonstrate that DQ-LoRe significantly outperforms prior state-of-the-art methods in the automatic selection of exemplars for GPT-4, enhancing performance from 92.5% to 94.2%. Our comprehensive analysis further reveals that DQ-LoRe consistently outperforms retrieval-based approaches in terms of both performance and adaptability, especially in scenarios characterized by distribution shifts. DQ-LoRe pushes the boundary of in-context learning and opens up new avenues for addressing complex reasoning challenges. Our code is released at https://github.com/AI4fun/DQ-LoRe}{https://github.com/AI4fun/DQ-LoRe.

arXiv:2310.00839공식 코드 · Papers with Code

Subsurface Characterization using Ensemble-based Approaches with Deep Generative Models

Estimating spatially distributed properties such as hydraulic conductivity (K) from available sparse measurements is a great challenge in subsurface characterization. However, the use of inverse modeling is limited for ill-posed, high-dimensional applications due to computational costs and poor prediction accuracy with sparse datasets. In this paper, we combine Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), a deep generative model that can accurately capture complex subsurface structure, and Ensemble Smoother with Multiple Data Assimilation (ES-MDA), an ensemble-based inversion method, for accurate and accelerated subsurface characterization. WGAN-GP is trained to generate high-dimensional K fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface examples are used to evaluate the accuracy and efficiency of the proposed method and the main features of the unknown K fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method, especially for the channelized and fractured field examples. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

arXiv:2309.14857공식 코드 · Papers with Code

Cluster Exploration using Informative Manifold Projections

Dimensionality reduction (DR) is one of the key tools for the visual exploration of high-dimensional data and uncovering its cluster structure in two- or three-dimensional spaces. The vast majority of DR methods in the literature do not take into account any prior knowledge a practitioner may have regarding the dataset under consideration. We propose a novel method to generate informative embeddings which not only factor out the structure associated with different kinds of prior knowledge but also aim to reveal any remaining underlying structure. To achieve this, we employ a linear combination of two objectives: firstly, contrastive PCA that discounts the structure associated with the prior information, and secondly, kurtosis projection pursuit which ensures meaningful data separation in the obtained embeddings. We formulate this task as a manifold optimization problem and validate it empirically across a variety of datasets considering three distinct types of prior knowledge. Lastly, we provide an automated framework to perform iterative visual exploration of high-dimensional data.

arXiv:2309.10000공식 코드 · Papers with Code

Detecting covariate drift in text data using document embeddings and dimensionality reduction

Detecting covariate drift in text data is essential for maintaining the reliability and performance of text analysis models. In this research, we investigate the effectiveness of different document embeddings, dimensionality reduction techniques, and drift detection methods for identifying covariate drift in text data. We explore three popular document embeddings: term frequency-inverse document frequency (TF-IDF) using Latent semantic analysis(LSA) for dimentionality reduction and Doc2Vec, and BERT embeddings, with and without using principal component analysis (PCA) for dimensionality reduction. To quantify the divergence between training and test data distributions, we employ the Kolmogorov-Smirnov (KS) statistic and the Maximum Mean Discrepancy (MMD) test as drift detection methods. Experimental results demonstrate that certain combinations of embeddings, dimensionality reduction techniques, and drift detection methods outperform others in detecting covariate drift. Our findings contribute to the advancement of reliable text analysis models by providing insights into effective approaches for addressing covariate drift in text data.

arXiv:2309.10775공식 코드 · Papers with Code

$O(k)$-Equivariant Dimensionality Reduction on Stiefel Manifolds

Many real-world datasets live on high-dimensional Stiefel and Grassmannian manifolds, $V_k(\mathbb{R}^N)$ and $Gr(k, \mathbb{R}^N)$ respectively, and benefit from projection onto lower-dimensional Stiefel and Grassmannian manifolds. In this work, we propose an algorithm called \textit{Principal Stiefel Coordinates (PSC)} to reduce data dimensionality from $ V_k(\mathbb{R}^N)$ to $V_k(\mathbb{R}^n)$ in an \textit{$O(k)$-equivariant} manner ($k \leq n \ll N$). We begin by observing that each element $\alpha \in V_n(\mathbb{R}^N)$ defines an isometric embedding of $V_k(\mathbb{R}^n)$ into $V_k(\mathbb{R}^N)$. Next, we describe two ways of finding a suitable embedding map $\alpha$: one via an extension of principal component analysis ($\alpha_{PCA}$), and one that further minimizes data fit error using gradient descent ($\alpha_{GD}$). Then, we define a continuous and $O(k)$-equivariant map $\pi_\alpha$ that acts as a "closest point operator" to project the data onto the image of $V_k(\mathbb{R}^n)$ in $V_k(\mathbb{R}^N)$ under the embedding determined by $\alpha$, while minimizing distortion. Because this dimensionality reduction is $O(k)$-equivariant, these results extend to Grassmannian manifolds as well. Lastly, we show that $\pi_{\alpha_{PCA}}$ globally minimizes projection error in a noiseless setting, while $\pi_{\alpha_{GD}}$ achieves a meaningfully different and improved outcome when the data does not lie exactly on the image of a linearly embedded lower-dimensional Stiefel manifold as above. Multiple numerical experiments using synthetic and real-world data are performed.

arXiv:2309.08077공식 코드 · Papers with Code

Supervised Stochastic Neighbor Embedding Using Contrastive Learning

Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization. Contrastive learning, especially self-supervised contrastive learning (SSCL), has showed great success in embedding features from unlabeled data. The conceptual connection between SNE and SSCL has been exploited. In this work, within the scope of preserving neighboring information of a dataset, we extend the self-supervised contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information. Clusters of samples belonging to the same class are pulled together in low-dimensional embedding space, while simultaneously pushing apart clusters of samples from different classes.

arXiv:2309.06708공식 코드 · Papers with Code

Predicting Fatigue Crack Growth via Path Slicing and Re-Weighting

Predicting potential risks associated with the fatigue of key structural components is crucial in engineering design. However, fatigue often involves entangled complexities of material microstructures and service conditions, making diagnosis and prognosis of fatigue damage challenging. We report a statistical learning framework to predict the growth of fatigue cracks and the life-to-failure of the components under loading conditions with uncertainties. Digital libraries of fatigue crack patterns and the remaining life are constructed by high-fidelity physical simulations. Dimensionality reduction and neural network architectures are then used to learn the history dependence and nonlinearity of fatigue crack growth. Path-slicing and re-weighting techniques are introduced to handle the statistical noises and rare events. The predicted fatigue crack patterns are self-updated and self-corrected by the evolving crack patterns. The end-to-end approach is validated by representative examples with fatigue cracks in plates, which showcase the digital-twin scenario in real-time structural health monitoring and fatigue life prediction for maintenance management decision-making.

arXiv:2309.00903공식 코드 · Papers with Code

An explainable three dimension framework to uncover learning patterns: A unified look in variable sulci recognition

The significant features identified in a representative subset of the dataset during the learning process of an artificial intelligence model are referred to as a 'global' explanation. 3D global explanations are crucial in neuroimaging, where a complex representational space demands more than basic 2D interpretations. However, current studies in the literature often lack the accuracy, comprehensibility, and 3D global explanations needed in neuroimaging and beyond. To address this gap, we developed an explainable artificial intelligence (XAI) 3D-Framework capable of providing accurate, low-complexity global explanations. We evaluated the framework using various 3D deep learning models trained on a well-annotated cohort of 596 structural MRIs. The binary classification task focused on detecting the presence or absence of the paracingulate sulcus, a highly variable brain structure associated with psychosis. Our framework integrates statistical features (Shape) and XAI methods (GradCam and SHAP) with dimensionality reduction, ensuring that explanations reflect both model learning and cohort-specific variability. By combining Shape, GradCam, and SHAP, our framework reduces inter-method variability, enhancing the faithfulness and reliability of global explanations. These robust explanations facilitated the identification of critical sub-regions, including the posterior temporal and internal parietal regions, as well as the cingulate region and thalamus, suggesting potential genetic or developmental influences. Our XAI 3D-Framework leverages global explanations to uncover the broader developmental context of specific cortical features. This approach advances the fields of deep learning and neuroscience by offering insights into normative brain development and atypical trajectories linked to mental illness, paving the way for more reliable and interpretable AI applications in neuroimaging.

arXiv:2309.01532공식 코드 · Papers with Code

Are We Using Autoencoders in a Wrong Way?

Autoencoders are certainly among the most studied and used Deep Learning models: the idea behind them is to train a model in order to reconstruct the same input data. The peculiarity of these models is to compress the information through a bottleneck, creating what is called Latent Space. Autoencoders are generally used for dimensionality reduction, anomaly detection and feature extraction. These models have been extensively studied and updated, given their high simplicity and power. Examples are (i) the Denoising Autoencoder, where the model is trained to reconstruct an image from a noisy one; (ii) Sparse Autoencoder, where the bottleneck is created by a regularization term in the loss function; (iii) Variational Autoencoder, where the latent space is used to generate new consistent data. In this article, we revisited the standard training for the undercomplete Autoencoder modifying the shape of the latent space without using any explicit regularization term in the loss function. We forced the model to reconstruct not the same observation in input, but another one sampled from the same class distribution. We also explored the behaviour of the latent space in the case of reconstruction of a random sample from the whole dataset.