PyTorchKR Papers

최신 논문

총 848편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2001.09746

SensAI+Expanse Emotional Valence Prediction Studies with Cognition and Memory Integration

The humans are affective and cognitive beings relying on memories for their individual and social identities. Also, human dyadic bonds require some common beliefs such as empathetic behaviour for better interaction. In this sense, research studies involving human-agent interaction should resource on affect, cognition, and memory integration. The developed artificial agent system (SensAI+Expanse) includes machine learning algorithms, heuristics, and memory as cognition aids towards emotional valence prediction on the interacting human. Further, an adaptive empathy score is always present in order to engage the human in a recognisable interaction outcome. [...] The agent is resilient on collecting data, adapts its cognitive processes to each human individual in a learning best effort for proper contextualised prediction. The current study make use of an achieved adaptive process. Also, the use of individual prediction models with specific options of the learning algorithm and evaluation metric from a previous research study. The accomplished solution includes a highly performant prediction ability, an efficient energy use, and feature importance explanation for predicted probabilities. Results of the present study show evidence of significant emotional valence behaviour differences between some age ranges and gender combinations. Therefore, this work contributes with an artificial intelligent agent able to assist on cognitive science studies. This ability is about affective disturbances by means of predicting human emotional valence contextualised in space and time. Moreover, contributes with learning processes and heuristics fit to the task including economy of cognition and memory to cope with the environment. Finally, these contributions include an achieved age and gender neutrality on predicting emotional valence states in context and with very good performance for each individual.

arXiv:2001.09696

$¶$ILCRO: Making Importance Landscapes Flat Again

Convolutional neural networks have had a great success in numerous tasks, including image classification, object detection, sequence modelling, and many more. It is generally assumed that such neural networks are translation invariant, meaning that they can detect a given feature independent of its location in the input image. While this is true for simple cases, where networks are composed of a restricted number of layer classes and where images are fairly simple, complex images with common state-of-the-art networks do not usually enjoy this property as one might hope. This paper shows that most of the existing convolutional architectures define, at initialisation, a specific feature importance landscape that conditions their capacity to attend to different locations of the images later during training or even at test time. We demonstrate how this phenomenon occurs under specific conditions and how it can be adjusted under some assumptions. We derive the P-objective, or PILCRO for Pixel-wise Importance Landscape Curvature Regularised Objective, a simple regularisation technique that favours weight configurations that produce smooth, low-curvature importance landscapes that are conditioned on the data and not on the chosen architecture. Through extensive experiments, we further show that P-regularised versions of popular computer vision networks have a flat importance landscape, train faster, result in a better accuracy and are more robust to noise at test time, when compared to their original counterparts in common computer-vision classification settings.

arXiv:2001.09055

Forecasting Corn Yield with Machine Learning Ensembles

The emerge of new technologies to synthesize and analyze big data with high-performance computing, has increased our capacity to more accurately predict crop yields. Recent research has shown that Machine learning (ML) can provide reasonable predictions, faster, and with higher flexibility compared to simulation crop modeling. The earlier the prediction during the growing season the better, but this has not been thoroughly investigated as previous studies considered all data available to predict yields. This paper provides a machine learning based framework to forecast corn yields in three US Corn Belt states (Illinois, Indiana, and Iowa) considering complete and partial in-season weather knowledge. Several ensemble models are designed using blocked sequential procedure to generate out-of-bag predictions. The forecasts are made in county-level scale and aggregated for agricultural district, and state level scales. Results show that ensemble models based on weighted average of the base learners outperform individual models. Specifically, the proposed ensemble model could achieve best prediction accuracy (RRMSE of 7.8%) and least mean bias error (-6.06 bu/acre) compared to other developed models. Comparing our proposed model forecasts with the literature demonstrates the superiority of forecasts made by our proposed ensemble model. Results from the scenario of having partial in-season weather knowledge reveal that decent yield forecasts can be made as early as June 1st. To find the marginal effect of each input feature on the forecasts made by the proposed ensemble model, a methodology is suggested that is the basis for finding feature importance for the ensemble model. The findings suggest that weather features corresponding to weather in weeks 18-24 (May 1st to June 1st) are the most important input features.

arXiv:2001.07417

Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach

We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system's data inputs that causally drives the decision (i.e., changing the inputs in the set changes the decision) and is irreducible (i.e., changing any subset of the inputs does not change the decision). We (1) demonstrate how this framework may be used to provide explanations for decisions made by general, data-driven AI systems that may incorporate features with arbitrary data types and multiple predictive models, and (2) propose a heuristic procedure to find the most useful explanations depending on the context. We then contrast counterfactual explanations with methods that explain model predictions by weighting features according to their importance (e.g., SHAP, LIME) and present two fundamental reasons why we should carefully consider whether importance-weight explanations are well-suited to explain system decisions. Specifically, we show that (i) features that have a large importance weight for a model prediction may not affect the corresponding decision, and (ii) importance weights are insufficient to communicate whether and how features influence decisions. We demonstrate this with several concise examples and three detailed case studies that compare the counterfactual approach with SHAP to illustrate various conditions under which counterfactual explanations explain data-driven decisions better than importance weights.

arXiv:2001.06988

Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified

Differentiating the intrinsic subtypes of breast cancer is crucial for deciding the best treatment strategy. Deep learning can predict the subtypes from genetic information more accurately than conventional statistical methods, but to date, deep learning has not been directly utilized to examine which genes are associated with which subtypes. To clarify the mechanisms embedded in the intrinsic subtypes, we developed an explainable deep learning model called a point-wise linear (PWL) model that generates a custom-made logistic regression for each patient. Logistic regression, which is familiar to both physicians and medical informatics researchers, allows us to analyze the importance of the feature variables, and the PWL model harnesses these practical abilities of logistic regression. In this study, we show that analyzing breast cancer subtypes is clinically beneficial for patients and one of the best ways to validate the capability of the PWL model. First, we trained the PWL model with RNA-seq data to predict PAM50 intrinsic subtypes and applied it to the 41/50 genes of PAM50 through the subtype prediction task. Second, we developed a deep enrichment analysis method to reveal the relationships between the PAM50 subtypes and the copy numbers of breast cancer. Our findings showed that the PWL model utilized genes relevant to the cell cycle-related pathways. These preliminary successes in breast cancer subtype analysis demonstrate the potential of our analysis strategy to clarify the mechanisms underlying breast cancer and improve overall clinical outcomes.

arXiv:2001.05972

Topological Descriptors Help Predict Guest Adsorption in Nanoporous Materials

Machine learning has emerged as an attractive alternative to experiments and simulations for predicting material properties. Usually, such an approach relies on specific domain knowledge for feature design: each learning target requires careful selection of features that an expert recognizes as important for the specific task. The major drawback of this approach is that computation of only a few structural features has been implemented so far, and it is difficult to tell a priori which features are important for a particular application. The latter problem has been empirically observed for predictors of guest uptake in nanoporous materials: local and global porosity features become dominant descriptors at low and high pressures, respectively. We investigate a feature representation of materials using tools from topological data analysis. Specifically, we use persistent homology to describe the geometry of nanoporous materials at various scales. We combine our topological descriptor with traditional structural features and investigate the relative importance of each to the prediction tasks. We demonstrate an application of this feature representation by predicting methane adsorption in zeolites, for pressures in the range of 1-200 bar. Our results not only show a considerable improvement compared to the baseline, but they also highlight that topological features capture information complementary to the structural features: this is especially important for the adsorption at low pressure, a task particularly difficult for the traditional features. Furthermore, by investigation of the importance of individual topological features in the adsorption model, we are able to pinpoint the location of the pores that correlate best to adsorption at different pressure, contributing to our atom-level understanding of structure-property relationships.

arXiv:2001.01765

An Automatic Relevance Determination Prior Bayesian Neural Network for Controlled Variable Selection

We present an Automatic Relevance Determination prior Bayesian Neural Network(BNN-ARD) weight l2-norm measure as a feature importance statistic for the model-x knockoff filter. We show on both simulated data and the Norwegian wind farm dataset that the proposed feature importance statistic yields statistically significant improvements relative to similar feature importance measures in both variable selection power and predictive performance on a real world dataset.

arXiv:1912.11755

Feature-Attention Graph Convolutional Networks for Noise Resilient Learning

Noise and inconsistency commonly exist in real-world information networks, due to inherent error-prone nature of human or user privacy concerns. To date, tremendous efforts have been made to advance feature learning from networks, including the most recent Graph Convolutional Networks (GCN) or attention GCN, by integrating node content and topology structures. However, all existing methods consider networks as error-free sources and treat feature content in each node as independent and equally important to model node relations. The erroneous node content, combined with sparse features, provide essential challenges for existing methods to be used on real-world noisy networks. In this paper, we propose FA-GCN, a feature-attention graph convolution learning framework, to handle networks with noisy and sparse node content. To tackle noise and sparse content in each node, FA-GCN first employs a long short-term memory (LSTM) network to learn dense representation for each feature. To model interactions between neighboring nodes, a feature-attention mechanism is introduced to allow neighboring nodes learn and vary feature importance, with respect to their connections. By using spectral-based graph convolution aggregation process, each node is allowed to concentrate more on the most determining neighborhood features aligned with the corresponding learning task. Experiments and validations, w.r.t. different noise levels, demonstrate that FA-GCN achieves better performance than state-of-the-art methods on both noise-free and noisy networks.

arXiv:1912.10084

SensAI+Expanse Adaptation on Human Behaviour Towards Emotional Valence Prediction

An agent, artificial or human, must be continuously adjusting its behaviour in order to thrive in a more or less demanding environment. An artificial agent with the ability to predict human emotional valence in a geospatial and temporal context requires proper adaptation to its mobile device environment with resource consumption strict restrictions (e.g., power from battery). The developed distributed system includes a mobile device embodied agent (SensAI) plus Cloud-expanded (Expanse) cognition and memory resources. The system is designed with several adaptive mechanisms in a best effort for the agent to cope with its interacting humans and to be resilient on collecting data for machine learning towards prediction. These mechanisms encompass homeostatic-like adjustments such as auto recovering from an unexpected failure in the mobile device, forgetting repeated data to save local memory, adjusting actions to a proper moment (e.g., notify only when human is interacting), and the Expanse complementary learning algorithms' parameters with auto adjustments. Regarding emotional valence prediction performance, results from a comparison study between state-of-the-art algorithms revealed Extreme Gradient Boosting on average the best model for prediction with efficient energy use, and explainable using feature importance inspection. Therefore, this work contributes with a smartphone sensing-based system, distributed in the Cloud, robust to unexpected behaviours from humans and the environment, able to predict emotional valence states with very good performance.

arXiv:1912.10065

Learning Deep Attribution Priors Based On Prior Knowledge

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring that models produce meaningful explanations, rather than ones that rely on noise, is not straightforward. Exacerbating this problem is the fact that attribution methods do not provide insight as to why features are assigned their attribution values, leading to explanations that are difficult to interpret. In real-world problems we often have sets of additional information for each feature that are predictive of that feature's importance to the task at hand. Here, we propose the deep attribution prior (DAPr) framework to exploit such information to overcome the limitations of attribution methods. Our framework jointly learns a relationship between prior information and feature importance, as well as biases models to have explanations that rely on features predicted to be important. We find that our framework both results in networks that generalize better to out of sample data and admits new methods for interpreting model behavior.

arXiv:1912.09855공식 코드 · Papers with Code

Explainability and Adversarial Robustness for RNNs

Recurrent Neural Networks (RNNs) yield attractive properties for constructing Intrusion Detection Systems (IDSs) for network data. With the rise of ubiquitous Machine Learning (ML) systems, malicious actors have been catching up quickly to find new ways to exploit ML vulnerabilities for profit. Recently developed adversarial ML techniques focus on computer vision and their applicability to network traffic is not straightforward: Network packets expose fewer features than an image, are sequential and impose several constraints on their features. We show that despite these completely different characteristics, adversarial samples can be generated reliably for RNNs. To understand a classifier's potential for misclassification, we extend existing explainability techniques and propose new ones, suitable particularly for sequential data. Applying them shows that already the first packets of a communication flow are of crucial importance and are likely to be targeted by attackers. Feature importance methods show that even relatively unimportant features can be effectively abused to generate adversarial samples. Since traditional evaluation metrics such as accuracy are not sufficient for quantifying the adversarial threat, we propose the Adversarial Robustness Score (ARS) for comparing IDSs, capturing a common notion of adversarial robustness, and show that an adversarial training procedure can significantly and successfully reduce the attack surface.

arXiv:1912.08937공식 코드 · Papers with Code

Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis

Cancer diagnosis, prognosis, and therapeutic response predictions are based on morphological information from histology slides and molecular profiles from genomic data. However, most deep learning-based objective outcome prediction and grading paradigms are based on histology or genomics alone and do not make use of the complementary information in an intuitive manner. In this work, we propose Pathomic Fusion, an interpretable strategy for end-to-end multimodal fusion of histology image and genomic (mutations, CNV, RNA-Seq) features for survival outcome prediction. Our approach models pairwise feature interactions across modalities by taking the Kronecker product of unimodal feature representations and controls the expressiveness of each representation via a gating-based attention mechanism. Following supervised learning, we are able to interpret and saliently localize features across each modality, and understand how feature importance shifts when conditioning on multimodal input. We validate our approach using glioma and clear cell renal cell carcinoma datasets from the Cancer Genome Atlas (TCGA), which contains paired whole-slide image, genotype, and transcriptome data with ground truth survival and histologic grade labels. In a 15-fold cross-validation, our results demonstrate that the proposed multimodal fusion paradigm improves prognostic determinations from ground truth grading and molecular subtyping, as well as unimodal deep networks trained on histology and genomic data alone. The proposed method establishes insight and theory on how to train deep networks on multimodal biomedical data in an intuitive manner, which will be useful for other problems in medicine that seek to combine heterogeneous data streams for understanding diseases and predicting response and resistance to treatment.

arXiv:1911.11901

Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis

Have you ever wondered how your feature space is impacting the prediction of a specific sample in your dataset? In this paper, we introduce Single Sample Feature Importance (SSFI), which is an interpretable feature importance algorithm that allows for the identification of the most important features that contribute to the prediction of a single sample. When a dataset can be learned by a Random Forest classifier or regressor, SSFI shows how the Random Forest's prediction path can be utilized for low-level feature importance calculation. SSFI results in a relative ranking of features, highlighting those with the greatest impact on a data point's prediction. We demonstrate these results both numerically and visually on four different datasets.

arXiv:1911.11024

Architectural configurations, atlas granularity and functional connectivity with diagnostic value in Autism Spectrum Disorder

Currently, the diagnosis of Autism Spectrum Disorder (ASD) is dependent upon a subjective, time-consuming evaluation of behavioral tests by an expert clinician. Non-invasive functional MRI (fMRI) characterizes brain connectivity and may be used to inform diagnoses and democratize medicine. However, successful construction of deep learning models from fMRI requires addressing key choices about the model's architecture, including the number of layers and number of neurons per layer. Meanwhile, deriving functional connectivity (FC) features from fMRI requires choosing an atlas with an appropriate level of granularity. Once a model has been built, it is vital to determine which features are predictive of ASD and if similar features are learned across atlas granularity levels. To identify aptly suited architectural configurations, probability distributions of the configurations of high versus low performing models are compared. To determine the effect of atlas granularity, connectivity features are derived from atlases with 3 levels of granularity and important features are ranked with permutation feature importance. Results show the highest performing models use between 2-4 hidden layers and 16-64 neurons per layer, granularity dependent. Connectivity features identified as important across all 3 atlas granularity levels include FC to the supplementary motor gyrus and language association cortex, regions associated with deficits in social and sensory processing in ASD. Importantly, the cerebellum, often not included in functional analyses, is also identified as a region whose abnormal connectivity is highly predictive of ASD. Results of this study identify important regions to include in future studies of ASD, help assist in the selection of network architectures, and help identify appropriate levels of granularity to facilitate the development of accurate diagnostic models of ASD.

arXiv:1911.00483공식 코드 · Papers with Code

Explanation by Progressive Exaggeration

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance (e.g. saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually changes the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input.

arXiv:1910.14212공식 코드 · Papers with Code

Sobolev Independence Criterion

We propose the Sobolev Independence Criterion (SIC), an interpretable dependency measure between a high dimensional random variable X and a response variable Y . SIC decomposes to the sum of feature importance scores and hence can be used for nonlinear feature selection. SIC can be seen as a gradient regularized Integral Probability Metric (IPM) between the joint distribution of the two random variables and the product of their marginals. We use sparsity inducing gradient penalties to promote input sparsity of the critic of the IPM. In the kernel version we show that SIC can be cast as a convex optimization problem by introducing auxiliary variables that play an important role in feature selection as they are normalized feature importance scores. We then present a neural version of SIC where the critic is parameterized as a homogeneous neural network, improving its representation power as well as its interpretability. We conduct experiments validating SIC for feature selection in synthetic and real-world experiments. We show that SIC enables reliable and interpretable discoveries, when used in conjunction with the holdout randomization test and knockoffs to control the False Discovery Rate. Code is available at http://github.com/ibm/sic.

arXiv:1910.12389공식 코드 · Papers with Code

Variable Selection with Copula Entropy

Variable selection is of significant importance for classification and regression tasks in machine learning and statistical applications where both predictability and explainability are needed. In this paper, a Copula Entropy (CE) based method for variable selection which use CE based ranks to select variables is proposed. The method is both model-free and tuning-free. Comparison experiments between the proposed method and traditional variable selection methods, such as Distance Correlation, Hilbert-Schmidt Independence Criterion, Stepwise Selection, regularized generalized linear models and Adaptive LASSO, were conducted on the UCI heart disease data. Experimental results show that CE based method can select the `right' variables out more effectively and derive better interpretable results than traditional methods do without sacrificing accuracy performance. It is believed that CE based variable selection can help to build more explainable models.

arXiv:1910.12336공식 코드 · Papers with Code

CXPlain: Causal Explanations for Model Interpretation under Uncertainty

Feature importance estimates that inform users about the degree to which given inputs influence the output of a predictive model are crucial for understanding, validating, and interpreting machine-learning models. However, providing fast and accurate estimates of feature importance for high-dimensional data, and quantifying the uncertainty of such estimates remain open challenges. Here, we frame the task of providing explanations for the decisions of machine-learning models as a causal learning task, and train causal explanation (CXPlain) models that learn to estimate to what degree certain inputs cause outputs in another machine-learning model. CXPlain can, once trained, be used to explain the target model in little time, and enables the quantification of the uncertainty associated with its feature importance estimates via bootstrap ensembling. We present experiments that demonstrate that CXPlain is significantly more accurate and faster than existing model-agnostic methods for estimating feature importance. In addition, we confirm that the uncertainty estimates provided by CXPlain ensembles are strongly correlated with their ability to accurately estimate feature importance on held-out data.

arXiv:1910.10536공식 코드 · Papers with Code

Self-attention for raw optical Satellite Time Series Classification

The amount of available Earth observation data has increased dramatically in the recent years. Efficiently making use of the entire body information is a current challenge in remote sensing and demands for light-weight problem-agnostic models that do not require region- or problem-specific expert knowledge. End-to-end trained deep learning models can make use of raw sensory data by learning feature extraction and classification in one step solely from data. Still, many methods proposed in remote sensing research require implicit feature extraction through data preprocessing or explicit design of features. In this work, we compare recent deep learning models on crop type classification on raw and preprocessed Sentinel 2 data. We concentrate on the common neural network architectures for time series, i.e., 1D-convolutions, recurrence, a shallow random forest baseline, and focus on the novel self-attention architecture. Our central findings are that data preprocessing still increased the overall classification performance for all models while the choice of model was less crucial. Self-attention and recurrent neural networks, by their architecture, outperformed convolutional neural networks on raw satellite time series. We explore this by a feature importance analysis based on gradient back-propagation that exploits the differentiable nature of deep learning models. Further, we qualitatively show how self-attention scores focus selectively on few classification-relevant observations.

arXiv:1910.08534공식 코드 · Papers with Code

Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification

Feature importance is commonly used to explain machine predictions. While feature importance can be derived from a machine learning model with a variety of methods, the consistency of feature importance via different methods remains understudied. In this work, we systematically compare feature importance from built-in mechanisms in a model such as attention values and post-hoc methods that approximate model behavior such as LIME. Using text classification as a testbed, we find that 1) no matter which method we use, important features from traditional models such as SVM and XGBoost are more similar with each other, than with deep learning models; 2) post-hoc methods tend to generate more similar important features for two models than built-in methods. We further demonstrate how such similarity varies across instances. Notably, important features do not always resemble each other better when two models agree on the predicted label than when they disagree.