PyTorchKR Papers

최신 논문

총 848편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2102.04625

WheaCha: A Method for Explaining the Predictions of Models of Code

Attribution methods have emerged as a popular approach to interpreting model predictions based on the relevance of input features. Although the feature importance ranking can provide insights of how models arrive at a prediction from a raw input, they do not give a clear-cut definition of the key features models use for the prediction. In this paper, we present a new method, called WheaCha, for explaining the predictions of code models. Although WheaCha employs the same mechanism of tracing model predictions back to the input features, it differs from all existing attribution methods in crucial ways. Specifically, WheaCha divides an input program into "wheat" (i.e., the defining features that are the reason for which models predict the label that they predict) and the rest "chaff" for any prediction of a learned code model. We realize WheaCha in a tool, HuoYan, and use it to explain four prominent code models: code2vec, seq-GNN, GGNN, and CodeBERT. Results show (1) HuoYan is efficient - taking on average under twenty seconds to compute the wheat for an input program in an end-to-end fashion (i.e., including model prediction time); (2) the wheat that all models use to predict input programs is made of simple syntactic or even lexical properties (i.e., identifier names); (3) Based on wheat, we present a novel approach to explaining the predictions of code models through the lens of training data.

arXiv:2101.11871

Website fingerprinting on early QUIC traffic

Cryptographic protocols have been widely used to protect the user's privacy and avoid exposing private information. QUIC (Quick UDP Internet Connections), including the version originally designed by Google (GQUIC) and the version standardized by IETF (IQUIC), as alternatives to the traditional HTTP, demonstrate their unique transmission characteristics: based on UDP for encrypted resource transmitting, accelerating web page rendering. However, existing encrypted transmission schemes based on TCP are vulnerable to website fingerprinting (WFP) attacks, allowing adversaries to infer the users' visited websites by eavesdropping on the transmission channel. Whether GQUIC and IQUIC can effectively resist such attacks is worth investigating. In this paper, we study the vulnerabilities of GQUIC, IQUIC, and HTTPS to WFP attacks from the perspective of traffic analysis. Extensive experiments show that, in the early traffic scenario, GQUIC is the most vulnerable to WFP attacks among GQUIC, IQUIC, and HTTPS, while IQUIC is more vulnerable than HTTPS, but the vulnerability of the three protocols is similar in the normal full traffic scenario. Features transferring analysis shows that most features are transferable between protocols when on normal full traffic scenario. However, combining with the qualitative analysis of latent feature representation, we find that the transferring is inefficient when on early traffic, as GQUIC, IQUIC, and HTTPS show the significantly different magnitude of variation in the traffic distribution on early traffic. By upgrading the one-time WFP attacks to multiple WFP Top-a attacks, we find that the attack accuracy on GQUIC and IQUIC reach 95.4% and 95.5%, respectively, with only 40 packets and just using simple features, whereas reach only 60.7% when on HTTPS. We also demonstrate that the vulnerability of IQUIC is only slightly dependent on the network environment.

arXiv:2101.07581

Continual Deterioration Prediction for Hospitalized COVID-19 Patients

Leading up to August 2020, COVID-19 has spread to almost every country in the world, causing millions of infected and hundreds of thousands of deaths. In this paper, we first verify the assumption that clinical variables could have time-varying effects on COVID-19 outcomes. Then, we develop a temporal stratification approach to make daily predictions on patients' outcome at the end of hospital stay. Training data is segmented by the remaining length of stay, which is a proxy for the patient's overall condition. Based on this, a sequence of predictive models are built, one for each time segment. Thanks to the publicly shared data, we were able to build and evaluate prototype models. Preliminary experiments show 0.98 AUROC, 0.91 F1 score and 0.97 AUPR on continuous deterioration prediction, encouraging further development of the model as well as validations on different datasets. We also verify the key assumption which motivates our method. Clinical variables could have time-varying effects on COVID-19 outcomes. That is to say, the feature importance of a variable in the predictive model varies at different disease stages.

arXiv:2101.07312공식 코드 · Papers with Code

Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents

One of the most prominent methods for explaining the behavior of Deep Reinforcement Learning (DRL) agents is the generation of saliency maps that show how much each pixel attributed to the agents' decision. However, there is no work that computationally evaluates and compares the fidelity of different saliency map approaches specifically for DRL agents. It is particularly challenging to computationally evaluate saliency maps for DRL agents since their decisions are part of an overarching policy. For instance, the output neurons of value-based DRL algorithms encode both the value of the current state as well as the value of doing each action in this state. This ambiguity should be considered when evaluating saliency maps for such agents. In this paper, we compare five popular perturbation-based approaches to create saliency maps for DRL agents trained on four different Atari 2600 games. The approaches are compared using two computational metrics: dependence on the learned parameters of the agent (sanity checks) and fidelity to the agent's reasoning (input degradation). During the sanity checks, we encounter issues with one approach and propose a solution to fix these issues. For fidelity, we identify two main factors that influence which saliency approach should be chosen in which situation.

arXiv:2101.05950

Robusta: Robust AutoML for Feature Selection via Reinforcement Learning

Several AutoML approaches have been proposed to automate the machine learning (ML) process, such as searching for the ML model architectures and hyper-parameters. However, these AutoML pipelines only focus on improving the learning accuracy of benign samples while ignoring the ML model robustness under adversarial attacks. As ML systems are increasingly being used in a variety of mission-critical applications, improving the robustness of ML systems has become of utmost importance. In this paper, we propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL)--to perform feature selection, aiming to select features that lead to both accurate and robust ML systems. We show that a variation of the 0-1 robust loss can be directly optimized via an RL-based combinatorial search in the feature selection scenario. In addition, we employ heuristics to accelerate the search procedure based on feature scoring metrics, which are mutual information scores, tree-based classifiers feature importance scores, F scores, and Integrated Gradient (IG) scores, as well as their combinations. We conduct extensive experiments and show that the proposed framework is able to improve the model robustness by up to 22% while maintaining competitive accuracy on benign samples compared with other feature selection methods.

arXiv:2101.05249

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

The availability of accurate day-ahead electricity price forecasts is pivotal for electricity market participants. In the context of trade liberalisation and market harmonisation in the European markets, accurate price forecasting becomes difficult for electricity market participants to obtain because electricity forecasting requires the consideration of features from ever-growing coupling markets. This study provides a method of exploring the influence of market coupling on electricity price prediction. We apply state-of-the-art long short-term memory (LSTM) deep neural networks combined with feature selection algorithms for electricity price prediction under the consideration of market coupling. LSTM models have a good performance in handling nonlinear and complex problems and processing time series data. In our empirical study of the Nordic market, the proposed models obtain considerably accurate results. The results show that feature selection is essential to achieving accurate prediction, and features from integrated markets have an impact on prediction. The feature importance analysis implies that the German market has a salient role in the price generation of Nord Pool.

arXiv:2101.04230

Explaining the Black-box Smoothly- A Counterfactual Approach

We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., saliency maps) that assess feature importance do not explain "how" imaging features in important anatomical regions are relevant to the classification decision. Our framework explains the decision for a target class by gradually "exaggerating" the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation. We used counterfactual explanations from our framework to audit a classifier trained on a chest x-ray dataset with multiple labels. We proposed clinically-relevant quantitative metrics such as cardiothoracic ratio and the score of a healthy costophrenic recess to evaluate our explanations. We conducted a human-grounded experiment with diagnostic radiology residents to compare different styles of explanations (no explanation, saliency map, cycleGAN explanation, and our counterfactual explanation) by evaluating different aspects of explanations: (1) understandability, (2) classifier's decision justification, (3) visual quality, (d) identity preservation, and (5) overall helpfulness of an explanation to the users. Our results show that our counterfactual explanation was the only explanation method that significantly improved the users' understanding of the classifier's decision compared to the no-explanation baseline. Our metrics established a benchmark for evaluating model explanation methods in medical images. Our explanations revealed that the classifier relied on clinically relevant radiographic features for its diagnostic decisions, thus making its decision-making process more transparent to the end-user.

arXiv:2101.03690

Modeling Household Online Shopping Demand in the U.S.: A Machine Learning Approach and Comparative Investigation between 2009 and 2017

Despite the rapid growth of online shopping and research interest in the relationship between online and in-store shopping, national-level modeling and investigation of the demand for online shopping with a prediction focus remain limited in the literature. This paper differs from prior work and leverages two recent releases of the U.S. National Household Travel Survey (NHTS) data for 2009 and 2017 to develop machine learning (ML) models, specifically gradient boosting machine (GBM), for predicting household-level online shopping purchases. The NHTS data allow for not only conducting nationwide investigation but also at the level of households, which is more appropriate than at the individual level given the connected consumption and shopping needs of members in a household. We follow a systematic procedure for model development including employing Recursive Feature Elimination algorithm to select input variables (features) in order to reduce the risk of model overfitting and increase model explainability. Extensive post-modeling investigation is conducted in a comparative manner between 2009 and 2017, including quantifying the importance of each input variable in predicting online shopping demand, and characterizing value-dependent relationships between demand and the input variables. In doing so, two latest advances in machine learning techniques, namely Shapley value-based feature importance and Accumulated Local Effects plots, are adopted to overcome inherent drawbacks of the popular techniques in current ML modeling. The modeling and investigation are performed both at the national level and for three of the largest cities (New York, Los Angeles, and Houston). The models developed and insights gained can be used for online shopping-related freight demand generation and may also be considered for evaluating the potential impact of relevant policies on online shopping demand.

arXiv:2101.03654공식 코드 · Papers with Code

Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction

Click-Through Rate (CTR) prediction, whose aim is to predict the probability of whether a user will click on an item, is an essential task for many online applications. Due to the nature of data sparsity and high dimensionality of CTR prediction, a key to making effective prediction is to model high-order feature interaction. An efficient way to do this is to perform inner product of feature embeddings with self-attentive neural networks. To better model complex feature interaction, in this paper we propose a novel DisentanglEd Self-atTentIve NEtwork (DESTINE) framework for CTR prediction that explicitly decouples the computation of unary feature importance from pairwise interaction. Specifically, the unary term models the general importance of one feature on all other features, whereas the pairwise interaction term contributes to learning the pure impact for each feature pair. We conduct extensive experiments using two real-world benchmark datasets. The results show that DESTINE not only maintains computational efficiency but achieves consistent improvements over state-of-the-art baselines.

arXiv:2101.04013

Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients

Machine Learning (ML) models typically require large-scale, balanced training data to be robust, generalizable, and effective in the context of healthcare. This has been a major issue for developing ML models for the coronavirus-disease 2019 (COVID-19) pandemic where data is highly imbalanced, particularly within electronic health records (EHR) research. Conventional approaches in ML use cross-entropy loss (CEL) that often suffers from poor margin classification. For the first time, we show that contrastive loss (CL) improves the performance of CEL especially for imbalanced EHR data and the related COVID-19 analyses. This study has been approved by the Institutional Review Board at the Icahn School of Medicine at Mount Sinai. We use EHR data from five hospitals within the Mount Sinai Health System (MSHS) to predict mortality, intubation, and intensive care unit (ICU) transfer in hospitalized COVID-19 patients over 24 and 48 hour time windows. We train two sequential architectures (RNN and RETAIN) using two loss functions (CEL and CL). Models are tested on full sample data set which contain all available data and restricted data set to emulate higher class imbalance.CL models consistently outperform CEL models with the restricted data set on these tasks with differences ranging from 0.04 to 0.15 for AUPRC and 0.05 to 0.1 for AUROC. For the restricted sample, only the CL model maintains proper clustering and is able to identify important features, such as pulse oximetry. CL outperforms CEL in instances of severe class imbalance, on three EHR outcomes with respect to three performance metrics: predictive power, clustering, and feature importance. We believe that the developed CL framework can be expanded and used for EHR ML work in general.

arXiv:2012.14982

Elastic Net based Feature Ranking and Selection

Feature selection is important in data representation and intelligent diagnosis. Elastic net is one of the most widely used feature selectors. However, the features selected are dependant on the training data, and their weights dedicated for regularized regression are irrelevant to their importance if used for feature ranking, that degrades the model interpretability and extension. In this study, an intuitive idea is put at the end of multiple times of data splitting and elastic net based feature selection. It concerns the frequency of selected features and uses the frequency as an indicator of feature importance. After features are sorted according to their frequency, linear support vector machine performs the classification in an incremental manner. At last, a compact subset of discriminative features is selected by comparing the prediction performance. Experimental results on breast cancer data sets (BCDR-F03, WDBC, GSE 10810, and GSE 15852) suggest that the proposed framework achieves competitive or superior performance to elastic net and with consistent selection of fewer features. How to further enhance its consistency on high-dimension small-sample-size data sets should be paid more attention in our future work. The proposed framework is accessible online (https://github.com/NicoYuCN/elasticnetFR).

arXiv:2012.11905공식 코드 · Papers with Code

GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art tools to explain such classifiers rely on visual highlighting of important areas of the input data. Contrary, counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image in a way such that the classifier would have made a different prediction. By doing so, the users of counterfactual explanation systems are equipped with a completely different kind of explanatory information. However, methods for generating realistic counterfactual explanations for image classifiers are still rare. Especially in medical contexts, where relevant information often consists of textural and structural information, high-quality counterfactual images have the potential to give meaningful insights into decision processes. In this work, we present GANterfactual, an approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Additionally, we conduct a user study to evaluate our approach in an exemplary medical use case. Our results show that, in the chosen medical use-case, counterfactual explanations lead to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the-art systems that work with saliency maps, namely LIME and LRP.

arXiv:2012.10929공식 코드 · Papers with Code

Automated Clustering of High-dimensional Data with a Feature Weighted Mean Shift Algorithm

Mean shift is a simple interactive procedure that gradually shifts data points towards the mode which denotes the highest density of data points in the region. Mean shift algorithms have been effectively used for data denoising, mode seeking, and finding the number of clusters in a dataset in an automated fashion. However, the merits of mean shift quickly fade away as the data dimensions increase and only a handful of features contain useful information about the cluster structure of the data. We propose a simple yet elegant feature-weighted variant of mean shift to efficiently learn the feature importance and thus, extending the merits of mean shift to high-dimensional data. The resulting algorithm not only outperforms the conventional mean shift clustering procedure but also preserves its computational simplicity. In addition, the proposed method comes with rigorous theoretical convergence guarantees and a convergence rate of at least a cubic order. The efficacy of our proposal is thoroughly assessed through experimental comparison against baseline and state-of-the-art clustering methods on synthetic as well as real-world datasets.

arXiv:2012.08868

Using Spatio-temporal Deep Learning for Forecasting Demand and Supply-demand Gap in Ride-hailing System with Anonymised Spatial Adjacency Information

To reduce passenger waiting time and driver search friction, ride-hailing companies need to accurately forecast spatio-temporal demand and supply-demand gap. However, due to spatio-temporal dependencies pertaining to demand and supply-demand gap in a ride-hailing system, making accurate forecasts for both demand and supply-demand gap is a difficult task. Furthermore, due to confidentiality and privacy issues, ride-hailing data are sometimes released to the researchers by removing spatial adjacency information of the zones, which hinders the detection of spatio-temporal dependencies. To that end, a novel spatio-temporal deep learning architecture is proposed in this paper for forecasting demand and supply-demand gap in a ride-hailing system with anonymized spatial adjacency information, which integrates feature importance layer with a spatio-temporal deep learning architecture containing one-dimensional convolutional neural network (CNN) and zone-distributed independently recurrent neural network (IndRNN). The developed architecture is tested with real-world datasets of Didi Chuxing, which shows that our models based on the proposed architecture can outperform conventional time-series models (e.g., ARIMA) and machine learning models (e.g., gradient boosting machine, distributed random forest, generalized linear model, artificial neural network). Additionally, the feature importance layer provides an interpretation of the model by revealing the contribution of the input features utilized in prediction.

arXiv:2012.07671공식 코드 · Papers with Code

E2E-FS: An End-to-End Feature Selection Method for Neural Networks

Classic embedded feature selection algorithms are often divided in two large groups: tree-based algorithms and lasso variants. Both approaches are focused in different aspects: while the tree-based algorithms provide a clear explanation about which variables are being used to trigger a certain output, lasso-like approaches sacrifice a detailed explanation in favor of increasing its accuracy. In this paper, we present a novel embedded feature selection algorithm, called End-to-End Feature Selection (E2E-FS), that aims to provide both accuracy and explainability in a clever way. Despite having non-convex regularization terms, our algorithm, similar to the lasso approach, is solved with gradient descent techniques, introducing some restrictions that force the model to specifically select a maximum number of features that are going to be used subsequently by the classifier. Although these are hard restrictions, the experimental results obtained show that this algorithm can be used with any learning model that is trained using a gradient descent algorithm.

arXiv:2012.04218공식 코드 · Papers with Code

Evaluating Explainable Methods for Predictive Process Analytics: A Functionally-Grounded Approach

Predictive process analytics focuses on predicting the future states of running instances of a business process. While advanced machine learning techniques have been used to increase accuracy of predictions, the resulting predictive models lack transparency. Current explainable machine learning methods, such as LIME and SHAP, can be used to interpret black box models. However, it is unclear how fit for purpose these methods are in explaining process predictive models. In this paper, we draw on evaluation measures used in the field of explainable AI and propose functionally-grounded evaluation metrics for assessing explainable methods in predictive process analytics. We apply the proposed metrics to evaluate the performance of LIME and SHAP in interpreting process predictive models built on XGBoost, which has been shown to be relatively accurate in process predictions. We conduct the evaluation using three open source, real-world event logs and analyse the evaluation results to derive insights. The research contributes to understanding the trustworthiness of explainable methods for predictive process analytics as a fundamental and key step towards human user-oriented evaluation.

arXiv:2012.03625

Shapley values for cluster importance: How clusters of the training data affect a prediction

This paper proposes a novel approach to explain the predictions made by data-driven methods. Since such predictions rely heavily on the data used for training, explanations that convey information about how the training data affects the predictions are useful. The paper proposes a novel approach to quantify how different data-clusters of the training data affect a prediction. The quantification is based on Shapley values, a concept which originates from coalitional game theory, developed to fairly distribute the payout among a set of cooperating players. A player's Shapley value is a measure of that player's contribution. Shapley values are often used to quantify feature importance, ie. how features affect a prediction. This paper extends this to cluster importance, letting clusters of the training data act as players in a game where the predictions are the payouts. The novel methodology proposed in this paper lets us explore and investigate how different clusters of the training data affect the predictions made by any black-box model, allowing new aspects of the reasoning and inner workings of a prediction model to be conveyed to the users. The methodology is fundamentally different from existing explanation methods, providing insight which would not be available otherwise, and should complement existing explanation methods, including explanations based on feature importance.

arXiv:2012.03491공식 코드 · Papers with Code

AI-enabled Prediction of eSports Player Performance Using the Data from Heterogeneous Sensors

The emerging progress of eSports lacks the tools for ensuring high-quality analytics and training in Pro and amateur eSports teams. We report on an Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors. For this reason, we collected the physiological, environmental, and the game chair data from Pro and amateur players. The player performance is assessed from the game logs in a multiplayer game for each moment of time using a recurrent neural network. We have investigated that attention mechanism improves the generalization of the network and provides the straightforward feature importance as well. The best model achieves ROC AUC score 0.73. The prediction of the performance of particular player is realized although his data are not utilized in the training set. The proposed solution has a number of promising applications for Pro eSports teams and amateur players, such as a learning tool or a performance monitoring system.

arXiv:2012.03188

Representaciones del aprendizaje reutilizando los gradientes de la retropropagacion

This work proposes an algorithm for taking advantage of backpropagation gradients to determine feature importance at different stages of training. Additionally, we propose a way to represent the learning process qualitatively. Experiments were performed over the Wisconsin cancer dataset provided by sklearn, and results showed an interesting convergence of the so called "learning gradients" towards the most important features. --- Este trabajo propone el algoritmo de gradientes de aprendizaje para encontrar significado en las entradas de una red neuronal. Ademas, se propone una manera de evaluarlas por orden de importancia y representar el proceso de aprendizaje a traves de las etapas de entrenamiento. Los resultados obtenidos utilizan como referencia el conjunto de datos acerca de tumores malignos y benignos en Wisconsin. Esta referencia sirvio para detectar un patron en las variables mas importantes del modelo gracias, asi como su evolucion temporal.

arXiv:1910.09404

PV Power Forecasting Using Weighted Features for Enhanced Ensemble Method

Solar power becomes one of the most promising renewable energy resources in recent years. However, the weather is continuously changing, and this causes a discontinuity of energy generation. PV Power forecasting is a suitable solution to handle sudden disjointedness on energy generation by providing fast dispatching to grid electricity. These methods present a key insight into matchmaking grid electricity and photovoltaic plants. Bootstrap aggregation Ensemble method(Bagging) is classified as one of the most useful machine learning models which are applicable to supervised learning regression tasks. Following this regard, this paper proposes a state-of-art method based on bagging and this method works perfectly for PV power forecasting. The latter had powerful capabilities of tracking the behavior of stochastic problems with good accuracy with the aid of feature importance information. This approach comes to optimize bias/variance using feature weighting vector. Thus, this paper is devoted to present various feature importance techniques for Photovoltaic forecasting parameters. This technique consists of improving the aforementioned ensemble model via contributing the knowledge expertise obtained from features analysis to be directly transformed into the Ensemble model. The proposed model is tested on PV power prediction. Therefore, the benchmarked technique shows an improvement in accuracy in terms of RMSE to 5%.