Transfer learning helps predict social roles in unlabelled networks.
problem Recognizing social roles in unlabelled social networks.
method Transfer learning with feature transformations.
result Improved role classification accuracy on real-world datasets.
In this work, we propose a new method to integrate two recent lines of work: unsupervised induction of shallow semantics (e.g., semantic roles) and factorization of relations in text and knowledge bases. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles…
We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexical features; (2) a reconstruction component: a tensor factoriz…
The study examines how hyperparameters affect prediction discrepancies in machine learning models.
problem Prediction inconsistencies across different machine learning models trained on the same dataset.
method Investigation of six models (Elastic Net, Decision Tree, k-NN, SVM, RF, XGBoost) on 21 benchmark datasets, focusing on key hyperparameters.
result Hyperparameter tuning improves model performance but increases prediction discrepancies, especially in Extreme Gradient Boosting.
Persona2vec learns multiple node roles in graphs.
problem Graphs often have nodes with multiple overlapping roles.
method Persona2vec learns multiple node representations based on structural contexts.
result Persona2vec outperforms state-of-the-art models in link prediction.
CopulaGNN integrates graph representational and correlational roles for better node-level predictions.
problem Graphs encode diverse roles in node-level prediction tasks, but GNNs struggle with correlational information.
method Copula theory to describe multivariate dependence, integrating representational and correlational graph information.
result CopulaGNN improves GNN performance on regression tasks by leveraging both types of graph information.
New model quantifies interactions' role in real-world phenomena.
problem Understanding the role of interactions in real-world phenomena.
method Interactive Mixed Membership Stochastic Block Model (IMMSBM).
result Interactions significantly improve model predictive power.
Machine learning aids in neuroscience across various tasks.
problem Understanding complex brain functions through ML.
method ML for engineering, predictive modeling, benchmark setting, and modeling brain function.
result Machine learning is a valuable tool for systems neuroscience.
Nodes in real world networks often have class labels, or underlying attributes, that are related to the way in which they connect to other nodes. Sometimes this relationship is simple, for instance nodes of the same class are may be more likely to be connected. In other cases, however, this is not true, and the way tha…
Intangible investment becomes a strong predictor of stock returns over time.
problem Understanding the role of intangible investment in stock returns over different periods.
method Comparing intangible investment's predictive power over two distinct periods (1963-1992 and 1993-2022) using orthogonal factors.
result Intangible investment's predictive power for stock returns has significantly increased over time, becoming a main predictor for recent periods.
Novel approach for directed graph node embeddings.
problem Lack of effective node representations for directed graphs.
method Alternating random walk strategy for role-specific embeddings.
result Robust, generalizable embeddings outperform baselines.
Proposes a new neural head for asymmetric representation learning.
problem Asymmetric representation learning in directed relations.
method Role-aware neural convex divergence head.
result Role-aware projections improve directional accuracy over plain ICNN-Bregman heads.
Bayesian methods often misinterpret data and asymptotic concepts.
problem Misunderstandings in Bayesian predictive inference.
method Discussion of two specific misunderstandings.
result Consequences of misinterpretations illustrated through examples.
Study shows model uncertainty is crucial for medical predictions, especially for individual patients.
problem Uncertainty in medical predictions, especially for individual patients.
method Used RNN ensembles and various Bayesian RNNs to analyze model uncertainty.
result RNNs with only Bayesian embeddings are more efficient for capturing model uncertainty.
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
New tree splitting criteria improve probabilistic predictions.
problem Improving tree-based nonparametric predictive distributions.
method Using proper scoring rules for tree splitting criteria.
result Trees with new splitting criteria produce better predictive distributions.
Neural networks learn symbolic structure to perform compositional tasks.
problem How neural networks perform well on compositional tasks without explicit representations.
method ROLE analysis to uncover symbolic structure in recurrent neural networks.
result Neural networks converge to solutions that implicitly represent symbolic structure.
The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.
problem The need for accurate joint predictions in decision-making problems.
method The paper analyzes combinatorial decision problems, sequential predictions, and multi-armed bandits, introducing an approximate Thompson sampling algorithm and new regret bounds.
result Accurate joint predictions are essential for good performance in decision-making problems.
Develops a new method for building data-driven portfolios with a target risk-return.
problem Building a portfolio with a specific risk-return level.
method Applies LSTM to select the best predictor for portfolio construction and uses predictive threshold-based portfolios (TBPs) to target specific risk-return levels.
result Thresholds play a dominant role in characterizing risk, return, and prediction accuracy of the subset.
Researchers develop a method to interpret GNNs by identifying unnecessary edges in NLP models.
problem Understanding which parts of graphs contribute to NLP model predictions.
method A post-hoc method using differentiable edge masking to identify and drop unnecessary edges.
result Large proportions of edges can be dropped without affecting model performance, providing insights into model predictions.
DE improves GNNs by distinguishing graph substructures, enhancing accuracy.
problem Limited expressive power of GNNs in representing graph substructures.
method Introduces Distance Encoding (DE) to assist GNNs in distinguishing graph substructures.
result DE distinguishes graph substructures that traditional GNNs cannot, improving accuracy.
New metric reduces arbitrariness in fair binary classification predictions.
problem Variance in predictions leads to arbitrary decisions in fair classification.
method Developed a self-consistency metric and an abstention algorithm.
result Fair binary classification is often close to fair due to variance, not interventions.
Improved stock volume prediction using Kalman Filters with various hidden states.
problem Improving accuracy of intraday trading volume prediction.
method Extended Kalman Filter with various hidden states for different stocks, using cross-validation to determine optimal state number.
result Demonstrated improved accuracy through comparison experiments and numerical analysis.
Paper predicts multiple types of miRNA-disease associations using tensor decomposition.
problem Predicting miRNA-disease associations, especially multi-type ones.
method Represented miRNA-disease-type triplets as a tensor and used Tensor Decomposition methods.
result Tensor Decomposition methods improve a recent baseline by up to 38% in top-1 F1.
Self-calibrating conformal prediction improves interval efficiency and offers a practical alternative.
problem Improving the reliability and uncertainty quantification of machine learning predictions.
method Combines Venn-Abers calibration and conformal prediction for binary and regression problems.
result Improves interval efficiency through model calibration and offers practical alternatives.
In this paper we explore the specific role of randomness in financial markets, inspired by the beneficial role of noise in many physical systems and in previous applications to complex socio- economic systems. After a short introduction, we study the performance of some of the most used trading strategies in predicting…
Improves survival prediction model calibration for better individual decision-making.
problem Survival prediction's marginal and conditional calibration issues.
method Conformal prediction using individual survival probabilities.
result Effective marginal and conditional calibration without compromising discrimination.
The paper predicts brain tumor patient survival using segmentation and features.
problem Predicting overall survival of brain tumor patients.
method Automated brain tumor segmentation and use of age, shape, and volumetric features for prediction.
result Random forest classifier achieves 59% accuracy on test dataset and 67% on gross total resection dataset.
Bayesian models predict antimicrobial and multifunctional peptides with high accuracy.
problem Classifying peptides with antimicrobial and multifunctional properties.
method Bayesian network models to identify amino acid sequence motifs and predict antimicrobial activity.
result Models achieve 94% accuracy in predicting antimicrobial activity, with interpretability of parameters.
SAM optimizer benefits from normalization, stabilizing and guiding optimization.
problem Improving deep neural network performance with SAM optimizer.
method Theoretical and empirical study of normalization in SAM for convex and non-convex functions.
result Normalization helps SAM in stabilizing and guiding optimization along a continuum of minima.
The paper proposes a method for distribution-free prediction sets that adapt to unknown temporal changes.
problem Distribution-free prediction sets require reliable calibration data, which is often unavailable in real-world settings with temporal changes.
method The method selects an adaptive window to construct prediction sets, optimizing a bias-variance tradeoff.
result The method provides sharp coverage guarantees and is shown to be adaptive to temporal drift through numerical experiments.
Algorithm uncovers roles and sub-communities in online forums.
problem Identifying roles and sub-communities in online forums.
method Scalable algorithm based on stochastic variational inference and topic models.
result Model outperforms existing methods in predicting user behavior.
New analysis reveals batch size effects on stochastic conditional gradient methods.
problem Understanding the role of batch size in stochastic conditional gradient methods.
method Deriving a new analysis focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion).
result Increasing batch size initially improves optimization accuracy but can degrade performance beyond a critical threshold.
Improved video tracking accuracy with active learning.
problem Efficiently predicting object matches in videos with active learning.
method Adversarial approach for active learning with structured prediction domains.
result Better accuracy and computational efficiency for object tracking.
Study reduces gender bias in web data used for image recognition.
problem Gender bias in web data amplifies in machine learning models.
method Inject corpus-level constraints for calibrating structured prediction models.
result Bias amplification decreased by 47.5% and 40.5% for multilabel classification and visual semantic role labeling.
Study on how attention in prompt-tuning affects large language models.
problem Limited theoretical understanding of prompt-tuning and attention in LLMs.
method Exploration of prompt-tuning for one-layer attention architectures, contextual mixture-models, and self-contained prompt-attention model.
result Softmax-prompt-attention is more expressive than self-attention and linear-prompt-attention under contextual data model.
Paper proposes LIME for explaining machine learning credit risk predictions.
problem Lack of explainability in machine learning models for credit risk.
method Uses LIME technique to explain machine learning predictions.
result LIME improves explainability of machine learning models in credit risk.
Proposes SSM to improve CTR prediction with deep neural networks.
problem Improving CTR prediction with deep neural networks.
method Designs an orthogonal base convolution and pooling model to learn multi-scale base semantic representation.
result Demonstrates superior performance in CTR prediction.
Machine learning improves RNA secondary structure prediction.
problem Stagnant performance of RNA secondary structure prediction methods.
method Machine learning, especially deep learning, is used to predict RNA secondary structures.
result Machine learning methods have improved the prediction of RNA secondary structures.
French bank uses corporate transaction data to predict credit default risk better than traditional methods.
problem Predicting credit default risk of enterprises using financial ratios and transaction data.
method Advanced machine learning methods applied to transaction data.
result Transaction data outperforms traditional financial ratios in predicting credit default risk.
The paper addresses ill-conditioning in large spatial data, proposing solutions for prediction and likelihood estimation.
problem Ill-conditioning of the kernel matrix in large spatial data sets.
method Introduction of various optimality criteria and solutions for managing large spatial data.
result Solutions for managing large spatial data, addressing ill-conditioning and improving prediction and likelihood estimation.
New framework predicts earnings announcements using press release content, surpassing earnings surprises.
problem Predicting stock returns based on earnings press releases.
method Compared traditional and BERT-based embeddings of press releases, finding content as informative as earnings surprises.
result FinBERT yields highest predictive power for earnings announcement returns.
Paper compares generative and discriminative models in uncertainty quantification.
problem Comparing generative and discriminative approaches in uncertainty quantification.
method Analysis of generative and discriminative models, focusing on posterior predictive distribution and prior distributions.
result Discriminative models struggle with imbalanced datasets, while generative models offer a more flexible prior distribution.
A new LSTM architecture improves time series forecasting efficiency.
problem Efficiency and accuracy in time series forecasting using linear models.
method Attention-free LSTM architecture for time series prediction.
result Improved prediction capacity and efficiency compared to LSTM.
Investor attention predicts global equity market volatility during Ukraine invasion.
problem Predicting global equity market volatility during geopolitical events.
method Event-specific attention indices based on Google Trends, analyzed across 51 global equity markets.
result Investor attention significantly predicts volatility in countries with higher economic openness to Russia and closer to it.
Skew-adaptive method improves prediction intervals for regression.
problem Improving prediction intervals for regression models, especially in cases of skewness and varying scales.
method Develops a skew-adaptive extension of split conformal prediction using an asymmetric interval family and gauge approach.
result Preserves marginal validity and adapts to local scale and skewness, with efficiency gains over existing methods.
New approach predicts commuters' flow with 90.4% accuracy.
problem Limited ability to predict and reconstruct commuters' networks.
method Machine learning and 22 urban indicators.
result Predictions with 90.4% accuracy and 77.6% variance explained.
Gaussian process models improve MJO predictions with better uncertainty quantification.
problem Lack of uncertainty quantification in MJO predictions by machine learning models.
method Developed a nonparametric strategy based on Gaussian process models, calibrating them using empirical correlations and proposing a posteriori covariance correction.
result Gaussian process models provide better prediction skills and extended probabilistic coverage for MJO forecasts.