New measure detects direct causal influences and captures strong dependencies.
problem Shortcomings of existing dependency measures in detecting direct causal influences and group selection.
method Inspired by Dobrushin's coefficients, the measure uses conditional distribution properties.
result Advantages over related measures in detecting dependencies and causal influences.
New framework detects directional influence in multivariate time series.
problem Detecting directional influence in multivariate time series.
method Order-constrained spectral non-invariance.
result Unique diagnostic functional for directional influence.
Develops a method to audit indirect feature influence in complex models.
problem Auditing indirect feature influence in complex, black-box models.
method Disentangled influence audits using disentangled representations.
result Can detect proxy features and show which ones affect model outcomes most.
We introduce kernel nonparametric tests for Lancaster three-variable interaction and for total independence, using embeddings of signed measures into a reproducing kernel Hilbert space. The resulting test statistics are straightforward to compute, and are used in powerful interaction tests, which are consistent against…
Ranking stock indices based on causal influence using directed information graphs.
problem Identifying which countries exert the most economic influence in a subset of the global economy.
method Representing indices as nodes in a directed graph, estimating causal influences using directed information functional, ranking indices based on net-flow.
result Indices representing smaller economies can exert significant influence on larger economies.
New method detects anomalies in systems influenced by their environment.
problem Detecting anomalies in systems under environmental influence.
method Adversarial learning and time series representation learning.
result Successfully addresses label sparsity and subjectivity in anomaly detection.
Dynamic Influence Tracker measures changing sample importance during model training.
problem Static influence measurements during training overlook how sample importance varies over time.
method Dynamic Influence Tracker (DIT) captures time-varying sample influence across arbitrary time windows.
result DIT reveals distinct learning phases with shifting priorities and detects corrupted samples more efficiently.
Identifies influential neurons in deep networks for better explanations.
problem Explaining complex behaviors of deep neural networks.
method Identifies neurons with high influence using an influence measure and provides interpretations.
result Identifies influential concepts that generalize across instances and isolates individual features used by the network.
Framework detects and mitigates data-poisoning attacks in causal effect estimation.
problem Vulnerability to append-only attacks in observational causal analyses.
method Develops a data-poisoning audit for augmented inverse-probability-weighted estimation.
result Proposes a greedy scan to compute exact worst-case movement at every append budget.
CMC method detects causal relationships in time series data.
problem Understanding causal relationships in nonlinear systems.
method Cross-Mapping Coherence method, based on nonlinear state-space reconstruction and coherence metrics.
result CMC accurately identifies causal connections in various systems.
Method detects adversarial samples using influence functions and nearest neighbors.
problem Detecting adversarial attacks on deep neural networks.
method Influence functions and k-NN model on activation layers.
result Successfully distinguishes adversarial examples with state-of-the-art results.
We study the time dependent cross correlations of stock returns, i.e. we measure the correlation as the function of the time shift between pairs of stock return time series using tick-by-tick data. We find a weak but significant effect showing that in many cases the maximum correlation is at nonzero time shift indicati…
Study detects spoofing in high-frequency trading using micro-structural analysis.
problem Challenges in detecting spoofing due to complex electronic platforms and high-frequency trading.
method Micro-structural study in a simplified setting, optimization of spoofing strategy, monitoring with Wasserstein distance.
result Optimal spoofing strategy and its impact on market imbalance quantified.
New method detects key borrowers in financial networks by considering long-range interactions.
problem Identifying systemically important elements in financial networks.
method Analyzes long-range interactions, considering agent attributes and indirect impacts.
result Identifies two types of key borrowers: major players and intermediaries.
Enhances influence functions for deep models without costly Hessian inversion.
problem Challenges in computing Hessian matrix inverse for deep models.
method Substitutes Hessian inverse with identity matrix and extends applications.
result TracIn method performs well in measuring model utility and fairness.
CNMs detect tipping points in complex systems using causal network markers.
problem Identifying tipping points ahead of critical transitions in complex systems.
method Introducing CNMs that incorporate causality indicators to detect tipping points.
result CNMs show higher predictive power and accuracy than traditional DNB indicators.
Unified framework interprets SSL models, revealing biases.
problem Interpreting black-box SSL models for transparency.
method KREPES framework using Representer Landmarks and Nyström approximation.
result Direct audit of SSL latent space without supervision.
Novel framework for contextual anomaly detection models uncertainty.
problem Identifying anomalies in target variables influenced by contextual variables.
method Normalcy score (NS) framework using heteroscedastic Gaussian process regression.
result NS outperforms state-of-the-art methods in detection accuracy and interpretability.
Influence sketching identifies influential samples in large datasets.
problem Finding important samples in large-scale regression models.
method Developed a scalable version of Cook's distance using random projections.
result Deleting high-influence samples reduces predictive accuracy significantly.
Paper tackles hyper-gradient estimation in decentralized FL over time-varying networks.
problem Excessive communication costs and inability to use robust networks.
method Introduces an optimality condition and uses Push-Sum for averaging model parameters and gradients over time-varying directed networks.
result Derives a hyper-gradient estimator that operates over time-varying directed networks and converges to the true hyper-gradient.
Maximizes influence in adversarial networks by choosing optimal seed nodes.
problem Maximizing influence in networks with an adversarial edge specification.
method Formulated as a repeated game between player and adversary, with online node selection.
result Established upper and lower bounds on minimax pseudo-regret.
New method estimates data influence efficiently by leveraging test samples.
problem Efficiently estimating influence of training data on model predictions.
method Mirrored Influence Hypothesis, forward pass for test samples.
result Significant improvement in efficiency over existing methods.
TimeInf estimates data contribution in time series data, improving model performance and anomaly detection.
problem Estimating data contribution in time series datasets with temporal dependencies.
method Model-agnostic data contribution estimation method using influence scores.
result TimeInf effectively detects time series anomalies and outperforms existing methods.
ACI identifies cause-effect relationships and causal influence ranges in dynamical systems.
problem Detecting and quantifying causal influence ranges in complex systems.
method Bayesian data assimilation and assimilative causal inference (ACI) to trace causes back from observed effects.
result Mathematically rigorous formulations of forward and backward causal influence ranges (CIRs) for nonlinear dynamical systems.
New approach detects and ranks novel and developing cyber threats in Twitter.
problem Detecting and ranking novel and developing cyber threats in Twitter streams.
method Unsupervised machine learning approach focusing on novelty and trendiness.
result Ranking of cyber threat events based on importance score using extracted terms.
A new method approximates pNML for faster out-of-distribution detection.
problem Detecting out-of-distribution examples efficiently.
method Influence functions approximation of pNML for neural networks.
result The approximation effectively detects out-of-distribution examples.
The paper improves bounds on influence in network models using nonbacktracking walks.
problem Computing the expected influence in network models.
method Nonbacktracking walks, FKG inequalities, message passing.
result Improved bounds on influence computation in independent cascade models.
There are more than eight hundred interest rates published in China bond market every day. Which are the benchmark interest rates that have broad influences on most interest rates is a major concern for economists. In this paper, multi-variable Granger causality test is developed and applied to construct a directed net…
Improved data attribution for high-dimensional models.
problem Inaccurate influence functions in high-dimensional settings.
method Rescaled influence functions (RIF) for more precise data attribution.
result RIFs offer significantly better predictions in practice.
Personalized Influence Estimation helps understand key factors influencing individual observations.
problem Understanding key factors influencing individual observations in various business problems.
method Joint behavior of feature dimensions and relative feature importance.
result Encouraging results justify key reasons for churn in majority of the sample.
Improves community detection in directed networks with theoretical guarantees.
problem Degree heterogeneity affects community detection in directed networks.
method Introduced D-SCORE algorithm and established theoretical guarantees for Directed-DCBM.
result Established theoretical guarantees and provided improvements for D-SCORE.
Influence functions explain black-box model predictions by tracing back to training data.
problem Explain predictions of black-box models.
method Use influence functions from robust statistics to trace predictions back to training data.
result Influence functions provide valuable insights into model behavior and training data.
One of the goals of probabilistic inference is to decide whether an empirically observed distribution is compatible with a candidate Bayesian network. However, Bayesian networks with hidden variables give rise to highly non-trivial constraints on the observed distribution. Here, we propose an information-theoretic appr…
New method detects latent common causes from observational data.
problem Detecting latent common causes in observational data.
method Modified causal discovery algorithms to detect latent common causes.
result Successfully detects latent common causes in various noise regimes and real data.
We tackle robust influence maximization in social networks with hyperparametric edge probabilities.
problem Maximizing worst-case influence in social networks with hyperparametric edge probabilities.
method Proposed a model with NP-hard proper robust optimization, using sampling and multiplicative weight updates.
result Empirically validated method outperforms state-of-the-art robust influence maximization techniques.
Study identifies influences in VAR models with latent processes.
problem Identify influences among observed and latent processes in VAR models.
method Identify support of transition matrix and lengths of latent paths.
result Support of transition matrix and lengths of latent paths can be identified successfully under certain conditions.
Study reveals strong interdependence between stocks near financial crises.
problem Understanding stock market interdependence during financial crashes.
method Analysis of FTSE 100 companies' daily stock values using information theoretical measures.
result Stocks exhibit strong interdependence for a prolonged period near financial crises.
The paper presents a method for sound event localization and detection using CRNN models.
problem Sound event localization and detection in complex environments.
method Consecutive ensemble of CRNN models for estimating event onset, offset, direction of arrival, and classification.
result The proposed method outperforms other participants in the DCASE2019 task3.
Advances in deep learning for spatio-temporal event modeling.
problem Limitations of traditional parametric models in capturing nonstationary dynamics.
method Integration of deep neural architectures to model conditional intensity function and influence kernels.
result Deep influence kernel approach enhances expressiveness and statistical explainability.
Hölder-Bayes robustly infers model parameters and contamination levels.
problem Robustness to data contamination in Bayesian inference.
method Introduces Hölder-Bayes framework for joint inference of model parameters and contamination proportion using Hölder divergence.
result Hölder-Bayes framework provides robust parameter inference, contamination-level recovery, and uncertainty-aware outlier detection.
A model predicts influential nodes in complex networks by considering indirect interactions.
problem Identifying influential nodes in complex networks using indirect interactions.
method Proposes MOGen, a multi-order generative model that considers all indirect influences up to a maximum distance.
result MOGen consistently outperforms network models and path-based approaches in predicting influential nodes.
In a stock market, the price fluctuations are interactive, that is, one listed company can influence others. In this paper, we seek to study the influence relationships among listed companies by constructing a directed network on the basis of Chinese stock market. This influence network shows distinct topological prope…
We introduce a program aimed to studying problems arising from the theory of complex networks with differential geometric means. We study the propagation of influences on manifolds assuming that at each point only a finite number of propagation velocities are allowed. This leads to the computation of the volume of the …
Paper introduces AIF for anomaly detection with variable feature sensitivity.
problem Lack of variable sensitivity in anomaly detection methods.
method Extended Isolation Forest with feature sensitivities (Anisotropic Isolation Forest).
result AIF enables anomaly detection with controllable sensitivity to different features.
Improved scalability and interpretability in training data attribution.
problem Identifying which training data drives specific behaviors, especially unintended ones.
method Leveraging interpretable structures within the model to attribute model behavior to semantic directions, not individual test examples.
result Simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster.
New method detects when models influence their own drift in real-time data streams.
problem Models can induce concept drift in real-time data streams.
method CheckerBoard Performative Drift Detection (CB-PDD)
result CB-PDD effectively detects performative drift in real-time data streams.
Bi-directional Curriculum Learning improves graph anomaly detection by considering both homogeneity and heterogeneity.
problem Existing graph anomaly detection methods often ignore the different contributions of nodes to training.
method Introduces Bi-directional Curriculum Learning (BCL) to optimize GAD methods by considering both homogeneity and heterogeneity of nodes.
result Extensive experiments show that BCL significantly improves the performance of GAD anomaly detection models.
Proposes a new estimator for causal mediation with continuous treatments.
problem Estimation of direct and indirect effects with continuous treatments.
method Kernel smoothing approach with cross-fitting for non-parametric estimation.
result Multiply robust and asymptotically normal estimator for continuous treatments.