arXiv research

Paper introduces a multi-stage influence function to track model predictions.

New method reveals true causal functions in nonlinear time series, not just scores.

DataInf efficiently approximates data influence in large models, improving transparency and identifying mislabeled data.

There is an especially strong need in modern large-scale data analysis to prioritize samples for manual inspection. For example, the inspection could target important mislabeled samples or key vulnerabilities exploitable by an adversarial attack. In order to solve the "needle in the haystack" problem of which samples t…

This work introduces RISE to explain LLMs more reliably by distinguishing essential context.

This paper improves credit scoring models using a novel dataset distillation technique.

Big data from phone calls improves credit scoring models and profits.

INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.

Introduces a new feature importance measure using Gram-Schmidt decorrelation.

We present a new machine learning and text information extraction approach to detection of cyber threat events in Twitter that are novel (previously non-extant) and developing (marked by significance with respect to similarity with a previously detected event). While some existing approaches to event detection measure …

Better Hessian approximations improve influence function attributions in deep learning.

The paper addresses bias amplification in prediction and decision-making using causal analysis.

We propose $β$-graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment $β$-score reduces the influence of contamination and robustly measures the difference between the underlying correct expected weights of links and the specified generative m…

Improves understanding of PWS by calculating influence of sources and data.

Data samples collected for training machine learning models are typically assumed to be independent and identically distributed (iid). Recent research has demonstrated that this assumption can be problematic as it simplifies the manifold of structured data. This has motivated different research areas such as data poiso…

In this paper, we consider a statistical problem of learning a linear model from noisy samples. Existing work has focused on approximating the least squares solution by using leverage-based scores as an importance sampling distribution. However, no finite sample statistical guarantees and no computationally efficient o…

ULFS-KDPE estimates parameters efficiently without influence functions.

This paper presents two cases of random banking data generators based on migration matrices and scoring rules. The banking data generator is a new hope in researches of finding the proving method of comparisons of various credit scoring techniques. There is analyzed the influence of one cyclic macro--economic variable …

Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the proba…

This paper addresses the problem of inferring sparse causal networks modeled by multivariate auto-regressive (MAR) processes. Conditions are derived under which the Group Lasso (gLasso) procedure consistently estimates sparse network structure. The key condition involves a "false connection score." In particular, we sh…

MISS identifies influential subsets in ML models.

Two new outlyingness scores improve outlier detection in high-dimensional data.

We present a new approach to understanding credit relationships between commercial banks and quoted firms, and with this approach, examine the temporal change in the structure of the Japanese credit network from 1980 to 2005. At each year, the credit network is regarded as a weighted bipartite graph where edges corresp…

Framework detects and mitigates data-poisoning attacks in causal effect estimation.

This research analyzes and accelerates score-based diffusion models using discretization and Hessian information.

Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting…

Proposes a method to infer the distributional impacts of predictive models on stakeholders.

Unified framework interprets SSL models, revealing biases.

Novel framework for contextual anomaly detection models uncertainty.

Two new methods assess feature importance for fairness in machine learning models.

Active learning aims to obtain a classifier of high accuracy by using fewer label requests in comparison to passive learning by selecting effective queries. Many active learning methods have been developed in the past two decades, which sample queries based on informativeness or representativeness of unlabeled data poi…

Introduces privilege scores to measure and interpret protected attribute-related privilege in machine learning models.

The $\alpha$-Alternator adapts to varying noise levels in sequences, improving robustness and performance.

Conditional forecasts improve performative prediction accuracy.

Data poisoning attacks can manipulate recommender systems to recommend target items.

A new method for graph neural networks speeds up inference and training.

Recently, due to the booming influence of online social networks, detecting fake news is drawing significant attention from both academic communities and general public. In this paper, we consider the existence of confounding variables in the features of fake news and use Propensity Score Matching (PSM) to select gener…

Nonparametric method measures influence of training images on diffusion model outputs.

Study uses Granger causality to show investor sentiment influences stock prices.

A novel diffusion method for Bayesian posterior sampling with theoretical guarantees.

New method improves conditional coverage of conformal prediction.

The health outcomes of high-need patients can be substantially influenced by the degree of patient engagement in their own care. The role of care managers includes that of enrolling patients into care programs and keeping them sufficiently engaged in the program, so that patients can attain various goals. The attainmen…

Predicting properties of nodes in a graph is an important problem with applications in a variety of domains. Graph-based Semi-Supervised Learning (SSL) methods aim to address this problem by labeling a small subset of the nodes as seeds and then utilizing the graph structure to predict label scores for the rest of the …

Bayesian approach scores influential training examples for model predictions.

Prediction-powered causal inference achieves smaller asymptotic variance than traditional methods.

INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.

Semiparametric method removes bias in functional bilevel gradient estimation.

Study uses BNs to predict cryptocurrency prices, improving accuracy with discretisation.