Proposes a method to measure similarity between anomaly scores from different methods.
problem Difficulty in directly comparing anomaly detection methods.
method A measure based on extremal similarity in scoring distributions using a novel upper quadrant modeling approach.
result Demonstrates the ability to detect clusters of anomaly detection algorithms and achieve an accurate ensemble algorithm.
We introduce a new discrepancy score between two distributions that gives an indication on their similarity. While much research has been done to determine if two samples come from exactly the same distribution, much less research considered the problem of determining if two finite samples come from similar distributio…
Interpretable semantic textual similarity (iSTS) task adds a crucial explanatory layer to pairwise sentence similarity. We address various components of this task: chunk level semantic alignment along with assignment of similarity type and score for aligned chunks with a novel system presented in this paper. We propose…
Proposes Vendi Score for evaluating diversity in ML models.
problem Lack of flexible diversity evaluation metrics in ML.
method Integrates ecological and quantum statistical mechanics concepts to define Vendi Score.
result Vendi Score enables flexible diversity evaluation without requiring a reference dataset.
MAS scores cluster size consistency from points, robust to label changes.
problem Desired uniformity in cluster sizes, stability under label perturbations.
method Mass Agreement Score (MAS) measures point-centric cluster size consistency, robust to label changes.
result MAS yields similar scores for partitions with similar bulk structure, sensitive to genuine redistribution of cluster mass.
Deep learning improves forensic matching of casings.
problem Identifying if two casings came from the same firearm.
method Contrastive neural networks trained on casings dataset.
result Contrastive learning achieved better ROC AUC than CMC.
FUJI scores similarity of ranked lists more robustly.
problem Improving similarity assessment of ranked lists.
method Integrates a membership function into Jaccard index for better rank consideration.
result More stable and accurate similarity estimates.
A new stable similarity measure for time series using persistent homology.
problem Constructing a robust measure of time series similarity.
method Persistent homology for stability, bi-conditional periodicity score for similarity.
result Stability of the bi-conditional periodicity score under perturbations and dimension reduction.
We propose a method to visualize class similarity in large-scale classifiers.
problem Analyzing hierarchical structures and relationships in large-scale classification.
method Compute class similarity based on prediction scores and visualize the class similarity matrix.
result Visualizing class similarity matrices reveals hierarchical structures and relationships.
Turtle Score analyzes developer similarity to match high-performing candidates.
problem Finding suitable candidates for IT companies based on cultural fit.
method Examines employee performance data, applies machine learning for similarity analysis.
result Develops a model for recruiters to identify high-performing candidates.
In correlation clustering, we are given n objects together with a binary similarity score between each pair of them. The goal is to partition the objects into clusters so to minimise the disagreements with the scores. In this work we investigate correlation clustering as an active learning problem: each similarity sc…
A novel outlier score detects new road infrastructure images.
problem Detecting newly observed road infrastructure images.
method Entropy-based outlier score using directed nearest neighbor graphs.
result High potential of the proposed technique in identifying outliers.
Measuring dependence between two random variables is very important, and critical in many applied areas such as variable selection, brain network analysis. However, we do not know what kind of functional relationship is between two covariates, which requires the dependence measure to be equitable. That is, it gives sim…
Some real-world problems revolve to solve the optimization problem \max_{x\in\mathcal{X}}f\left(x\right) where f\left(.\right) is a black-box function and X might be the set of non-vectorial objects (e.g., distributions) where we can only define a symmetric and non-negative similarity score on it. This setting requires…
CLS measures dataset similarity through decision rule performance.
problem Measuring dataset similarity in machine learning, especially for transfer learning and domain adaptation.
method Cross-Learning Score (CLS) measures similarity through bidirectional generalization performance of decision rules, linking to cosine similarity under canonical linear models.
result CLS effectively measures dataset similarity and transferability, validated on synthetic and real-world datasets.
BiLRP explains deep similarity models by decomposing scores into feature contributions.
problem Verifying meaningful patterns in complex similarity models.
method Augmenting similarity scores with feature explanations using LRP.
result BiLRP robustly explains deep neural network features and historical document similarities.
We propose a theoretical framework for thinking about score normalization, which confirms that normalization is not needed under (admittedly fragile) ideal conditions. If, however, these conditions are not met, e.g. under data-set shift between training and runtime, our theory reveals dependencies between scores that c…
Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems. However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm. Hence, policy gradient methods are used since the gradient can be computed without requiri…
We introduce GSimCNN (Graph Similarity Computation via Convolutional Neural Networks) for predicting the similarity score between two graphs. As the core operation of graph similarity search, pairwise graph similarity computation is a challenging problem due to the NP-hard nature of computing many graph distance/simila…
In this paper, we propose a novel approach for measuring the degree of similarity between categories of two pieces of Persian text, which were published as descriptions of two separate advertisements. We built an appropriate dataset for this work using a dataset which consists of advertisements posted on an e-commerce …
The study improves the assessment of fairness in face recognition using ROC curves and statistical guarantees.
problem Improving the assessment of fairness in face recognition systems.
method Proves asymptotic guarantees for empirical ROC curves and fairness metrics, and introduces a recentering technique to avoid bootstrap pitfalls.
result Demonstrates the practical relevance of the methods for assessing fairness in face recognition systems.
TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.
problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a d-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-…
Binary testing for softmax models requires many samples, similar to leverage score models.
problem Binary hypothesis testing for softmax models and leverage score models.
method Analyzing sample complexity and drawing analogies between models.
result Sample complexity is asymptotically \(O(ε^{-2})\), where \(ε\) is the distance between model parameters.
SMT trains generative models by estimating mixture scores, outperforming existing methods.
problem Training one-step generative models efficiently and effectively.
method Score-of-Mixture Training (SMT) estimates the score of mixture distributions between real and fake samples.
result SMT/SMD outperform existing methods on CIFAR-10 and ImageNet 64x64 datasets.
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
The study analyzes neural network predictions of knot invariants and finds that braid representations work best.
problem Understanding and predicting knot invariants using neural networks.
method Investigated different knot representations and invariants, proposed a cosine similarity score.
result Braid representations are best for predicting knot invariants, and some invariants are easier to learn than others.
PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.
problem Efficiently compute graph similarity scores for large graphs.
method Graph partitioning followed by subgraph-level and node-level comparisons using a graph neural network.
result PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks.
New scoring rules for multivariate distributions and level sets.
problem Evaluating forecast accuracy for multivariate distributions and level sets.
method Theoretical framework for scoring rules, decomposition of multivariate scoring functions, numerical algorithm for computation.
result New scoring functions for multivariate distributions and level sets, including density and cumulative distribution level sets.
Pairwise quantile regression tackles similarity scoring in biometric systems.
problem Analyzing errors in similarity scoring for facial recognition.
method Established theoretical guarantees for pairwise quantile regression solutions, leveraging sharp concentration results for U-processes. result Proved generalization bounds and identified conditions for fast learning rates.
CoSimGNN improves graph similarity computation for large graphs.
problem Efficiently computing graph similarity scores for large graphs.
method Embedding-coarsening-matching framework with adaptive pooling and fine-grained interactions.
result CoSimGNN achieves best performance in graph similarity computation.
High-quality image synthesis with diffusion models, achieving state-of-the-art FID score.
problem Generating high-quality images from latent variables.
method Training diffusion probabilistic models with a weighted variational bound, inspired by denoising score matching and Langevin dynamics.
result State-of-the-art FID score of 3.17 on CIFAR10 dataset.
Retrieving the most similar objects in a large-scale database for a given query is a fundamental building block in many application domains, ranging from web searches, visual, cross media, and document retrievals. State-of-the-art approaches have mainly focused on capturing the underlying geometry of the data manifolds…
Study compares different scoring rules for machine-learned weather forecasts, finding scale-awareness improves forecast realism.
problem Improving the accuracy of machine-learned probabilistic weather forecasts.
method Comparison of scoring rules (CRPS, fair global energy score, graph energy score) and analysis of their impact on forecast field spectra.
result Scale-awareness improves forecast realism, particularly in the tropics.
Emergent misalignment is influenced by training dynamics, model priors, and data.
problem Emergent misalignment in models
method Exploring training dynamics, model priors, and data
result Activation deltas before and after narrow fine-tuning correlate with their similarities when measured with the last prompt-token activations.
Music genre classification is an essential tool for music information retrieval systems and it has been finding critical applications in various media platforms. Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarit…
Diffusion models improve creativity by smoothing the score function, leading to interpolated data.
problem Improving creativity in diffusion models.
method Analyzing the effect of score smoothing on diffusion model dynamics.
result Score smoothing causes diffusion models to generate data that interpolate the training set.
We applied machine learning to predict whether a gene is involved in axon regeneration. We extracted 31 features from different databases and trained five machine learning models. Our optimal model, a Random Forest Classifier with 50 submodels, yielded a test score of 85.71%, which is 4.1% higher than the baseline scor…
A network may have weak signals and severe degree heterogeneity, and may be very sparse in one occurrence but very dense in another. SCORE (Jin, 2015) is a recent approach to network community detection. It accommodates severe degree heterogeneity and is adaptive to different levels of sparsity, but its performance for…
Rapid overlay of chemical structures (ROCS) is a standard tool for the calculation of 3D shape and chemical ("color") similarity. ROCS uses unweighted sums to combine many aspects of similarity, yielding parameter-free models for virtual screening. In this report, we decompose the ROCS color force field into "color com…
Extends importance sampling to nonlinear models using adjoint operators.
problem Lack of tools for identifying important data points in nonlinear models.
method Introduces adjoint operator for nonlinear maps, generalizes norm and leverage scores.
result Generalized scores provide approximation guarantees for nonlinear mappings.
We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity betw…
Framework for assessing fairness across similar predictive models.
problem Fairness in predictive models across different groups.
method Develops a framework for characterizing fairness over the set of good models under selective labels.
result Framework can replace or audit models for better fairness properties.
A new algorithm learns MAGs from data more efficiently using entropy.
problem Learning MAGs from data is unstable and computationally expensive.
method Uses entropy estimation and refined Markov property to score MAGs.
result Algorithm is polynomial in number of nodes and outperforms existing methods.
Method predicts ODX scores for breast cancer patients based on clinical data.
problem Predicting ODX scores for breast cancer patients to aid decision-making.
method Distributional random forest approach using 9 clinico-pathological characteristics.
result Correctly predicted 92% of low risk and 40.2% of high risk patients.
Framework scores DeFi users based on liquidity and trading behavior.
problem Distinguishing between liquidity provision and active trading in DeFi.
method Rule-based decomposition, deep residual neural network, pool-level context.
result Deep residual neural network improves user scoring and risk assessment.
RecoBERT uses a language model to recommend items from catalogs.
problem Harnessing language models for text-based item recommendations.
method RecoBERT is a BERT-based approach that learns specialized language models for item recommendations without requiring labeled data.
result RecoBERT outperforms other techniques in inferring item similarities from textual catalogs.
The paper assesses fairness in risk score models, focusing on epistemic value.
problem Fairness of risk score models in communicating uncertainty.
method Identified key fairness desiderata, developed metrics for quantitative assessment, and applied methodology in two case studies.
result Introduced a novel calibration error metric for meaningful comparisons between groups of different sizes.