Paper defines and solves a problem in representation learning to ensure fairness with high confidence.
problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.
New method optimizes treatment policies to avoid winner's curse.
problem Winner's curse in treatment policy optimization.
method Inference-aware policy optimization.
result Optimizes for both estimated performance and downstream evaluation.
Decision-alignment evaluates uncertainty quantification for decision-relevant UQ
problem Evaluation of uncertainty quantification metrics
method Introduce decision-alignment
result Proper scoring rules align with decision utility
Geospatial ML models need special evaluation methods due to their unique challenges.
problem Evaluating geospatial machine learning models is challenging due to their specific characteristics.
method Delineated unique challenges and proposed concrete takeaways for improving geospatial model evaluations.
result Concrete takeaways for improving evaluations of geospatial model performance.
HEAR benchmark evaluates audio representations for diverse tasks.
problem Developing a general-purpose audio representation for various tasks.
method Evaluated 29 models across 19 tasks using 16 datasets.
result No single audio representation performs holistically.
This paper evaluates fairness in deep metric learning and proposes a method to reduce subgroup performance gaps.
problem The negative impact of deep metric learning representations on minority subgroup performance in downstream tasks.
method Definition of fairness in DML through inter-class, intra-class, and uniformity properties; finDML benchmark; Partial Attribute De-correlation (PARADE) method.
result Bias in DML representations propagates to downstream tasks, even with balanced training data.
A comprehensive benchmark of 15 scRNA-seq imputation methods across various datasets and analyses.
problem Imputation of single-cell RNA sequencing data to recover latent transcriptional signals.
method Evaluation of 15 imputation methods across 30 datasets and 6 downstream analyses.
result Traditional methods generally outperform DL-based methods in scRNA-seq data analysis.
Study shows scaling up models doesn't always improve downstream tasks.
problem Understanding why scaling up models doesn't always improve downstream performance.
method Systematic study of 4800 experiments on various models, analyzing performance on 20 downstream tasks.
result Performance on downstream tasks saturates as model size increases, revealing a nonlinear relationship.
Optimal Word2Vec hyper-parameters improve NLP tasks.
problem Finding the best Word2Vec hyper-parameters for NLP tasks.
method Empirical evaluation of various hyper-parameter combinations on NLP tasks.
result The best hyper-parameters vary by task, and high analogy scores don't always correlate with performance.
A benchmark evaluates ioUS-to-MR synthesis methods for brain tumor surgery.
problem Difficult interpretation of ioUS images for brain tumor surgery.
method Six generators trained under four inference regimes and two targets on public data.
result SynDiff-2.5D best preserved downstream segmentation (U_Dice=0.55).
Paper establishes a comprehensive benchmark for ECG time-series analysis.
problem Incomplete understanding of ECG signal properties and limitations in evaluation metrics.
method Categorization of downstream applications, identification of limitations, introduction of a novel metric, benchmarking of time-series models.
result Validation of the effectiveness of the proposed metric and model architecture.
Study improves healthcare time series imputation by considering structured missingness.
problem Structured missingness in clinical data impacts time series imputation models.
method Analysis of different masking strategies on imputation methods using PhysioNet Challenge 2012 dataset.
result Masking choices significantly affect imputation accuracy and clinical prediction.
New framework minimizes model complexity for improved few-shot learning.
problem Empirical benefits of pre-training scale with data size but lack theoretical explanation.
method Complexity Minimization framework for meta-representation learning.
result Theoretical analysis shows error rate improves with more meta-training data.
Generative models often fail to preserve joint structure despite matching marginals.
problem Generative models fail to capture complex dependencies beyond univariate marginals.
method Introduced D_Sigma(P,Q) = ||Sigma_P - Sigma_Q||_F to measure covariance-level dependence fidelity.
result Covariance-level divergence can lead to structural instability in downstream inference.
A new metric FRD improves comparing medical images.
problem Comparing medical images for distribution or domain differences.
method Developed a new metric FRD using standardized radiomic features.
result FRD outperforms other metrics in various medical imaging applications.
The paper proposes using density ratio estimation to evaluate synthetic data quality.
problem Improving the quality and utility of synthetic data for analysis.
method Density ratio estimation to measure synthetic data quality.
result Density ratio estimation yields more accurate global utility estimates than existing methods.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
The Neural Testbed evaluates joint predictions of neural agents, revealing their limitations.
problem Evaluating the quality of joint predictions generated by neural agents.
method Developed an open-source benchmark (The Neural Testbed) to assess agents' marginal and joint predictions.
result Popular Bayesian deep learning agents perform poorly on joint predictions, even with accurate marginal predictions.
Large language models correlate in errors, even with different architectures and providers.
problem Lack of empirical evidence on whether different large language models differ meaningfully.
method Empirical evaluation of over 350 large language models using two leaderboards and a resume-screening task.
result Large language models have substantial correlation in errors, even with distinct architectures and providers.
A framework evaluates synthetic tabular data quality objectively.
problem Lack of an objective interpretation of tabular data metrics.
method Proposes a single mathematical objective for synthetic tabular data distribution, structurally decomposes it, and unifies existing metrics.
result Synthesizers that represent tabular structure outperform other methods, especially on smaller datasets.
Study finds significant instability in node embeddings due to randomness.
problem Stability of node embeddings under random variations.
method Evaluated five node embedding algorithms (HOPE, LINE, node2vec, SDNE, GraphSAGE) on synthetic and empirical graphs.
result Significant instability in embedding spaces and downstream task accuracy.
Boxhead dataset tests autoencoder disentanglement in hierarchical data.
problem Evaluate disentanglement in hierarchical data.
method Introduced Boxhead dataset with hierarchically structured factors, evaluated autoencoder models.
result Hierarchical models outperform single-layer VAEs in disentangling factors.
Object-centric learning improves generalization and robustness in multi-object scenes.
problem Improving generalization and robustness in neural networks for scenes with multiple objects.
method Training state-of-the-art unsupervised models on multi-object datasets and evaluating segmentation metrics and downstream tasks.
result Object-centric representations are useful for downstream tasks and generally robust to most distribution shifts affecting objects, but less so for less structured shifts.
New approach to fairness in machine learning models using conformal prediction.
problem Fairness in machine learning models' downstream decision-making.
method Theoretical derivation and empirical evaluation of label-clustered conformal prediction.
result Label-clustered conformal prediction often provides a favorable balance between utility and substantive fairness.
Action-BED: Task-Driven Bayesian Experimental Design
problem Bayesian experimental design with doubly intractable objectives
method Formulating BED in terms of expected future loss (EFL) and optimising it with stochastic gradients
result Simplified and task-driven framework for BED
This work proposes a new pre-processing method for supervised learning to improve fairness without sacrificing utility.
problem Improving fairness in supervised learning without compromising model performance.
method Task-tailored pre-processing approach that balances fairness and utility.
result The proposed method preserves consistent trade-offs among multiple downstream models and improves fairness in computer vision tasks.
Proposes an alternative method for quantifying uncertainty in complex models.
problem Quantifying uncertainty in complex models and evaluations.
method Infinitesimally regularizes the training loss to assess downstream uncertainty.
result Provides reliable quantification of uncertainty and calibrated confidence intervals.
CIT and CIF improve feature selection for downstream prediction.
problem Feature selection bias in machine learning models.
method Conditional inference trees and forests with Bonferroni correction.
result CIF ranks top 3 among 18 regression methods and top 4 among 17 classification methods.
New methods evaluate data representations by complexity of low-loss predictor learning.
problem Evaluating quality of data representations for downstream tasks.
method Surplus Description Length (SDL) and ε Sample Complexity (εSC) methods.
result Methods measure the information needed to approximate optimal predictor up to specified tolerance.
Self-supervised learning improves few-shot classification and segmentation on point clouds.
problem Efficiently learn from limited labeled data in point cloud applications.
method Hierarchical cover-tree partitioning for self-supervised pre-training; restricted to support set for few-shot learning.
result Self-supervised learning significantly improves downstream classification and segmentation accuracy.
Develops a method to ensure accuracy of few-shot transfer learning models.
problem Lack of generalization guarantees for low-data transfer learning.
method Trains a distribution over PEFT parameters using upstream tasks and samples plausible PEFTs for downstream tasks.
result Demonstrates non-vacuous generalization guarantees compared to existing methods in the low-shot regime.
Proposes a new metric to quantify the difference between neural network representations based on downstream task performance.
problem The lack of a consistent metric to measure the difference between neural network representations.
method Introduced the Transferred Discrepancy (TD) metric, which evaluates the difference between representations based on their performance on downstream tasks.
result TD provides fine-grained information for various downstream tasks and can evaluate the effectiveness of different training strategies.
PRAGMA models financial event sequences for various banking tasks.
problem Handling diverse financial data for multiple applications.
method Pre-training a Transformer model on a large banking event corpus with a self-supervised objective.
result PRAGMA achieves superior performance across multiple financial domains from raw event sequences.
PEARL combines multiple representation learning methods to enhance model performance.
problem Different representation learning methods extract distinct data aspects, potentially missing important insights.
method Combines multiple representation learning approaches using surrogate loss functions for efficient weight estimation.
result Asymptotically achieves optimal performance in downstream tasks, assigning nonzero weights to correctly specified models.
New framework for evaluating multiclass classifier calibration.
problem Ensuring classifiers are well-calibrated for trustworthy predictions.
method Utility Calibration framework that measures calibration error relative to a utility function.
result Unified and robust interpretation of existing calibration metrics.
New method evaluates financial graphs for stock trend forecasting.
problem Lack of dynamic stock relationship graphs and evaluation methods.
method SPNews dataset and novel evaluation methods independent of downstream tasks.
result Evaluation methods can differentiate between various financial relationship graphs.
New measure assesses time series pre-training data quality without labels.
problem Challenges in collecting diverse pre-training datasets for time series classification.
method Contrastive-learning-based foundation model and contrastive accuracy measure.
result Contrastive accuracy correlates with model performance on downstream tasks.
In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption, finetuning a large pretrained language model on a downstream task is prone to degen…
A new robust scaling approach improves downstream metabolomics analysis.
problem Challenges in choosing scaling techniques for metabolomics data.
method Introduces a weighted scaling approach robust to outliers.
result The proposed method outperforms traditional scaling techniques in both outlier-free and outlier-present datasets.
Paper introduces a core-periphery model for identifying informative network structures.
problem Noise and bias in non-informative periphery structures obscure the informative core in complex networks.
method Spectral algorithms for core identification as a preprocessing step for network analysis.
result The proposed method outperforms traditional core-periphery methods in various downstream tasks.
New methods reduce bias in synthetic data for machine learning.
problem Statistical bias in synthetic data generated for privacy.
method Re-weighting strategies using privatised likelihood ratios.
result Private importance weighting enhances synthetic data utility.
Robust reinforcement learning agents generalize well to out-of-distribution settings using pretrained representations.
problem Achieving sample-efficient reinforcement learning agents that generalize to real-world settings.
method Trained 240 representations and 10,000 RL policies on a simulated robotic setup, evaluating different pretrained VAE-based representations' effects on OOD generalization.
result Many reinforcement learning agents are surprisingly robust to realistic distribution shifts, including sim-to-real cases.
Improved RL training for DMs reduces mode collapse and preserves diversity.
problem Mode collapse and training instability in RL fine-tuned diffusion models.
method Dynamic hierarchical RL training with sliding-window parameter regularisation.
result Models trained with HRF achieve better preservation of diversity in downstream tasks.
We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method estimates the temporal gap between two short audio segments extracted at random fr…
This paper improves SSL methods using ensemble techniques with data-dependent weighted losses.
problem Improving SSL performance and robustness with large unlabeled data.
method Developed a framework for weighted cross-entropy losses in ensembling SSL methods without altering the backbone.
result Our method outperforms state-of-the-art SSL methods on ImageNet-1K, especially in few-shot learning.
A new method for experimental design focuses on predicting downstream quantities of interest.
problem Designs that maximize parameter learning may not maximize downstream quantity prediction.
method Likelihood-free goal-oriented optimal experimental design (LF-GO-OED) using ABC density ratio estimation.
result LF-GO-OED maximizes the expected information gain for downstream quantities.
Theoretical analysis shows pretext-based self-supervised learning can be boosted by downstream data under certain conditions.
problem Theoretical analysis of pretext-based self-supervised learning and downstream data refinement.
method Theoretical analysis and experiments on synthetic and real-world datasets.
result Theoretical lower bounds and experiments show that downstream data refinement can boost or hurt performance depending on conditions.
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.