Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

2.3%4.7%7.0%9.4% · Jun 202019922001200920172026
48 results for label decoupling

Decoupled GCN is shown to be equivalent to label propagation.

problem Improving semi-supervised node classification in graph learning.
method The paper proves the equivalence of decoupled GCN and label propagation, and proposes a new method named PTA.
result Decoupled GCN is equivalent to two-step label propagation and can automatically assign weights to pseudo-labels.

Unified approach to learning from noisy labels using auxiliary clean labels.

problem Learning from noisy labels in real-world applications.
method Rotational-Decoupling Consistency Regularization (RDCR) framework integrating consistency-based methods and self-supervised rotation task.
result RDCR achieves comparable or superior performance than state-of-the-art methods under small noise, significantly outperforming existing methods under large noise.

Unified approach to non-standard classification tasks.

problem Non-standard classification tasks like semi-supervised, positive-unlabelled, multi-positive-unlabelled and noisy-label learning.
method Probabilistic, unified approach training a classifier to predict label-distributions, then inferring class-distributions.
result Unified model for various non-standard classification tasks.

Decoupled PFNs improve sequential decision-making by separating epistemic and aleatoric uncertainties.

problem Sequential decision-making requires distinguishing between epistemic uncertainty about latent signals and irreducible aleatoric observation noise.
method Developed a decoupled PFN architecture that uses query-level labels to train separate heads for latent signal and aleatoric noise.
result Empirically, decoupled PFNs mitigate the failure mode of total-variance exploration in noisy and heteroscedastic settings.

A new framework decouples instance representation learning from subject-level supervision in EEG-based disease diagnosis.

problem Inherently assigning subject labels to all instances in EEG-based disease diagnosis leads to unreliable representations.
method BridgeMIL, a two-stage framework that pretrains an encoder without inherited instance labels and then applies subject-level supervision.
result BridgeMIL achieves the highest mean accuracy in 14 of 15 dataset-backbone settings, with an overall mean accuracy of 76.57%.

This paper introduces the factorial marked temporal point process model and presents efficient learning methods. In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i.e. a marker. In this paper, we describe the factorial marked point processes w…

2018-01-21abs ↗pdf ↗

Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…

2018-04-22abs ↗pdf ↗

JoCoR improves deep learning with noisy labels by reducing network diversity.

problem Learning with noisy labels in deep learning.
method JoCoR uses two networks to make predictions, calculates a joint loss with Co-Regularization, and updates both networks simultaneously.
result JoCoR outperforms state-of-the-art approaches in learning with noisy labels.

A new framework decouples SSL tasks into VDA and VLC, revealing VDA's importance.

problem Designing effective self-supervised learning tasks without manual annotation.
method Borrowing a multi-view perspective, the paper decouples popular pretext tasks into VDA and VLC, focusing on VDA's role in feature learning.
result VDA tasks dominate SSL performance, and integrating predictions from augmented views improves overall performance.

We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.

problem Achieving decoupled convergence in nonlinear two-time-scale stochastic approximation.
method Nested local linearity assumption, suitable step size selection, convergence analysis of matrix cross term, fourth-order moment convergence rates.
result Finite-time decoupled convergence rates can be achieved in nonlinear two-time-scale stochastic approximation with proper step size selection.

A new neural network layer integrates graph learning into classification tasks.

problem Lack of relational information in standard deep learning architectures for label predictions.
method Derives backpropagation equations for a differentiable graph learning layer.
result Smooth label transitions, improved generalization, and robustness to adversarial attacks.

Spectral decoupling improves neural network generalization in medical imaging.

problem Poor generalization of neural networks trained on medical imaging data.
method Spectral decoupling, a regularization technique that encourages learning more features.
result Spectral decoupling increases network robustness and performance on external datasets.

Unified framework suppresses model bias in semi-supervised learning with decoupled sampling control.

problem Class imbalance in semi-supervised learning, especially with distributional mismatches.
method Unified framework SC-SSL with decoupled sampling control, explicit expansion capability, and adaptive sampling probabilities.
result Consistent and state-of-the-art performance across various benchmark datasets and distribution settings.

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant represent…

2018-05-14abs ↗pdf ↗

Regularization is a big issue for training deep neural networks. In this paper, we propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay. The originality of the approach is to define a prior based on conditional entropy, which explicitly decouples the learning of invariant represent…

2018-04-29abs ↗pdf ↗

The paper addresses bias in fraud detection models by improving label recovery in payment networks.

problem Systematic bias in chargeback labels in payment networks.
method Formalizes the observation pipeline as a sequential missing-data problem with three stages and a corruption layer. Constructs the Sequential Triply Robust (STR) estimator to correct for all four impairments simultaneously.
result Achieves the semiparametric efficiency bound and provably dominates naive chargeback-based training in mean squared error.

The paper proposes a decoupled approach to efficiently estimate CoVaR, a measure of systemic financial risk.

problem Estimating CoVaR, a measure of systemic financial risk, is challenging due to zero-probability events and portfolio repricing.
method The paper introduces a decoupled approach using smoothing techniques and a functional perspective to model CoVaR.
result The decoupled estimator achieves a rate of convergence of approximately OmP(Γ1/2)O_{ m P}(Γ^{-1/2}).

Proposes a new network for accurate predictions and uncertainty estimation.

problem Uncertainty estimation in regression predictions without sacrificing accuracy.
method Decoupled two-stage training process with custom loss function.
result Reduces prediction error by 23-34% while maintaining 95% PICP.

This paper investigates the effectiveness of decoupled weight decay at the start of training.

problem The traditional approach to weight decay is not effective throughout training.
method The authors investigate decoupled weight decay, applying it only at the start of training.
result Applying weight decay only at the start of training stabilizes network weights and improves performance.

Clarifies method of phase synchronization for decoupling linear differential equations.

problem Velocity-dependent transformations in linear second-order differential equations.
method Linear transformation of coordinates and velocities.
result Velocity-dependent transformations do not preserve second-order character and define their own system.

Paper tackles musical version matching at segment level using contrastive learning from weakly-labeled data.

problem Match musical versions at the segment level, not just tracks, with weak annotations.
method Proposes contrastive learning from weakly-labeled audio segments, using a new loss variant.
result Breakthrough performance in segment-level evaluation, outperforming state-of-the-art.

We establish decoupled functional CLTs for two-time-scale stochastic approximation.

problem Understanding the asymptotic behavior of two-time-scale stochastic approximation.
method Martingale problem approach and auxiliary sequence.
result The limiting dynamics of two-time-scale SA are independent of each other.

Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …

2018-04-27abs ↗pdf ↗

PeL separates sensory interface optimization from decision learning.

problem Optimizing sensory interfaces without task-specific information.
method Formal separation of perception and decision learning, using metrics for stability, informativeness, and geometry.
result Updates preserving invariants are orthogonal to decision gradients.

Improves model fairness under changing bias between labels and sensitive groups.

problem Fairness of models deteriorates when bias between labels and sensitive groups changes.
method Introduces correlation shifts to explicitly capture bias changes and proposes a pre-processing step to adjust data ratios.
result Our approach effectively improves model accuracy and fairness, both synthetic and real datasets.

Decouples data privatization from user preferences for privacy-preserving data.

problem Privacy-preserving data with user-specific private information.
method Decouples data privatization from user preferences using a Variational Autoencoder (VAE) and a generative filter trained by a GAN-type robust optimization.
result Effective privatization of data with minimal disturbance to utility, as shown by experiments on MNIST, UCI-Adult, and CelebA.

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully l…

2018-04-27abs ↗pdf ↗

New equations simplify gauge-theoretic Khovanov homology solutions.

problem Solving the Haydys-Witten equations for Khovanov homology.
method Introduced decoupled version of Haydys-Witten equations; investigated asymptotic behavior.
result Decoupled equations simplify analysis of full equations on manifolds with ends and boundaries.

A new model decouples global and local image representations without supervision.

problem Learning decoupled global and local image representations without supervision.
method Variational auto-encoding framework with invertible generative flow.
result The model effectively learns decoupled representations of images.

Novel Adam-family method with decoupled weight decay for training neural networks.

problem Training nonsmooth neural networks with weight decay.
method Proposes a novel Adam-family method with decoupled weight decay, establishing convergence properties and demonstrating superior performance.
result Asymptotically approximates SGD and enhances generalization performance.

DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.

problem Decoupling prior and likelihood in diffusion-based inverse problems for better performance.
method Introducing DAPS++, which separates diffusion initialization from likelihood refinement.
result DAPS++ achieves high computational efficiency and robust reconstruction performance.

New method uses diffusion models for Bayesian inverse problems.

problem Solving Bayesian inverse problems with linear-Gaussian models.
method Decoupled Diffusion Sequential Monte Carlo (DDSMC) method.
result Asymptotically exact solution demonstrated on various data types.

DAPS++ improves diffusion-based image restoration by decoupling prior and likelihood.

problem Decoupling prior and likelihood in diffusion-based inverse problems.
method Introducing DAPS++, which fully decouples diffusion-based initialization from likelihood-driven refinement.
result Achieves high computational efficiency and robust reconstruction performance.

FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.

problem Decoupled multi-armed bandit problem with observed and unobserved losses.
method Follow-the-Perturbed-Leader (FTPL) policy that avoids convex optimization and resampling.
result Achieves constant regret in stochastic regime and optimal O(KT)O(\sqrt{KT}) regret in adversarial regime.

Extends capacity analysis to neural networks, showing how capacity is distributed across layers.

problem How capacity is distributed in neural networks with non-linear layers.
method Introduces layer decoupling to quantify non-linear activation's impact, and uses a markovian rule for capacity propagation in deep networks.
result Shows that under certain conditions, capacity allocation in neural networks is equivalent to linear capacity allocation in an extended input space.