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.

169,341 papers · 148 categories

Trend · papers per month

4079119158 · Jun 202019922001200920182026
48 results for Layer-wise relevance propagation

The paper explains deep learning models for recommendations using layer-wise relevance propagation.

problem Explainable recommendations in deep learning models.
method Layer-wise relevance propagation applied to a Deep Convolutional Neural Network.
result Demonstrates the effectiveness of the method on an Amazon products dataset.

We improve neural network explainability by bypassing batch normalization.

problem Lack of transparency in neural networks.
method Layer-wise Relevance Propagation with a method to include normalization layers.
result Heatmaps are more accurate for convolutional layers with our method.

Improved sentiment analysis explanations using LRP for RNNs.

problem Creating understandable explanations for recurrent neural network predictions.
method Extending Layer-wise Relevance Propagation (LRP) to recurrent neural networks (RNNs), specifically to multiplicative connections in LSTMs and GRUs.
result Better explanation quality for sentiment analysis tasks using LRP compared to gradient-based methods.

InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.

problem Modeling noncovalent protein-ligand interactions with graph neural networks.
method InteractionNet uses a GNN architecture with separated covalent and noncovalent convolution layers and layer-wise relevance propagation for explainability.
result InteractionNet successfully predicts noncovalent protein-ligand interactions with chemical relevance.

Researchers use LRP to explain CNN predictions in NLP tasks.

problem Explaining predictions of complex non-linear classifiers in NLP.
method Layer-wise relevance propagation (LRP) applied to a CNN for topic categorization.
result LRP highlights relevant words for CNN predictions, validating its suitability for NLP.

Modified BP attribution methods often ignore later layers' information, leading to misleading explanations.

problem Misleading explanations from modified BP methods ignoring later layers' information.
method Analysis of 9 modified BP methods including Deep Taylor Decomposition, LRP, Excitation BP, PatternAttribution, DeepLIFT, Deconv, RectGrad, Guided BP.
result Only DeepLIFT does not ignore later layers' information, providing a faithful explanation.

Proposes QEP to mitigate quantization error propagation in layer-wise post-training quantization.

problem Growth of quantization errors across layers degrades performance, especially in low-bit regimes.
method Quantization Error Propagation (QEP) framework that explicitly propagates and compensates for quantization errors.
result QEP-enhanced layer-wise PTQ achieves substantially higher accuracy, especially in low-bit regimes.

Pixel-wise relevance method shows how CNNs classify faces, varying across datasets and tasks.

problem Interpreting black-box CNN face recognition models.
method Layer-wise relevance propagation (LRP) applied to VGG-16 models trained for face recognition.
result Relevance maps are generally stable across random initializations and tasks, but less so across pretraining datasets.

Machine learning explains text document categorization decisions.

problem Understanding how text documents are categorized by machine learning models.
method Layer-wise relevance propagation (LRP) to trace predictions back to individual words.
result Word-based ML models can be made more comprehensible through LRP.

New algorithm trains deep neural networks with adaptive learning rates.

problem Inconsistent gradient magnitudes across layers in SGD.
method Back-matching propagation with approximations for layer-wise adaptive learning rates.
result Achieves favorable results over standard SGD in training deep neural networks.

Study reveals XAI methods fail in neuroimaging, suggesting domain-specific adaptation.

problem Systematic failures of XAI methods in neuroimaging applications.
method Systematic comparison of XAI methods on 45,000 structural brain MRIs using a novel validation framework.
result Two widely used XAI methods (GradCAM and Layer-wise Relevance Propagation) fail to accurately explain neuroimaging data.

DNNs with LRP improve EEG classification and reveal single-trial neural patterns.

problem Limited interpretability of DNNs in EEG analysis.
method Application of DNNs with Layer-wise Relevance Propagation (LRP) for EEG data analysis.
result DNN achieves comparable classification accuracy to CSP-LDA and reveals neurophysiologically plausible patterns.

Proposes a new feature-based evaluation method for explaining Deep Learning models in text classification.

problem Lack of consideration for linguistic dependencies in existing attribution-based explanations.
method Investigates perturbations based on embedded features removal from intermediate layers of Convolutional Neural Networks.
result Visualization tool assists analysts in understanding model predictions better.

Proposes a new framework for EEG-based BCIs without adversarial learning.

problem High intra- and inter-subject variabilities in EEG data.
method Mutual information-driven deep learning approach to learn class-relevant and subject-invariant feature representations.
result Effective in learning class-relevant and subject-invariant feature representations without adversarial learning.

Layer-wise training for deep linear networks achieves faster convergence with optimal learning rate.

problem Training deep neural networks is challenging; layer-wise training is proposed as an alternative.
method Layer-wise training using block coordinate gradient descent (BCGD) with orthogonal-like initialization.
result The optimal learning rate guarantees the fastest decrease in loss and is applicable without prior knowledge.

A new framework explains mixed models by propagating Shapley values.

problem Making complex models like neural networks and stacked models explainable for healthcare applications.
method DeepSHAP framework for layer-wise propagation of Shapley values.
result DeepSHAP enables attributions for mixed models and theoretically justifies attributions with respect to a background distribution.

Deep learning explains individual gait patterns in clinical biomechanics.

problem Understanding complex gait patterns from medical data.
method Layer-Wise Relevance Propagation (LRP) technique to attribute relevance of input variables to model predictions.
result Demonstrates which input variables are most relevant for characterizing individual gait patterns.

Interprets how intrinsic motivation shapes behavior in RL agents.

problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.

Gradual pruning reduces inference cost by pruning least important channels during training.

problem Reduction of deep neural network inference cost.
method Gradual channel pruning using feature relevance scores during training.
result Achieved significant model compression with minimal accuracy loss.

Study investigates XAI methods in clinical gait analysis.

problem Limited understanding of machine learning models in healthcare.
method XAI methods, specifically Layer-wise Relevance Propagation (LRP), to explain ML predictions.
result Explanations from LRP show promising statistical and clinical relevance.

Study compares neural networks for age and gender recognition, revealing feature importance and robustness.

problem Understanding which facial features are used and how preprocessing affects deep neural networks for age and gender recognition.
method Compared four neural network architectures, evaluated preprocessing robustness, visualized prediction strategies.
result Suitable parameter initialization improves holistic perception of input, leading to state-of-the-art performance in gender recognition.

GAIT-prop derives a biologically plausible learning rule from backpropagation.

problem Biological implausibility in traditional backpropagation for neural networks.
method GAIT-prop uses a top-down model to convert output error into plausible targets for weight updates.
result GAIT-prop and backpropagation give identical weight updates under certain conditions.

Detects object edges and assigns class labels without pixel-level annotations.

problem Semantic boundary and edge detection with image-level labels.
method Proposes a novel strategy to perform edge detection and class assignment using whole image neural nets and backpropagation.
result High pixel-wise scores indicate semantic boundary locations, suggesting edge labels are not needed during training.

The paper proposes a scalable framework for uncertainty quantification and propagation in surrogate-based Bayesian inference.

problem Uncertainty in surrogate models and its impact on inference and decision-making.
method Bayesian inference methods for surrogate models with measurement data.
result Scalable framework for uncertainty quantification and propagation in surrogate models.

Backpropagation-free RL method trains layers using local signals.

problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.

The multi-layer IB problem optimizes relevance and compression rates.

problem Optimizing relevance and compression rates in multi-layer information propagation.
method Single-letter characterization of the rate-relevance region, conditions for successive refinability, and counterexamples.
result Successive refinability of binary and Gaussian models, counterexample provided.

LNPE enhances local connections in embeddings using extended neighbor propagation.

problem Improving local connections and interactions in nonlinear dimensionality reduction.
method Inspired by GCN, LNPE extends 1-hop neighbors to n-hop neighbors in LLE.
result LNPE produces more faithful and robust embeddings with better topological and geometrical properties.

Paper visualizes and analyzes deep neural networks for CTR prediction.

problem Interpreting deep neural networks for CTR prediction is challenging.
method Visualizing and analyzing deep neural networks at neuron level, measuring layer-wise performance, and calculating saliency scores.
result Insights into the model's performance and mechanism.

We show LLMs can be locally linear, enabling better control of activations.

problem Suboptimal control of LLM activations during generation.
method Model LLM inference as a linear dynamical system, compute feedback controllers using Jacobians, and adapt classical control theory.
result Robust, fine-grained control of LLM activations across models and tasks.

Study on rich regime training in deep learning, finding active parameters in bottom layers.

problem Understanding the practical success of deep learning models.
method Empirical study on rich regime training with benchmark datasets, re-initialization analysis, and probabilistic Layer-Wise Sparse SGD.
result Probabilistic Layer-Wise Sparse SGD matches vanilla SGD's generalization performance with improved efficiency.

Layer-wise preconditioning methods improve neural network optimization and feature learning.

problem Suboptimal feature learning in standard optimization algorithms.
method Layer-wise preconditioning methods that introduce preconditioners per axis of each layer's weight tensors.
result Layer-wise preconditioning is necessary for provable feature learning in linear and single-index models.

The paper introduces metrics to quantify information discarding in DNNs.

problem Understanding how input information is discarded during neural network processing.
method Developed two entropy-based metrics to measure pixel-wise and reconstruction uncertainty.
result The metrics provide new insights into DNN performance and information processing efficiency.