Unified framework for analyzing machine learning model attributions.
problem Lack of a general and theoretical framework for understanding attribution methods.
method Proposes a Taylor attribution framework to unify and analyze seven mainstream attribution methods.
result Established three principles for good attribution and empirically validated the Taylor reformulations.
Improved deep learning models using new attribution priors and expected gradients.
problem Improving interpretability and performance of deep learning models.
method Introducing new attribution priors and expected gradients method that satisfies interpretability axioms.
result Improves model performance across various real-world tasks.
Paper tackles embedding attributed sequences in unsupervised learning.
problem Mining tasks over attributed sequences with dependencies between sequences and attributes.
method Proposes a deep multimodal learning framework, NAS, for unsupervised learning of attributed sequences.
result NAS produces task-independent embeddings for various mining tasks on real-world datasets.
VarNet learns and manipulates high-level attributes from inputs.
problem Manipulating high-level attributes of inputs.
method Generative model that learns attributes from data and can handle predefined attributes.
result VarNet can learn and manipulate relevant attributes from datasets.
Paper tackles attribute pattern learning in high-dimensional SLAMs.
problem Learning significant attribute patterns from high-dimensional SLAMs.
method Proposes a penalized likelihood method for selecting attribute patterns.
result Establishes selection consistency in overfitted SLAMs.
Proposes VCLANC for attributed network clustering using node and attribute embeddings.
problem Lack of mutual affinity exploitation between nodes and attributes in graph convolution.
method Dual variational auto-encoders for node and attribute embeddings, Gaussian mixture model priors, mutual distance and clustering assignment hardening losses.
result Demonstrates effectiveness on real-world attributed network datasets.
Generates missing node attributes for better graph-based tasks.
problem Missing or incomplete node attributes degrade graph-based algorithms' performance.
method Deep adversarial learning-based method (NANG) to generate node attributes.
result Generated node attributes improve node classification and link prediction.
Secure methods learn fair models without revealing sensitive attributes.
problem Training fair machine learning models without exposing sensitive data.
method Secure multi-party computation to encrypt sensitive attributes.
result Outcome-based fair models can be learned, checked, or verified without revealing sensitive attributes.
AttGAN edits facial attributes by changing only what you want, preserving details.
problem Facial attribute editing with preservation of details.
method Encoder-decoder architecture with attribute classification and reconstruction learning.
result Outperforms state-of-the-arts on realistic attribute editing with preserved details.
AVA combines feature attribution methods for better model explanations.
problem Improving feature attribution methods for machine learning models.
method AVA: Aggregate Valuation of Antecedents, fusing antecedent event influence and value attribution.
result AVA provides better local and global model explanations.
AnomalyDAE detects anomalies in networks by learning cross-modality interactions.
problem Detecting anomalies in attributed networks where structure and attributes interact.
method Dual autoencoder framework with attention mechanism for joint learning of structure and attribute embeddings.
result AnomalyDAE effectively detects anomalies by reconstructing node attributes and structures.
Paper presents a code authorship attribution attack using adversarial learning.
problem Misleading attribution of source code using machine learning methods.
method Exploits adversarial examples and semantics-preserving code transformations guided by Monte-Carlo tree search.
result Demonstrates substantial effect on attribution methods, reducing accuracy from over 88% to 1%.
New method separates graph structure from node attributes to recover lost signal.
problem Standard representation learning on attributed graphs merges incompatible metric spaces, leading to geometrically flawed alignment.
method Custom variational autoencoder that separates manifold learning from structural alignment.
result Transforms geometric conflict into interpretable structural descriptor, uncovering connectivity patterns and anomalies.
A new method improves semi-supervised learning by handling tasks with different attribute spaces.
problem Existing methods assume tasks share the same attribute space, limiting their applicability.
method Meta-learning approach that embeds labeled and unlabeled data in task-specific spaces using neural networks.
result Improves test performance on tasks with small labeled data using unlabeled and various task data.
New method clusters graph topology and attributes efficiently.
problem Clustering attributed graphs with complex topology-attribute relationships.
method Symmetric NMF with PU learning for non-linear projection.
result Outperforms existing methods in clustering quality.
Framework learns dynamic graph attributes and links co-evolution.
problem Forecasting change of node attributes and link formation in dynamic graphs.
method CoEvoGNN framework with temporal self-attention and joint optimization.
result Framework outperforms baselines on predicting unseen graph snapshots.
Method generates time-series attribution maps with identifiability guarantees.
problem Lack of identifiability guarantees in gradient-based attribution methods.
method Regularized contrastive learning algorithm trained on time-series data.
result Empirically shows robust approximation of zero vs. non-zero entries in the ground-truth attribution map.
MAIN network learns attributes without unseen class attributes for faster, more adaptable ZSL.
problem Learning unseen categories without known attributes and handling continual learning.
method Meta-learning attribute self-interaction network with inverse regularization.
result Main network outperforms state-of-the-art ZSL methods without unseen class attributes.
Proposes a Taylor framework to unify and analyze attribution methods.
problem Lack of a unified guideline for feature contribution assignment in machine learning models.
method Introduces a Taylor attribution framework to model the attribution problem and reformulates fourteen mainstream methods.
result Empirically validates the Taylor reformulations and reveals a positive correlation between performance and principles followed.
Paper proposes embedding attributes across domains using CNN for better classification.
problem Transfer learning with stable attributes across domains.
method Embed attributes in a common space using CNN, combine domain-independent and domain-specific CNN outputs.
result Effective classification model with minimized errors.
RoSHAP stabilizes feature attribution in machine learning models.
problem Stochastic variation in feature attribution measures.
method Modeling feature attribution score distribution and estimating it through bootstrap resampling and kernel density estimation.
result RoSHAP provides stable feature rankings and improves model performance.
Generative model controls text attributes for realistic sentences.
problem Challenges in generating natural language sentences with desired attributes.
method Combines variational auto-encoders and holistic attribute discriminators for semantic structure imposition.
result Effective generation of realistic sentences with desired attributes.
Proposes a method to predict node attributes using network topology.
problem Predicting node attributes in graphs for various applications.
method Creates a feature map using all attributes of neighbors to predict attributes values for a node.
result Significantly improves prediction accuracy compared to baseline approaches.
System helps scientists visualize deep learning model of x-ray images.
problem Understanding complex x-ray scattering images with multiple attributes.
method Interactive visualization system in feature space and classification output.
result Users can explore and compare images and attributes flexibly.
Unified analysis of removal-based feature attributions robustness.
problem Robustness of removal-based feature attributions is not well understood.
method Theoretical analysis and upper bounds derivation for removal-based feature attributions under input and model perturbations.
result Upper bounds for the difference between intact and perturbed attributions derived under various perturbation settings.
Adapts IG for better feature attributions and robustness.
problem Reliability concerns in feature attributions for deep learning models.
method Adaptation of path-based feature attribution to Riemannian geometry of data manifolds.
result IG along geodesics generates more intuitive and robust explanations.
DRSVM uses deep learning to rank relative attributes between image pairs.
problem Classifying relative attributes between image pairs.
method Deep Siamese network with rank SVM loss function.
result DRSVM outperforms state-of-the-art methods on multiple datasets.
New method learns fair representations by separating out protected attributes.
problem Learning fair representations invariant to protected attributes.
method FD-VAE: disentangles latent space into target, protected, and mutual attributes.
result FD-VAE outperforms previous methods in fairness metrics.
Develops framework to evaluate feature attribution methods.
problem Lack of ground truth for evaluating feature attribution methods.
method Proposes a framework including a dataset and metrics.
result Certain methods produce false positive explanations.
MACQ method explains deep learning models by analyzing feature contributions across prediction levels.
problem Explaining deep learning model predictions.
method Global gradient-based, model-agnostic approach focusing on marginal attribution.
result MACQ separates feature contributions from interaction effects and visualizes 3-way relationships.
Study reduces dataset size by 3 attributes to 73% classification accuracy.
problem Reducing dataset size for gender classification in TSI Life Satisfaction Survey.
method Attribute selection using Chi2 algorithm, followed by classification tests with Naive Bayes and Random Forest.
result Best classification rate achieved with 3 attributes selected by Chi2 algorithm.
SLOGAN improves GANs' conditional generation by balancing latent attribute distributions.
problem Imbalanced latent attribute distributions in GANs.
method Stein latent optimization with a Gaussian mixture prior and contrastive loss.
result SLOGAN achieves state-of-the-art unsupervised conditional generation performance.
Introduces FairCOCCO for fair learning with multitype, multivariate sensitive attributes.
problem Fairness in machine learning with multiple, complex sensitive attributes.
method FairCOCCO measure based on cross-covariance operators, incorporating a regularisation term.
result Consistent improvements in balancing fairness and predictive power on real-world datasets.
Proposes DAPr framework to learn feature importance from prior knowledge.
problem Ensuring meaningful feature attributions in deep models.
method Jointly learns feature importance from prior knowledge and biases models to rely on important features.
result Improves model generalization and provides new interpretation methods.
Study reveals attributes help in few-shot classification generalization.
problem Understanding what makes some novel classes easier to learn.
method Defined attributes to quantify concept relatedness, used supervised and self-supervised learning.
result Combining self-supervised pretraining with supervised finetuning improves generalization.
New G-GNN models learn global graph info for better node learning.
problem Learning distant node info and handling plain graphs.
method Unsupervised pre-training for global features, parallel GNN framework.
result G-GNNs outperform other models on standard graphs.
Greedy PIG adapts integrated gradients for better feature attribution.
problem Interpreting deep learning model predictions.
method Unified discrete optimization framework for feature attribution and selection.
result Greedy PIG improves feature attribution on various tasks.
MDNE embeds network structures and attributes for better analysis.
problem Preserving both structural and attribute features in network embedding.
method Multimodal Deep Network Embedding (MDNE) using deep model with multiple layers of non-linear functions.
result MDNE outperforms baselines on various tasks with real-world datasets.
Automates UI implementation from designer images.
problem Automating UI implementation from designer images.
method Generative model training and imitation learning.
result 92.5% accuracy on Android Button attribute inference.
GGDA simplifies DA for large models, speeding up attribution by up to 50x.
problem Computational intensity of existing DA methods limits their applicability to large-scale models.
method Generalized Group Data Attribution (GGDA) framework attributing to groups of training points.
result GGDA achieves up to 50x speedups over standard DA methods while maintaining effectiveness.
This research compares two encoding methods for categorical attributes in machine learning, affecting model fairness.
problem The impact of encoding protected categorical attributes on fairness in machine learning models.
method Comparison of one-hot encoding and target encoding methods.
result Target encoding can lead to more unfair models compared to one-hot encoding due to induced bias.
This work introduces a fair learning method for diverse sensitive attributes.
problem Fairness in supervised learning with complex sensitive attributes.
method Neural network with a simple random sampler for fairness penalties.
result The method improves fairness and utility on benchmark data.
Detects adversarial examples using attribution methods.
problem Detecting adversarial examples in machine learning models.
method Integrated Gradient method for finding attributions and masking high attribution features to define causal neighborhoods.
result Adversarial inputs are not robust to masking high attribution features, while benign inputs are.
WGNN learns graph representations from incomplete attribute data.
problem Missing node attributes in graphs.
method WGNN learns node representations from decomposed attribute matrices and uses Wasserstein space for message passing.
result WGNN outperforms existing methods in node classification tasks with missing attribute data.
In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing which vertex to query in order to learn as much as possible about the attributes of …
AttriGuard defends against attribute inference attacks via adversarial machine learning.
problem Attribute inference attacks on user data from public data.
method Two phases: finding minimum noise and sampling attribute values.
result AttriGuard outperforms existing methods in protecting user data.
Model manipulates facial expressions without affecting other attributes.
problem Manipulating specific visual attributes in real scenes without altering others.
method Trains model on nonphotorealistic 3D renders to manipulate facial expressions, preserving other attributes.
result Model can manipulate facial expressions without affecting other attributes like head orientation.
A method for trust evaluation of devices in human-device coexistence systems.
problem Efficient trust evaluation of devices in systems with diverse physical and social attributes.
method Canonical correlation analysis-enhanced hypergraph self-supervised learning (HSLCCA).
result The proposed HSLCCA method significantly outperforms baseline algorithms in identifying trusted devices.