The paper investigates the limitations of additive explanations for complex models.
problem The trustworthiness of additive explanations for non-additive models.
method Examine and introduce a new method to detect interactions for instance-level explanations.
result Additive explanations can be misleading for non-additive models.
Fraud detection is a difficult problem that can benefit from predictive modeling. However, the verification of a prediction is challenging; for a single insurance policy, the model only provides a prediction score. We present a case study where we reflect on different instance-level model explanation techniques to aid …
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
A fast method finds interpretable counterfactual explanations using class prototypes.
problem Finding understandable counterfactual explanations for classifier predictions.
method Using class prototypes, the method speeds up and improves interpretability of counterfactual instances.
result The method significantly speeds up and improves the interpretability of counterfactual explanations.
Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary cl…
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a …
GLOBE-CE offers efficient global counterfactual explanations.
problem Lack of reliable and scalable global counterfactual explanations.
method Translation-based approach for global counterfactual explanations.
result GLOBE-CE performs significantly better than current methods across multiple metrics.
Proposes a method for multilevel explanations of black-box models.
problem Need for explanations at intermediate or group levels, especially for GDPR compliance.
method Meta-method that builds a multilevel explanation tree using local explainability methods.
result Effective multilevel explanations for groups of data points, including novel test points.
Paper addresses instance-level label prediction in MIL, improving performance compared to existing methods.
problem Lack of instance-level label prediction in existing MIL approaches restricts their applicability.
method Proposes a novel algorithm with instance-level loss function, unbiasedly and consistently estimated.
result Empirically validated superior instance-level and bag-level performance compared to state-of-the-art methods.
ISAHP discovers instance-level causal structures in event sequences.
problem Discovering fine-grained causal relationships in asynchronous, interdependent event sequences.
method ISAHP, a novel deep learning framework using self-attention mechanism.
result ISAHP meets Granger causality requirements and discovers complex causal structures.
Method uses elastic black-boxes to create interpretable models from complex ones.
problem Lack of trust and stability in opaque models and time-consuming feature engineering in interpretable models.
method Surrogate assisted feature extraction for model learning.
result Trains interpretable and accurate models without time-consuming feature engineering.
ILM-Norm normalizes instances individually for better performance.
problem Learning to normalize parameters for improved model performance.
method ILM-Norm learns normalization parameters via feature feed-forward and gradient back-propagation.
result ILM-Norm consistently improves model performance across different architectures and tasks.
InstanceFlow visualizes classifier confusion over training epochs.
problem Limited model interpretability through aggregate performance measures.
method Dual-view visualization tool showing instance-level learning behavior.
result Allows temporal analysis of training process and instance-level performance.
Paper improves deep learning for instance-level classification from label proportions.
problem Dealing with noisy pseudo-labeling and high-entropy class distributions in LLP.
method Introducing a two-stage training approach with constrained optimization and mixup strategy.
result Significant performance improvement in instance-level classification.
New framework explains ML credit scoring models using counterfactual examples.
problem Explaining complex ML models in finance for credit scoring.
method Adversarial counterfactual examples for tabular data.
result Proposes a method to generate realistic counterfactual examples for tabular data.
TaRP predicts missing relations in KGs using type and instance-level info.
problem Missing relations in KGs.
method Type-augmented relation prediction (TaRP) combining type and instance-level info.
result Significantly better performance on benchmark datasets.
The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.
problem Disparate impacts of noisy labels on instances with different representation frequencies.
method Quantifying harms, analyzing solutions, and comparing their impacts on different frequency instances.
result Existing solutions lead to disparate treatments, benefiting higher-frequency instances more.
Meta-learning framework improves explainability of GNNs.
problem Improving explainability of graph neural networks.
method Meta-learning framework to steer GNN training towards interpretable minima.
result Models are easier to explain by different algorithms without sacrificing accuracy.
The paper proposes a method to transfer knowledge across different settings using causal theory.
problem Learning transfer across similar but different settings.
method Bayesian perspective of causal theory induction, integrating instance-level associative learning and abstract-level structural causal knowledge.
result The proposed model achieved transfer behavior across trials and learning situations, unlike RL algorithms.
Easyllp simplifies LLP, achieving low task loss at individual instance level.
problem Weakly supervised classification with label proportions.
method Flexible debiasing approach based on aggregate labels, operating on arbitrary loss functions.
result Accurately estimates expected loss at individual level, with provable guarantees.
This paper compares two loss functions for learning from aggregated responses and introduces an interpolating estimator.
problem Learning from aggregated responses in privacy-sensitive settings.
method Investigates bag-level and instance-level loss functions, and introduces an interpolating estimator.
result Instance-level loss can be seen as a regularized form of bag-level loss, leading to improved estimators.
Bayesian algorithms improve crowdsourcing with label and instance constraints.
problem Efficiently labeling large datasets with additional human annotator information.
method Developed Bayesian algorithms for semi-supervised crowdsourced classification under label and instance constraints.
result Improved performance compared to unsupervised crowdsourcing on various datasets.
Unified method for local GBDT feature contributions.
problem Need for local model interpretation for GBDT.
method Unified computation mechanism for instance-level feature contributions.
result Unified computation mechanism for GBDT feature contributions.
LoRMIkA finds k-optimal association rules for local model interpretability.
problem Ensuring trust in machine learning predictions.
method Model-agnostic approach using k-optimal association rules from a neighbourhood.
result Achieves competitive results in local accuracy and interpretability.
Develops a new feature selection method using deep-learning saliency.
problem Lack of instance-level feature selection information.
method Saliency-based Feature Selection (SFS) method.
result SFS method provides instance-level feature selection information.
Linear Discriminant Analysis (LDA) is a well-known method for dimensionality reduction and classification. Previous studies have also extended the binary-class case into multi-classes. However, many applications, such as object detection and keyframe extraction cannot provide consistent instance-label pairs, while LDA …
Paper proposes M3Lcmf for better M3L performance.
problem Complex objects with diverse instances and multiple labels.
method Collaborative matrix factorization with heterogeneous network.
result M3Lcmf outperforms other solutions in benchmark datasets.
ICE proposes a new loss function for deep metric learning.
problem Deep metric learning from instance-level matching distribution.
method Instance Cross Entropy (ICE) loss function.
result ICE outperforms existing methods on real-world benchmarks.
Paper tackles open set domain adaptation by detecting unknown classes.
problem Adapting to target domains with unknown classes when label spaces partially overlap.
method Instance-level reweighting strategy combined with Extreme Value Theory for unknown class detection.
result Proposed method outperforms state-of-the-art models on conventional datasets.
DW-KNN improves KNN by integrating distance and neighbor reliability for better prediction accuracy.
problem Standard KNN assumes all neighbors are equally reliable, leading to unreliable predictions in heterogeneous feature spaces.
method DW-KNN integrates exponential distance with neighbor validity, providing instance-level interpretability and reducing hyperparameter sensitivity.
result DW-KNN achieves 0.8988 average accuracy, ranks 2nd among six methods, and has the lowest cross-validation variance.
NASirt automates CNN architecture design for spectral data.
problem Designing optimal neural architectures for complex data.
method Neural Architecture Search (NAS) with Item Response Theory (IRT) for instance-level complexity.
result NASirt achieves high accuracy (97.40%) on spectral datasets.
A new SSL method uses instance-dependent thresholds to improve accuracy.
problem Improving semi-supervised learning by better selecting confident unlabeled instances.
method Proposes instance-dependent thresholds that vary based on the ambiguity and error rates of pseudo-labels for each unlabeled instance.
result Demonstrates that instance-dependent thresholds provide a probabilistic guarantee for correct pseudo-labels.
Proposes OpenKI for better web-scale knowledge extraction and alignment.
problem Combining OpenIE and KB for web-scale knowledge extraction and alignment.
method Instance-level inference using neighborhood information from KB and OpenIE extractions, with attention mechanisms.
result Significantly improves performance on OpenIE extractions and semi-structured data.
Many methods to explain black-box models, whether local or global, are additive. In this paper, we study global additive explanations for non-additive models, focusing on four explanation methods: partial dependence, Shapley explanations adapted to a global setting, distilled additive explanations, and gradient-based e…
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New definition reveals encoding explanations that retain predictive power.
problem Challenges in evaluating and identifying encoding explanations.
method Developed a definition of encoding based on conditional dependence.
result Existing evaluation scores do not rank non-encoding explanations correctly, but STRIPE-X does.
Proposes new measures and methods for evaluating and improving explanations of machine learning models.
problem Evaluating and improving explanations of complex machine learning models.
method Introduces two new measures: infidelity and sensitivity, and proposes methods to optimize these measures.
result Optimal explanations for infidelity involve a novel combination of two methods, and can outperform existing explanations.
Combines neural network explanation methods to improve robustness and accuracy.
problem Lack of consensus on explaining neural network decisions and evaluating explanations.
method Investigates schemes to aggregate explanation methods and reduce model uncertainty.
result Aggregated explanations are better at identifying important features and more robust to adversarial attacks.
Survey on efficient counterfactual explanations for various ML models.
problem Providing understandable explanations for machine learning predictions.
method Review and propose methods for computing counterfactual explanations.
result Efficient methods for various ML models and new methods for unconsidered models.
GRANITE unifies feature-based explanation methods to reduce disagreement.
problem Disagreement among feature-based explanation methods.
method GRANITE partitions feature space into regions minimizing interaction and distribution influences.
result Unified and consistent feature explanations.
Efficiently computes counterfactual explanations for LVQ models.
problem Need to efficiently explain predictions of machine learning models.
method Derives convex and non-convex programs for LVQ models.
result Efficient computation of counterfactual explanations for LVQ models.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
Paper proposes metrics to evaluate AI explanations without ground truth.
problem Challenges in evaluating neural network explanations without ground truth.
method Designs four metrics to evaluate explanation results.
result New insights into neural network interpretation methods.
Paper explores a consumer-friendly approach to explain machine learning decisions.
problem Challenges in providing understandable explanations for machine learning predictions.
method Consumer-driven approach called TED that asks for explanations in training data.
result TED is robust to increasing numbers of explanations, noisy explanations, and missing explanations.
Formalizes explanations as blending input and model output.
problem Creating clear and consistent explanations for model predictions.
method Defines properties of explanation functions and links them to model layers.
result Consistency of activations across layers implies consistency of explanations.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.