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.
DEAL model predicts links for new nodes with only attribute info.
problem Predicting links for new nodes with only attribute info.
method DEAL model with two encoders and alignment mechanism.
result DEAL significantly outperforms existing methods on inductive link prediction.
EXAGREE selects a stakeholder-aligned model to reduce conflicting explanations in machine learning.
problem Conflicting explanations from different attribution methods limit the adoption of machine learning models in safety-critical domains.
method EXAGREE is a two-stage framework that selects a Stakeholder-Aligned Explanation Model (SAEM) from a set of similar-performing models, maximizing Stakeholder-Machine Agreement (SMA).
result EXAGREE achieves simultaneous gains in faithfulness, plausibility, and fairness over baselines while preserving task accuracy.
PAC-Bayesian theory improves text-to-image models by enforcing alignment and generalization.
problem Text-to-image models struggle with complex prompts, misaligning modifiers and neglecting certain elements.
method Proposes a Bayesian approach with custom priors over attention distributions to enforce desirable properties.
result Achieves state-of-the-art results across multiple metrics on standard benchmarks.
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.
We are interested in attribute-guided face generation: given a low-res face input image, an attribute vector that can be extracted from a high-res image (attribute image), our new method generates a high-res face image for the low-res input that satisfies the given attributes. To address this problem, we condition the …
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
problem Lack of systematic framework for quantifying feature contributions in opaque models.
method Taylor expansion framework with postulates (precision, federation, zero-discrepancy, adaptation).
result TaylorPODA achieves competitive results and provides principled explanations.
Bayesian approach scores influential training examples for model predictions.
problem Enhance interpretability and safety of machine learning models.
method Formulate TDA as a Bayesian information-theoretic problem, scoring subsets by information loss.
result Method aligns with classical influence scores while promoting diversity for subsets.
Paper detects biases in medical imaging ML models using counterfactual analysis.
problem Bias in medical imaging ML models negatively impacts generalization performance.
method Counterfactual invariance framework combining conditional latent diffusion models and statistical hypothesis testing.
result The method identifies and quantifies biases without direct access to counterfactual data.
Unified framework for aligning and composing diffusion models to satisfy multiple constraints.
problem Improving quality and compliance of generated samples from diffusion models.
method Constrained optimization framework that unifies alignment and composition of diffusion models.
result Proposed framework effectively satisfies multiple constraints in image generation.
CoDA Nets improve interpretability in neural networks.
problem Improving interpretability in neural networks.
method Dynamic Alignment Units (DAUs) for input-dependent linear transformations.
result CoDA Nets achieve on par results with ResNet and VGG models on complex datasets.
Enhances community detection in correlated networks with node attributes.
problem Community detection in multiple networks with correlated node attributes and edges.
method Introduced the correlated Contextual Stochastic Block Model (CSBM), developed a two-step matching procedure.
result Algorithm recovers exact node correspondence, enabling enhanced community detection.
Generative model tackles inconsistent attributes across datasets by enabling precise conditional generation.
problem Inconsistent attributes across merged datasets limit controllability in conditional generative modeling.
method Diffusion Model with Double Guidance, maintaining control over multiple conditions without joint annotations.
result Outperforms baselines in molecular and image generation tasks, aligning with target distributions and controlling missing conditions.
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.
New research shows input-gradients can be manipulated without changing model's core function, challenging their use for model interpretation.
problem Current methods for model interpretability using input-gradients are flawed due to their arbitrary manipulability.
method Investigated by reinterpreting logits as unnormalized log-densities, proposing novel approximations for score-matching.
result Improving alignment between implicit density model and data distribution enhances gradient structure and explanatory power.
Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or word vectors, as the bridge. However, due to the mutually disjoint of training (see…
StylEx trains a GAN to explain classifier decisions in StyleSpace.
problem Creating meaningful image-specific explanations for classifier decisions.
method Training a StyleGAN to learn a classifier-specific StyleSpace, incorporating the classifier model.
result StylEx finds attributes that align with semantic ones and generates human-interpretable explanations.
FCA improves fair clustering by optimizing utility and fairness.
problem Balancing fairness and utility in clustering.
method FCA alternates between aligning data and optimizing cluster centers in an aligned space.
result FCA achieves a superior trade-off between fairness and utility.
DVA framework attributes value of predictive models to features, configurations, and interactions.
problem Lack of explanation for how predictive models influence operational decisions.
method Shapley-based cooperative game theory applied to predict-then-optimize systems.
result DVA can guide targeted interventions to align model beliefs with operational performance.
A non-trivial predictor satisfies demographic parity and equalizes group risks in regression.
problem Achieving fairness in regression models while maintaining equal risks across groups.
method Provided an explicit example of a non-constant predictor satisfying Demographic Parity and Equal Group-Wise Risks.
result First explicit construction of a non-constant predictor satisfying both fairness notions.
Adding attributes for nodes to network embedding helps to improve the ability of the learned joint representation to depict features from topology and attributes simultaneously. Recent research on the joint embedding has exhibited a promising performance on a variety of tasks by jointly embedding the two spaces. Howeve…
WISCA generates consensus explanations from conflicting model-agnostic interpretability methods.
problem Conflicting explanations from diverse interpretability algorithms.
method WISCA integrates class probability and normalized attributions to generate consistent explanations.
result WISCA consistently aligns with the most reliable individual method, improving explanation reliability.
Changing initialization scale affects deep model generalization, leading to memorization or improved performance.
problem Understanding how initialization scale impacts deep model generalization and memorization.
method Experimental setup with varying initialization scales, analysis of activation and loss functions, and development of an alignment measure.
result Increasing initialization scale leads to memorization, and decreasing it improves generalization, depending on activation and loss functions.
Paper studies vertex correspondence recovery in correlated graphs with node features.
problem Recovering hidden vertex correspondence between two correlated graphs with observed edge weights and node features.
method Introduced featured correlated Gaussian Wigner model and proposed QPAlign algorithm for quadratic programming relaxation.
result Characterized optimal information-theoretic thresholds for exact and partial recovery of latent mapping.
We present a method for synthesizing a frontal, neutral-expression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous approaches, our encoding feature vector is largely…
LLMs can help explain credit risk models but not autonomously.
problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.
Hessian alignment improves OOD generalization in deep learning.
problem Improving deep learning models' ability to generalize to out-of-distribution data.
method Analyzed Hessian and gradient alignment for domain generalization using recent OOD theory.
result Hessian alignment methods achieve promising performance on various OOD benchmarks.
Digital personas improve survey results for stable attributes but fail for subjective responses.
problem When can digital personas reliably approximate human survey findings?
method Using LISS panel, constructed personas from background variables and survey histories, tested against held-out post-cutoff answers.
result Digital personas improve alignment with human response distributions for stable attributes but fail for subjective responses.
Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of labeled data in practice. The existing methods have succeeded by reducing the differen…
ExCIR provides efficient, consistent, and scalable explainability for complex models.
problem Complex models lack transparency and require efficient, stable, and scalable explainability methods.
method ExCIR uses correlation-aware feature attribution with robust centering and groupwise aggregation.
result ExCIR delivers trustworthy agreement with global baselines and full model rankings, reduces runtime, and scales to large datasets.
Proposes a new graph kernel framework using regularized Wasserstein distances.
problem Learning optimal transport distances for graph kernels.
method Introduces Regularized Wasserstein (RW) discrepancy with two regularization terms.
result Empirically validated method outperforms state-of-the-art methods.
Shapley values explain financial language models, aligning with domain knowledge.
problem Lack of explainability in financial applications of large language models.
method Shapley value analysis for financial textual data.
result Shapley values provide consistent explanations with financial reasoning.
Signed-permutation coordinate transport improves model alignment across checkpoints.
problem Improper alignment of coordinate-indexed objects across model checkpoints.
method Introduces sign-marginalized Hungarian matching and coordinate-preserving transport.
result Recovering signed-permutation gauge improves coordinate alignment and model performance.
A new deep generative model captures global dependencies without supervision.
problem Global modeling in deep generative models.
method Non-i.i.d. variational autoencoders with mixture model and global Gaussian latent variable.
result Captures interpretable disentangled representations and domain alignment.
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
MTNPs jointly model multiple correlated tasks from various sources.
problem Naive NPs can only model a single stochastic process and infer tasks independently.
method MTNPs are a hierarchical extension of NPs that jointly infer tasks from multiple stochastic processes, considering inter-task correlation and handling incomplete data.
result MTNPs successfully model multiple tasks jointly, discovering and exploiting their correlations in various real-world data.
A system for supervising decentralized finance risks using LLMs and structured evidence.
problem Supervising decentralized finance risks
method Forecast-grounded agentic supervision system
result Developed a system that scores tickets against a regulator-aligned ground truth and false-intervention rate.
DeXposure-Claw supervises decentralized finance risks by grounding LLM decisions in evidence.
problem Weak evidence leads to over-interventions by general-purpose LLM agents in decentralized finance.
method DeXposure-Claw uses a graph time-series foundation model to forecast exposure networks, turning forecasts into alerts and constraining escalation with data-health gates.
result DeXposure-Claw reduces false alarms and improves regulator alignment in decentralized finance risk supervision.
Study evaluates deep learning models for solar flare prediction with interpretability analysis.
problem Lack of interpretability in deep learning models for solar flare prediction.
method Proximity-based metric for analyzing attribution maps generated by Guided Grad-CAM.
result Models' predictions align with active region characteristics, offering insights into their behavior.
Framework quantifies financial NLP robustness under regime shifts.
problem Semantic and causal drift in financial news narratives.
method Four metrics: FCAS, PCS, TSV, NLICS.
result Transformer models are more affected by semantic drift.
CDOT optimizes transport between domains preserving both feature and geometric structure.
problem Optimizing transport between heterogeneous domains with preserved feature and geometric structure.
method CDOT uses operator-based regularization to align distance structures, proving pseudometric properties.
result CDOT improves robustness to local geometric variations and is provably convex.
Framework achieves fairness in predictions using partially known causal graph over clusters of variables.
problem Achieving fairness in algorithmic decisions when causal graph knowledge is limited.
method Leverages a causal graph over clusters of variables to train a prediction model, reducing interventional distribution discrepancies.
result Framework strikes a better balance between fairness and accuracy than existing approaches under limited causal graph knowledge.
NCL improves interpretability of deep features by enforcing non-negativity.
problem Lack of interpretability in deep representations.
method Non-negative Contrastive Learning (NCL) using non-negativity constraints.
result NCL outperforms standard contrastive learning in feature disentanglement and selection.
A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines and there is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning …
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc interface between two existing models to solve a new task. Specifically, we take i…
COCKATIEL explains neural net models on NLP tasks by identifying meaningful concepts.
problem Transformer models are complex and hard to interpret.
method COCKATIEL uses NMF and sensitivity analysis to identify and rank concepts used by the model.
result COCKATIEL provides accurate and meaningful explanations without affecting model performance.
New method selects equivariant models using uncertainty metrics.
problem Selecting equivariant models among pretrained ones with varying symmetry biases.
method Uncertainty-aware model selection using frequentist, Bayesian, and calibration-based measures.
result Bayesian model evidence often misaligns with predictive performance.