Home Knowledge Base Data Attribution

Data Attribution

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution

Announce Type: new Abstract: Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critical subset dynamics, including data redundancy and complementary coverage. In this work, we reframe attribution as subset-level counterfactual utility prediction and introduce GRASP, an interaction-aware surrogate.

arXiv CS 2d ago

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

Announce Type: replace Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or object classes). Group-wise attribution is counterfactual: how would a model's behavior on a generated sample change if a group were absent from training?

arXiv CS 8d ago

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units

Announce Type: replace Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive. We introduce Mechanistic Data Attribution (MDA), a scalable framework that employs Influence Functions to trace interpretable units back to specific training samples. Through extensive experiments on the Pythia family, we causally validate that targeted intervention--removing or augmenting a small fraction of high-influence...

arXiv CS 1d ago

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations

Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model changes when data is added or removed, but repeated retraining is computationally challenging for Large Language Models (LLMs). Consequently, most approaches approximate this effect in the parameter space using gradients.

arXiv CS 6d ago

Data Attribution in Large Language Models via Bidirectional Gradient Optimization

Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance. Understanding which training data most influenced a model's output remains a fundamental open problem. We address this challenge through training data attribution (TDA) for auto-regressive LLMs by expanding upon the inverse formulation: How would training data be affected if the model had seen the...

arXiv CS 6d ago

Bridging CAD and Data-Driven Design: Attributed Feature Graphs for Engineering Design

Announce Type: new Abstract: Engineering design is an iterative, simulation-driven process where traditional workflows rely heavily on computationally expensive analyses such as finite element and computational fluid dynamics. Although data-driven methods have accelerated design evaluation and optimization, most existing geometric representations discard parametric and feature-level semantics, limiting their integration with CAD-driven design workflows and reducing model interpretability. To...

arXiv CS 5d ago

ReSAGE-PAR: Representational Similarity Assessment for Generative Expansion in Pedestrian Attribute Recognition

arXiv:2606.06020v1 Announce Type: new Abstract: To address the limited diversity and data scarcity in Pedestrian Attribute Recognition (PAR), we explore image synthesis using diffusion models guided by attribute-based prompts. While this enables the controlled generation of pedestrian images, it faces two critical challenges: (i) the domain gap between high-quality pre-training data and low-resolution, non-standard surveillance crops, and (ii) the need for reliable attribute verification to...

arXiv CS 5d ago

PINNfluence: Interpreting PINNs through Influence Functions

arXiv:2409.08958v3 Announce Type: replace-cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) in the physical sciences, yet their behavior remains largely opaque and is typically understood through failure mode analyses rather than explicit interpretability. To address this issue, we introduce PINNfluence, a training data attribution framework for interpreting PINNs based on influence...

arXiv Physics 7d ago

PINNfluence: Interpreting PINNs through Influence Functions

arXiv:2409.08958v3 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) in the physical sciences, yet their behavior remains largely opaque and is typically understood through failure mode analyses rather than explicit interpretability. To address this issue, we introduce PINNfluence, a training data attribution framework for interpreting PINNs based on influence...

arXiv CS 7d ago

ActiveMimic: Egocentric Video Pretraining with Active Perception

Announce Type: new Abstract: Egocentric human video offers a scalable alternative to robot data for pretraining, yet models pretrained on such video consistently underperform those pretrained on robot data. We attribute this gap to a missing signal, the active perception behavior in egocentric videos, where humans continuously reposition their viewpoint during manipulation, inducing camera motion that standard pipelines treat as noise. To address this, we present ActiveMimic, a pretraining...

arXiv CS 5d ago