Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

• URL: http://arxiv.org/abs/2606.22314v2
• Date: Tue, 23 Jun 2026 07:21:49 GMT
• Title: Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
• Abstract summary: Integrated Diffusion Gradients (DiffIG) is a novel method that reformulates path generation as a conditional generative modeling problem.<n>We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations.<n>This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.
• Score: 29.066960285647962
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. However, the choice of the attribution path largely affects the quality of explanations, and existing approaches rely on fixed or hand-crafted paths that often produce noisy or distorted attributions. To address this limitation, we propose Diffusion Integrated Gradients (DiffIG), a novel method that reformulates path generation as a conditional generative modeling problem. DiffIG first trains a diffusion model to learn a distribution over paths generated from a Stick-Breaking Process, then employs guided sampling to embed user guidance during the sampling procedure. We demonstrate that DiffIG quantitatively matches or outperforms existing path-based methods, achieving perceptually aligned explanations. This work introduces a new generative perspective for flexible, inference-time controllable Explainable Artificial Intelligence (XAI) methods.

Related papers

• Attribution via Distributional Paths for Information Revelation [2.707154152696381]
  Our method Reveal-IG lifts path attribution from input space to a space of structured probe distributions.<n>It produces stable, signed attributions -- leading to metrics that use attribution sign while remaining competitive on the rest.
  arXiv  Detail & Related papers  (2026-06-02T16:50:28Z)
• Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics [49.242224984144904]
  We propose Euphonium, a novel framework that steers generation via process reward gradient guided dynamics.<n>Our key insight is to formulate the sampling process as a theoretically principled algorithm that explicitly incorporates the gradient of a Process Reward Model.<n>We derive a distillation objective that internalizes the guidance signal into the flow network, eliminating inference-time dependency on the reward model.
  arXiv  Detail & Related papers  (2026-02-04T08:59:57Z)
• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling [53.61290359948953]
  Tangential Amplifying Guidance (TAG) operates solely on trajectory signals without modifying the underlying diffusion model.<n>We formalize this guidance process by leveraging a first-order Taylor expansion.<n> TAG is a plug-and-play, architecture-agnostic module that improves diffusion sampling fidelity with minimal computational addition.
  arXiv  Detail & Related papers  (2025-10-06T06:53:29Z)
• Flows and Diffusions on the Neural Manifold [0.0]
  Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling.<n>In this work, we extend these advances to weight space learning by leveraging recent techniques to incorporate structural priors derived from optimization dynamics.<n>We unify several trajectory inference techniques towards matching a gradient flow, providing a theoretical framework for treating optimization paths as inductive bias.
  arXiv  Detail & Related papers  (2025-07-14T02:26:06Z)
• DDPS: Discrete Diffusion Posterior Sampling for Paths in Layered Graphs [27.60869539689859]
  We study the problem of generating paths in a layered graph using discrete diffusion models.<n>Our approach utilizes a simple yet effective representation for paths which we call the padded adjacency-list matrix.<n>Our preliminary results show that our method outperforms alternatives which do not explicitly account for path constraints.
  arXiv  Detail & Related papers  (2025-04-29T13:34:17Z)
• Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI [59.96044730204345]
  We introduce Derivative-Free Diffusion Manifold-Constrainted Gradients (FreeMCG)<n>FreeMCG serves as an improved basis for explainability of a given neural network.<n>We show that our method yields state-of-the-art results while preserving the essential properties expected of XAI tools.
  arXiv  Detail & Related papers  (2024-11-22T11:15:14Z)
• Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models [63.1637853118899]
  We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. We employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions.
  arXiv  Detail & Related papers  (2023-10-15T18:44:30Z)
• Towards Controllable Diffusion Models via Reward-Guided Exploration [15.857464051475294]
  We propose a novel framework that guides the training-phase of diffusion models via reinforcement learning (RL) RL enables calculating policy gradients via samples from a pay-off distribution proportional to exponential scaled rewards, rather than from policies themselves. Experiments on 3D shape and molecule generation tasks show significant improvements over existing conditional diffusion models.
  arXiv  Detail & Related papers  (2023-04-14T13:51:26Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.