Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability

• URL: http://arxiv.org/abs/2305.03100v3
• Date: Wed, 17 May 2023 17:21:45 GMT
• Title: Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainability
• Authors: Daniel Lundstrom and Meisam Razaviyayn
• Abstract summary: We present a unifying framework for game-theory-inspired attribution and $ktextth$-order interaction methods. We identify how various methods are characterized by their policy of distributing synergies. We show that the combination of various criteria uniquely defines the attribution/interaction methods.
• Score: 9.416757363901295
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust in AI-powered decision making and is necessary for understanding other practical needs such as robustness and fairness. A popular means of enhancing model transparency is to quantify how individual inputs contribute to model outputs (called attributions) and the magnitude of interactions between groups of inputs. A growing number of these methods import concepts and results from game theory to produce attributions and interactions. This work presents a unifying framework for game-theory-inspired attribution and $k^\text{th}$-order interaction methods. We show that, given modest assumptions, a unique full account of interactions between features, called synergies, is possible in the continuous input setting. We identify how various methods are characterized by their policy of distributing synergies. We also demonstrate that gradient-based methods are characterized by their actions on monomials, a type of synergy function, and introduce unique gradient-based methods. We show that the combination of various criteria uniquely defines the attribution/interaction methods. Thus, the community needs to identify goals and contexts when developing and employing attribution and interaction methods.

Related papers

• The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models [40.128112851978116]
  We study how different prompting methods affect the geometry of representations in language models. Our analysis highlights the critical role of input distribution samples and label semantics in few-shot in-context learning. Our work contributes to the theoretical understanding of large language models and lays the groundwork for developing more effective, representation-aware prompting strategies.
  arXiv  Detail & Related papers  (2025-02-11T23:09:50Z)
• Hierarchical Banzhaf Interaction for General Video-Language Representation Learning [60.44337740854767]
  Multimodal representation learning plays an important role in the artificial intelligence domain. We introduce a new approach that models video-text as game players using multivariate cooperative game theory. We extend our original structure into a flexible encoder-decoder framework, enabling the model to adapt to various downstream tasks.
  arXiv  Detail & Related papers  (2024-12-30T14:09:15Z)
• Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory [21.405333804566357]
  We introduce a unified framework for local and global feature-based explanations. We introduce three fANOVA decompositions that determine the influence of feature distributions. We then empirically showcase the usefulness of our framework on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-12-22T20:12:16Z)
• Visual-Geometric Collaborative Guidance for Affordance Learning [63.038406948791454]
  We propose a visual-geometric collaborative guided affordance learning network that incorporates visual and geometric cues. Our method outperforms the representative models regarding objective metrics and visual quality.
  arXiv  Detail & Related papers  (2024-10-15T07:35:51Z)
• Data Science Principles for Interpretable and Explainable AI [0.7581664835990121]
  Interpretable and interactive machine learning aims to make complex models more transparent and controllable. This review synthesizes key principles from the growing literature in this field.
  arXiv  Detail & Related papers  (2024-05-17T05:32:27Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications [90.6849884683226]
  We study the challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data. Using a precise information-theoretic definition of interactions, our key contribution is the derivation of lower and upper bounds. We show how these theoretical results can be used to estimate multimodal model performance, guide data collection, and select appropriate multimodal models for various tasks.
  arXiv  Detail & Related papers  (2023-06-07T15:44:53Z)
• Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks [62.48782506095565]
  We show that due to the greedy nature of learning in deep neural networks, models tend to rely on just one modality while under-fitting the other modalities. We propose an algorithm to balance the conditional learning speeds between modalities during training and demonstrate that it indeed addresses the issue of greedy learning.
  arXiv  Detail & Related papers  (2022-02-10T20:11:21Z)
• Self-Attention Attribution: Interpreting Information Interactions Inside Transformer [89.21584915290319]
  We propose a self-attention attribution method to interpret the information interactions inside Transformer. We show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.
  arXiv  Detail & Related papers  (2020-04-23T14:58:22Z)
• Interactions in information spread: quantification and interpretation using stochastic block models [3.5450828190071655]
  In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. Here, we propose a new model, the Interactive Mixed Membership Block Model (IMMSBM), which investigates the role of interactions between entities. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150% in the probability of an outcome.
  arXiv  Detail & Related papers  (2020-04-09T14:22:10Z)

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.