Interpretability Guarantees with Merlin-Arthur Classifiers

• URL: http://arxiv.org/abs/2206.00759v3
• Date: Fri, 22 Mar 2024 14:13:56 GMT
• Title: Interpretability Guarantees with Merlin-Arthur Classifiers
• Authors: Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta,
• Abstract summary: We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. Our results are inspired by the Merlin-Arthur protocol from Interactive Proof Systems.
• Score: 21.55030847779525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the classification decision. Our results are inspired by the Merlin-Arthur protocol from Interactive Proof Systems and express these bounds in terms of measurable metrics such as soundness and completeness. Compared to existing interactive setups, we rely neither on optimal agents nor on the assumption that features are distributed independently. Instead, we use the relative strength of the agents as well as the new concept of Asymmetric Feature Correlation which captures the precise kind of correlations that make interpretability guarantees difficult. We evaluate our results on two small-scale datasets where high mutual information can be verified explicitly.

Related papers

• Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence [51.54175067684008]
  This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. We first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.
  arXiv  Detail & Related papers  (2024-03-17T07:02:55Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network [15.196758664999455]
  We re-frame the task of multimodal semantic segmentation by enforcing a tightly coupled feature representation and a symmetric information-sharing scheme. We also introduce an ad-hoc class-incremental continual learning scheme, proving our approach's effectiveness and reliability even in safety-critical settings.
  arXiv  Detail & Related papers  (2023-08-09T04:46:16Z)
• Copula for Instance-wise Feature Selection and Ranking [24.09326839818306]
  We propose to incorporate the Gaussian copula, a powerful mathematical technique for capturing correlations between variables, into the current feature selection framework. Experimental results on both synthetic and real datasets, in terms of performance comparison and interpretability, demonstrate that our method is capable of capturing meaningful correlations.
  arXiv  Detail & Related papers  (2023-08-01T13:45:04Z)
• 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)
• Compressed Regression over Adaptive Networks [58.79251288443156]
  We derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents.
  arXiv  Detail & Related papers  (2023-04-07T13:41:08Z)
• Robust Event-Driven Interactions in Cooperative Multi-Agent Learning [0.0]
  We present an approach to reduce the communication required between agents in a Multi-Agent learning system by exploiting the inherent robustness of the underlying Markov Decision Process. We compute so-called robustness surrogate functions (off-line), that give agents a conservative indication of how far their state measurements can deviate before they need to update other agents in the system. This results in fully distributed decision functions, enabling agents to decide when it is necessary to update others.
  arXiv  Detail & Related papers  (2022-04-07T11:00:39Z)
• Learning Multimodal VAEs through Mutual Supervision [72.77685889312889]
  MEME combines information between modalities implicitly through mutual supervision. We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes.
  arXiv  Detail & Related papers  (2021-06-23T17:54:35Z)
• Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation [32.37031528767224]
  Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between different groups in downstream applications. We demonstrate an effective method for controlling parity through mutual information based on contrastive information estimators. We test our approach on UCI Adult and Heritage Health datasets and demonstrate that our approach provides more informative representations across a range of desired parity thresholds.
  arXiv  Detail & Related papers  (2021-01-11T18:57:33Z)
• Combining Task Predictors via Enhancing Joint Predictability [53.46348489300652]
  We present a new predictor combination algorithm that improves the target by i) measuring the relevance of references based on their capabilities in predicting the target, and ii) strengthening such estimated relevance. Our algorithm jointly assesses the relevance of all references by adopting a Bayesian framework. Based on experiments on seven real-world datasets from visual attribute ranking and multi-class classification scenarios, we demonstrate that our algorithm offers a significant performance gain and broadens the application range of existing predictor combination approaches.
  arXiv  Detail & Related papers  (2020-07-15T21:58:39Z)

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.