paper-with-me

홈 › Papers

BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation

2024-12-23 · Oren Barkan, Yehonatan Elisha, Jonathan Weill, Noam Koenigstein

Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information through baseline representations. The existing literature introduces diverse evaluation metrics, each scrutinizing the quality of explanations through distinct lenses. Additionally, various baseline representations have been proposed, each modeling the notion of missingness differently. Yet, a consensus on the ultimate evaluation metric and baseline representation remains elusive. This work acknowledges the diversity in explanation metrics and baselines, demonstrating that different metrics exhibit preferences for distinct explanation maps resulting from the utilization of different baseline representations and distributions. To address the diversity in metrics and accommodate the variety of baseline representations in a unified manner, we propose Baseline Exploration-Exploitation (BEE) - a path-integration method that introduces randomness to the integration process by modeling the baseline as a learned random tensor. This tensor follows a learned mixture of baseline distributions optimized through a contextual exploration-exploitation procedure to enhance performance on the specific metric of interest. By resampling the baseline from the learned distribution, BEE generates a comprehensive set of explanation maps, facilitating the selection of the best-performing explanation map in this broad set for the given metric. Extensive evaluations across various model architectures showcase the superior performance of BEE in comparison to state-of-the-art explanation methods on a variety of objective evaluation metrics.

📄 PDF Abstract BibTeX arXiv:2412.17512

Code (1)

yonisGit/BEE 공식 구현 pytorch

Tasks

Diversity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits

2021-10-07 · ICLR 2022 4 · Yikun Ban, Yuchen Yan, Arindam Banerjee, Jingrui He

In this paper, we propose a novel neural exploration strategy in contextual bandits, EE-Net, distinct from the standard UCB-based and TS-based approaches. Contextual multi-armed bandits have been studied for decades with…

Multi-Armed BanditsThompson Sampling

Breaking Information Cocoons: A Hyperbolic Graph-LLM Framework for Exploration and Exploitation in Recommender Systems

2024-11-21 · Qiyao Ma, Menglin Yang, Mingxuan Ju, Tong Zhao 외

Modern recommender systems often create information cocoons, restricting users' exposure to diverse content. A key challenge lies in balancing content exploration and exploitation while allowing users to adjust their rec…

Recommendation SystemsRepresentation Learning

MetaGFN: Exploring Distant Modes with Adapted Metadynamics for Continuous GFlowNets

2024-08-28 · Dominic Phillips, Flaviu Cipcigan

Generative Flow Networks (GFlowNets) are a class of generative models that sample objects in proportion to a specified reward function through a learned policy. They can be trained either on-policy or off-policy, needing…

Dealing with uncertainty: balancing exploration and exploitation in deep recurrent reinforcement learning

2023-10-12 · Valentina Zangirolami, Matteo Borrotti

Incomplete knowledge of the environment leads an agent to make decisions under uncertainty. One of the major dilemmas in Reinforcement Learning (RL) where an autonomous agent has to balance two contrasting needs in makin…

Autonomous Drivingreinforcement-learningReinforcement Learning (RL)

Neural Exploitation and Exploration of Contextual Bandits

2023-05-05 · Yikun Ban, Yuchen Yan, Arindam Banerjee, Jingrui He

In this paper, we study utilizing neural networks for the exploitation and exploration of contextual multi-armed bandits. Contextual multi-armed bandits have been studied for decades with various applications. To solve t…

Multi-Armed BanditsThompson Sampling