Inflammation
发表于 2025-3-28 17:44:28
http://reply.papertrans.cn/32/3193/319289/319289_41.png
RECUR
发表于 2025-3-28 19:40:51
Dear XAI Community, We Need to Talk!unately, these unfounded parts are not on the decline but continue to grow. Many explanation techniques are still proposed without clarifying their purpose. Instead, they are advertised with ever more fancy-looking heatmaps or only seemingly relevant benchmarks. Moreover, explanation techniques are
名次后缀
发表于 2025-3-29 02:11:05
Speeding Things Up. Can Explainability Improve Human Learning? such circumstances, the algorithm requests a teacher, usually a human, to select or verify the system’s prediction on the most informative points. The most informative usually refers to the instances that are the hardest for the algorithm to label. However, it has been proven that humans are more l
fastness
发表于 2025-3-29 06:15:09
http://reply.papertrans.cn/32/3193/319289/319289_44.png
CLAY
发表于 2025-3-29 08:25:02
http://reply.papertrans.cn/32/3193/319289/319289_45.png
excursion
发表于 2025-3-29 15:01:03
Do Intermediate Feature Coalitions Aid Explainability of Black-Box Models? a hierarchical structure in which each level corresponds to features of a dataset (i.e., a player-set partition). The level of coarseness increases from the trivial set, which only comprises singletons, to the set, which only contains the grand coalition. In addition, it is possible to establish me
尊敬
发表于 2025-3-29 18:04:43
Unfooling SHAP and SAGE: Knockoff Imputation for Shapley Valuesbutions are susceptible to adversarial attacks. This originates from target function evaluations at extrapolated data points, which are easily detectable and hence, enable models to behave accordingly. In this paper, we introduce a novel strategy for increased robustness against adversarial attacks
commune
发表于 2025-3-29 20:07:49
Strategies to Exploit XAI to Improve Classification Systemsesults beyond their decisions. A significant goal of XAI is to improve the performance of AI models by providing explanations for their decision-making processes. However, most XAI literature focuses on how to explain an AI system, while less attention has been given to how XAI methods can be exploi
抓住他投降
发表于 2025-3-30 00:19:01
Beyond Prediction Similarity: ShapGAP for Evaluating Faithful Surrogate Models in XAImodels. Surrogation, emulating a black-box model (BB) with a white-box model (WB), is crucial in applications where BBs are unavailable due to security or practical concerns. Traditional fidelity measures only evaluate the similarity of the final predictions, which can lead to a significant limitati
动脉
发表于 2025-3-30 07:32:07
iPDP: On Partial Dependence Plots in Dynamic Modeling Scenariosinable artificial intelligence (XAI) to understand black-box machine learning models. While many real-world applications require dynamic models that constantly adapt over time and react to changes in the underlying distribution, XAI, so far, has primarily considered static learning environments, whe