Generative Well-intentioned Networks
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative network recovers the distribution of observations that the classifier labels correctly with high certainty. We introduce a reject option to the classifier during inference, allowing the classifier to reject an observation instance rather than predict an uncertain label. These rejected observations are translated by the generative network to high-certainty representations, which are then relabeled by the classifier. This architecture allows for any certainty-based classifier or rejection function and is not limited to multilayer perceptrons. The capability of this framework is assessed using benchmark classification datasets and shows that GWINs significantly improve the accuracy of uncertain observations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
The potential social harms that large language models pose, such as generating offensive content and reinforcing biases, are steeply rising. Existing works focus on coping with this concern while interacting with ill-int…
Response GenerationOptimal Attention Management: A Tractable Framework
A well-intentioned principal provides information to a rationally inattentive agent without internalizing the agent's cost of processing information. Whatever information the principal makes available, the agent may choo…
ManagementLinguistic Elements of Engaging Customer Service Discourse on Social Media
Customers are rapidly turning to social media for customer support. While brand agents on these platforms are motivated and well-intentioned to help and engage with customers, their efforts are often ignored if their ini…
Calibrating “Cheap Signals” in Peer Review without a Prior
Peer review lies at the core of the academic process, but even well-intentioned reviewers can still provide noisy ratings. While ranking papers by average ratings may reduce noise, varying noise levels and systematic bia…
Secondary Stakeholders in AI: Fighting for, Brokering, and Navigating Agency
As AI technologies become more human-facing, there have been numerous calls to adapt participatory approaches to AI development -- spurring the idea of participatory AI. However, these calls often focus only on primary s…
Navigate