Search

19 Jun 2024: on their effects on people belonging to certain sensitivedemographic groups (e.g., gender, race). ... Now we compare user judgments of fairness of individual features, fordifferent demographic subgroups of people.

19 Jun 2024: Our Contributions. We collected and analyzed fairness judgmentsfrom a survey of 576 people. ... So our framework for how people judgefeature usage fairness consists of two-parts.

19 Jun 2024: Yet both concepts are somewhat ambiguous, and can meandifferent things to different people in different contexts. ... People might be experts or not. We list several types and goals of transparency.

19 Jun 2024: However, we note that such judgments can begathered from any other group of people, ranging fromcrowd workers to domain experts. ... people) more likelyto be falsely predicted as having a higher risk of recidivismthan another group of people (e.g., white

19 Jun 2024: Let x2 be a sensitive fea-ture, such as age, given by the shape of the point: assume youngand mature people. ... 100% points are accurate (correctly, blue maturepeople are in the blue zone, red mature people are in the red zone).

19 Jun 2024: 1 Introduction. Many important data-sets involve networks: people belong to social networks, webpages are joined in a linkgraph, and power utilities are connected in a grid.

19 Jun 2024: in terms of thetotal number of people influenced, and the fraction of peopleinfluenced from both A and B communities. ... maximizing the to-tal number of influenced people, while also significantly de-creasing disparity.

19 Jun 2024: 2017),and might help to promote greater understanding and cohe-sion among people. ... CNN You mean, like the UNFOUNDED claims of Russiancollusion? You people are typically selective in your bias pro?https://t.co/CESkVpIZOk@nytimes His actions were

19 Jun 2024: SampleSize” denotes how many people received this variant. The next two columns contain the proportionof correct answers when identifying epistemic or aleatoric uncertainty for LSAT, respectively.

19 Jun 2024: That is, max-margin training with approximateinference—which is something people do anyway to learn graphical models—reduces not only theprediction error, but also the inference approximation error.

19 Jun 2024: 2.2. Fairness Criteria. In large part, works that formalize fairness in machine learn-ing do so by balancing a certain condition between groupsof people with different sensitive attributes, z versus ... Figure 3. The fraction of people with z = 0

19 Jun 2024: Here, following earlierwork, unfairness means discriminating against a particulargroup of people due to sensitive group characteristics suchas gender or race (Grgic-Hlaca et al. ... For the Adult data, a random guessing classi-fier would result in 75.9%

19 Jun 2024: We furtherillustrate this point with two examples: First, by this definition amodel that assigns the same outcome to everyone is considered fair,regardless of people’s merit for different outcomes ... This offersa framework to interpolate between group

19 Jun 2024: for most people.8 Moreover, decisions about how to define objective functions and what training data to use can introduce human error into AI decision making.9 Thus, there exist legitimate

19 Jun 2024: I’ve had the privilege to collaborate with wonderful people. Many thanks to Tony, Dan Ellis,.