Corpus ID: 127008

Graph-based Generalization Bounds for Learning Binary Relations

@article{London2013GraphbasedGB,
  title={Graph-based Generalization Bounds for Learning Binary Relations},
  author={Ben London and Bert Huang and L. Getoor},
  journal={ArXiv},
  year={2013},
  volume={abs/1302.5348}
}
We investigate the generalizability of learned binary relations: functions that map pairs of instances to a logical indicator. This problem has application in numerous areas of machine learning, such as ranking, entity resolution and link prediction. Our learning framework incorporates an example labeler that, given a sequence $X$ of $n$ instances and a desired training size $m$, subsamples $m$ pairs from $X \times X$ without replacement. The challenge in analyzing this learning scenario is… Expand

References

SHOWING 1-10 OF 20 REFERENCES
Learning Binary Relations and Total Orders
Generalization Bounds for Ranking Algorithms via Algorithmic Stability
Chromatic PAC-Bayes Bounds for Non-IID Data
Ranking and empirical minimization of U-statistics
Learning with Equivalence Constraints and the Relation to Multiclass Learning
Rademacher Complexity Bounds for Non-I.I.D. Processes
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
...
1
2
...