Similarity Score

A similarity score is a score that categorizes the similarity between two or more data points.

• AKA: Affinity Value.
• Example(s):
  • a Semantic Similarity Score.
  • …
• Counter-Example(s):
  • a Similarity Measure.
• See: Affinity Matrix, Distance Function, Kernel Similarity Score.

---

---

References

2008

• (Kang et al., 2008) ⇒ Hyunmo Kang, Lise Getoor, Ben Shneiderman, Mustafa Bilgic, and Louis Licamele. (2008). “Interactive Entity Resolution in Relational Data: A Visual Analytic Tool and Its Evaluation.” In: IEEE Transactions on Visualization and Computer Graphics (TVCG), 14(5).
  • QUOTE: Users have the choice of inspecting each potential duplicate or automatically merging all duplicates with a similarity score above a user-selected threshold.

2005

• (Leordeanu & Hebert, 2005) ⇒ Marius Leordeanu, and Martial Hebert. (2005). “A Spectral Technique for Correspondence Problems Using Pairwise Constraints.” In: Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV 2005) doi:10.1109/ICCV.2005.20
  • QUOTE: We require these affinities to be non-negative ...

2001

• (Crammer & Singer, 2001) ⇒ Koby Crammer, and Yoram Singer. (2001). “Ultraconservative Online Algorithms for Multiclass Problems" In: Proceedings of the Fourteenth Annual Conference on Computational Learning Theory (COLT 2001). doi:10.1007/3-540-44581-1_7
  • QUOTE: Given an input instance, a multiclass hypothesis computes a similarity-score between each prototype and the input instance and then sets the predicted label to be the index of the prototype achieving the highest similarity