aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYuchen Pei <me@ypei.me>2019-01-03 09:14:14 +0100
committerYuchen Pei <me@ypei.me>2019-01-03 09:14:14 +0100
commitf1e5741d03d181d7417dcf06e40d81d5e0fd5434 (patch)
tree48cd7512b18f0a87722f346748443366d0f699da
parent9b5045d3363a009b44edb986a7482e7ec450a8ec (diff)
corrected some attributions
-rw-r--r--posts/2018-12-02-lime-shapley.md10
1 files changed, 6 insertions, 4 deletions
diff --git a/posts/2018-12-02-lime-shapley.md b/posts/2018-12-02-lime-shapley.md
index a73d32e..c78a1e3 100644
--- a/posts/2018-12-02-lime-shapley.md
+++ b/posts/2018-12-02-lime-shapley.md
@@ -6,7 +6,7 @@ comments: true
---
In this post I explain LIME (Ribeiro et. al. 2016), the Shapley values
-(Shapley, 1953) and the SHAP values (Lundberg-Lee, 2017).
+(Shapley, 1953) and the SHAP values (Strumbelj-Kononenko, 2014; Lundberg-Lee, 2017).
__Acknowledgement__. Thanks to Josef Lindman Hörnlund for bringing the LIME
and SHAP papers to my attention. The research was done while working at KTH
@@ -247,9 +247,11 @@ Plugging this back into (6) we get the desired result. $\square$
SHAP
----
-The SHAP paper (Lundberg-Lee 2017) is not clear in its definition of the
-\"SHAP values\" and its relation to LIME, so the following is my
-interpretation of their interpretation model.
+The paper that coined the term \"SHAP values\" (Lundberg-Lee 2017)
+is not clear in its definition of the \"SHAP values\" and its
+relation to LIME, so the following is my
+interpretation of their interpretation model, which coincide with a
+model studied in Strumbelj-Kononenko 2014.
Recall that we want to calculate feature contributions to a model $f$ at
a sample $x$.