On the stability of recommendation algorithms

By Gediminas Adomavicius, Jingjing Zhang. 2010

86 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Anne-Marie Kermarrec
2. Karl Aberer
3. Alexandra Olteanu
4. Gediminas Adomavicius
5. Jingjing Zhang
6. Nisheeth K. Vishnoi

In Information Systems

1. Lingxiao Huang
2. Jingjing Zhang
3. Anne-Marie Kermarrec
4. Alexandra Olteanu
5. Karl Aberer
6. Nisheeth K. Vishnoi
7. Gediminas Adomavicius
8. Smriti Bhagat

In Management Science and Operations Research

1. Lingxiao Huang
2. Nisheeth K. Vishnoi
3. Jingjing Zhang
4. Anne-Marie Kermarrec
5. Alexandra Olteanu
6. Karl Aberer
7. Gediminas Adomavicius
8. Jin-Hee Cho

Citations in the corpus

• Stable and Fair Classification (2019, background): “Moreover, stability is also important for the reliability and acceptability of recommendation systems [2, 1, 3].”
• A Survey on Trust Modeling (2015, background): “Adomavicius and Zhang [2010] use the stability metric to measure the performance of recommendation systems based on the difference between performance predictions.”
• Comparing the Predictive Capability of Social and Interest Affinity for Recommendations (2014, methodology): “On top of it, we implement the main building blocks of SR and CF as used for comparison in literature [3, 20, 21, 35, 25, 23].”
• Maximizing stability of recommendation algorithms: A collective inference approach (2011, methodology): “Our experimental results on real-world movie rating data demonstrate that the proposed approach can achieve substantially higher stability as compared to the original recommendation algorithms, while, perhaps as importantly, providing additional improvements in predictive accuracy as well.”
• Classification, Ranking, and Top-K Stability of Recommendation Algorithms (2016, background): “Figure 1 (Color online) Illustration of Stability Computation, Adapted from Adomavicius and Zhang (2010) (in)stability of a recommendation algorithm represents the degree of (in)consistency between the different predictions made by the algorithm.”
• BlurMe: inferring and obfuscating user gender based on ratings (2012, background): “Our work is also related to studies of robustness in recommender systems [10, 3, 1].”