Unsupervised ranking of clustering algorithms by INFOMAX
Sandipan Sikdar1, Animesh Mukherjee2, Matteo Marsili3
1RWTH Aachen University, Aachen, Germany.
Plos One
|October 26, 2020
Summary
Ranking clustering algorithms is crucial for data analysis. Linsker's Infomax principle, using partition entropy, effectively ranks clustering and community detection algorithm performance on diverse datasets.
Area of Science:
- Data Science
- Machine Learning
- Network Analysis
Background:
- Clustering and community detection are vital for extracting insights from large datasets.
- Numerous algorithms exist, necessitating performance evaluation methods.
- Ranking algorithm effectiveness is essential for practical applications.
Purpose of the Study:
- To introduce a method for ranking clustering and community detection algorithms.
- To demonstrate the applicability of Linsker's Infomax principle for algorithm performance evaluation.
- To validate the proposed ranking method across various datasets.
Main Methods:
- Utilizing Linsker's Infomax principle to evaluate clustering algorithms.
- Calculating the entropy of the partition for different algorithms.
- Comparing algorithm rankings based on partition entropy with ground truth partitions.
Main Results:
- Linsker's Infomax principle provides a reliable method for ranking clustering algorithms.
- Higher partition entropy values correlate with better algorithm performance.
- The ranking method shows strong correlation with ground truth partitions across diverse datasets.
Conclusions:
- Partition entropy, guided by Linsker's Infomax principle, is an effective metric for ranking clustering algorithms.
- This approach offers a robust way to select optimal algorithms for data analysis tasks.
- The findings are validated on datasets with varying sizes and structures.
Related Concept Videos
01:20Cluster Sampling Method
13.8K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
13.8K
01:02Ranks
377
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
377
01:29Aggregates Classification
586
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
586
01:31Classification of Systems-II
392
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
392
01:26Classification of Systems-I
465
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
465
01:02Quantifying and Rejecting Outliers: The Grubbs Test
3.3K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
3.3K