Advanced Pattern Mining - Data Mining: Concepts and Techniques - page 280

frequent patterns
association rules
closed/max patterns
generators

Basic Patterns

multilevel (uniform, varied, or itemset-based support)
multidimensional patterns (incl. high-dimensional patterns)
continuous data (discretization-based or statistical)

Kinds of
Patterns
and Rules

Multilevel and
Multidimensional
Patterns

approximate patterns
uncertain patterns
compressed patterns
rare patterns/negative patterns
high-dimensional and colossal patterns

Extended Patterns

candidate generation (Apriori, partitioning, sampling, ...)
Pattern growth (FP-growth, HMine, FPMax, Closet+, ...)
vertical format (Eclat, CHARM, ...)

Basic Mining
Methods

interestingness (subjective vs. objective)
constraint-based mining
correlation rules
exception rules
distributed/parallel mining
incremental mining
stream patterns

Mining Interesting
Patterns

Mining Methods

Distributed, Parallel,
and Incremental

sequential and time-series patterns
structural (e.g., tree, lattice, graph) patterns
spatial (e.g., colocation) patterns
temporal (evolutionary, periodic) patterns
image, video, and multimedia patterns
network patterns

Extended Data
Types

Extensions and
Applications

pattern-based classification
pattern-based clustering
pattern-based semantic annotation
collaborative filtering
privacy-preserving

Applications

Figure 7.1 A general road map on pattern mining research.

Based on pattern diversity, pattern mining can be classified using the following
criteria:

Basic patterns: As discussed in Chapter 6, a frequent pattern may have several alter-
native forms, including a simple frequent pattern, a closed pattern, or a max-pattern.
To review, a frequent pattern is a pattern (or itemset) that satisfies a minimum sup-
port threshold. A pattern p is a closed pattern if there is no superpattern p 0 with the
same support as p . Pattern p is a max-pattern if there exists no frequent superpattern
of p . Frequent patterns can also be mapped into association rules , or other kinds
of rules based on interestingness measures. Sometimes we may also be interested in
infrequent or rare patterns (i.e., patterns that occur rarely but are of critical impor-
tance, or negative patterns (i.e., patterns that reveal a negative correlation between
items).