Evolutionary Robust Clustering Over Time for Temporal Data

TL;DR

A new clustering framework called evolutionary robust clustering over time is proposed, which automatically infers the a posteriori preference to temporal smoothness without data’s affinity matrix and predefined parameters, which holds better applicability and efficiency.

Abstract

In many clustering scenes, data samples' attribute values change over time. For such data, we are often interested in obtaining a partition for each time step and tracking the dynamic change of partitions. Normally, a smooth change is assumed for data to have a temporal smooth nature. Existing algorithms consider the temporal smoothness as an a priori preference and bias the search towards the preferred direction. This a priori manner leads to a risk of converging to an unexpected region because it is not always the case that a reasonable preference can be elicited given the little prior knowledge about the data. To address this issue, this paper proposes a new clustering framework called evolutionary robust clustering over time. One significant innovation of the proposed framework is processing the temporal smoothness in an a posteriori manner, which avoids unexpected convergence that occurs in existing algorithms. Furthermore, the proposed framework automatically tunes the weight of smoothness without data's affinity matrix and predefined parameters, which holds better applicability and scalability. The effectiveness and efficiency of the proposed framework are confirmed by comparing with state-of-the-art algorithms on both synthetic and real datasets.

Figures (12)

• Figure 1: An example of solution encoding with $C_{max}=4$ and $D=3$, where $C_{max}$ is the maximum number of clusters, and $D$ is the dimensionality of data samples.
• Figure 2: Procedure of smoothness weight auto-tuning at time $t$.
• Figure 3: Heat map of each algorithm ranked at a particular position in mRI and mNMI performance comparison in each dataset.
• Figure 4: Illustration of synthetic dataset in the 2-D space. The bottom-left cluster moves toward the top-right one as time goes by.
• Figure 5: Average RI value among all runs of each algorithm at each time step of Syn3.