Fusion Multiple Kernel K-means

Abstract

Multiple kernel clustering aims to seek an appropriate combination of base kernels to mine inherent non-linear information for optimal clustering. Late fusion algorithms generate base partitions independently and integrate them in the following clustering procedure, improving the overall efficiency. However, the separate base partition generation leads to inadequate negotiation with the clustering procedure and a great loss of beneficial information in corresponding kernel matrices, which negatively affects the clustering performance. To address this issue, we propose a novel algorithm, termed as Fusion Multiple Kernel k-means (FMKKM), which unifies base partition learning and late fusion clustering into one single objective function, and adopts early fusion technique to capture more sufficient information in kernel matrices. Specifically, the early fusion helps base partitions keep more beneficial kernel details, and the base partitions learning further guides the generation of consensus partition in the late fusion stage, while the late fusion provides positive feedback on two former procedures. The close collaboration of three procedures results in a promising performance improvement. Subsequently, an alternate optimization method with promising convergence is developed to solve the resultant optimization problem. Comprehensive experimental results demonstrate that our proposed algorithm achieves state-of-the-art performance on multiple public datasets, validating its effectiveness. The code of this work is publicly available at https://github.com/ethan-yizhang/Fusion-Multiple-Kernel-K-means.

Coalition Formation for Task Allocation Using Multiple Distance Metrics (Student Abstract)

“…The efficacy of the MDM heuristic indicates that machine learning techniques which learn best fit parameterized distance metrics (Zhang et al 2022) may succeed on the large-scale SCSGA-MF problem.…”

“…The choice of a specific distance metric for D c can influence the heuristic's performance by constraining it to certain agent and task distributions. To enhance the versatility of our Multiple Distance Metric (MDM) heuristic across a broader range of agent and task distributions (as proposed by (Zhang et al 2022)), we compute and combine a set of n M distance metrics {d…”

A Regression Perspective on Generalized Distance Covariance and the Hilbert–Schmidt Independence Criterion

“…We emphasize that this list is not exhaustive and many more interesting test statistics can be established using the same theory. As an example, the results for generalized linear models [17] may be extended to Bayesian generalized kernel models [70] in the future.…”