2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDMLSP-14.3
Paper Title ADAPTIVE FEATURE WEIGHT LEARNING FOR ROBUST CLUSTERING PROBLEM WITH SPARSE CONSTRAINT
Authors Feiping Nie, Wei Chang, Xuelong Li, Northwestern Polytechnical University, China; Jin Xu, Gongfu Li, Tencent Inc, China
SessionMLSP-14: Learning Algorithms 1
LocationGather.Town
Session Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Poster
Topic Machine Learning for Signal Processing: [MLR-LEAR] Learning theory and algorithms
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Clustering task has been greatly developed in recent years like partition-based and graph-based methods. However, in terms of improving robustness, most existing algorithms only focus on noise and outliers between data, while ignoring the noise in feature space. To deal with this situation, we propose a novel weight learning mechanism to adaptively reweight each feature in the data. Combining with the clustering task, we further propose a robust fuzzy K-Means model based on the auto-weighted feature learning, which can effectively reduce the proportion of noisy features. Besides, a regularization term is introduced into our model to make the sample-to-clusters memberships of each sample have suitable sparsity. Specifically, we design an effective strategy to determine the value of the regularization parameter. The experimental results on both synthetic and real-world datasets demonstrate that our model has better performance than other classical algorithms.