Joint Feature and Differentiable k-NN Graph Learning using Dirichlet Energy
Dec 10, 2023
Speakers
Feiping Nie
Speaker · 0 followers
Xuelong Li
Speaker · 0 followers
About
Feature selection (FS) plays an important role in machine learning, which extracts important features and accelerates the learning process. In this paper, we propose a deep FS method that simultaneously conducts feature selection and differentiable k-NN graph learning based on the Dirichlet Energy. The Dirichlet Energy identifies important features by measuring their smoothness on the graph structure, and facilitates the learning of a new graph that reflects the inherent structure in the new feature subspace during the training process using selected features. We employ the Gumbel Softmax technique and the Optimal Transport theory to address the non-differentiability issues of learning discrete FS results and learning k-NN graphs in neural networks, which theoretically makes our model applicable to other graph neural networks.Furthermore, the proposed framework is interpretable, since all modules are designed algorithmically.We validate the effectiveness of our model with extensive experiments on both synthetic and real-world datasets.Feature selection (FS) plays an important role in machine learning, which extracts important features and accelerates the learning process. In this paper, we propose a deep FS method that simultaneously conducts feature selection and differentiable k-NN graph learning based on the Dirichlet Energy. The Dirichlet Energy identifies important features by measuring their smoothness on the graph structure, and facilitates the learning of a new graph that reflects the inherent structure in the new fea…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Lossy Image Compression with Conditional Diffusion Model
Watch later
Ruihan Yang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Connecting Multi-modal Contrastive Representations
Watch later
Zehan Wang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage Data
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
JAB: Joint Adversarial Prompting and Belief Augmentation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
CellMixer: Annotation-free Semantic Cell Segmentation of Heterogeneous Cell Populations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Can LLMs Keep a Secret and Serve Pluralistic Values? On Privacy and Moral Implications of LLMs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%