Search Results for author:
Found 11 papers, 8 papers with code
Ordering-Based Causal Discovery for Linear and Nonlinear Relations
Identifying causal relations from purely observational data typically requires additional assumptions on relations and/or noise.
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
Time series forecasting typically needs to address non-stationary data with evolving trend and seasonal patterns.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
Multi-View Graph Representation Learning Beyond Homophily
However, partially due to the irregular non-Euclidean data in graphs, the pretext tasks are generally designed under homophily assumptions and cornered in the low-frequency signals, which results in significant loss of other signals, especially high-frequency signals widespread in graphs with heterophily.
Data Imputation with Iterative Graph Reconstruction
Instead of treating all samples equally, we introduce the concept: ``friend networks" to represent different relations among samples.
A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision
Guided by the integrated information from the multi-self-supervised learning model, a batch-attention mechanism is designed to generate feature weights according to batch-based feature selection patterns to alleviate the impacts introduced by a handful of noisy data.
An Embedded Feature Selection Framework for Control
Reducing sensor requirements while keeping optimal control performance is crucial to many industrial control applications to achieve robust, low-cost, and computation-efficient controllers.
Graph Representation Learning Beyond Node and Homophily
Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding.
Pair-view Unsupervised Graph Representation Learning
Low-dimension graph embeddings have proved extremely useful in various downstream tasks in large graphs, e. g., link-related content recommendation and node classification tasks, etc.
AFS: An Attention-based mechanism for Supervised Feature Selection
AFS consists of two detachable modules: an at-tention module for feature weight generation and a learning module for the problem modeling.
The Missing Ones: Key Ingredients Towards Effective Ambient Assisted Living Systems
Challenges in increasing the human participation in ambient assisted living are discussed in this paper and solutions to meet those challenges are also proposed.
