Search Results for author:
Found 10 papers, 3 papers with code
Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models
The typical paradigm is to pre-train a big deep learning model on large-scale data sets, and then fine-tune the model on small task-specific data sets for downstream tasks.
Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs.
Open-world Semi-supervised Novel Class Discovery
Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in the unlabeled set.
An Interpretable Neuron Embedding for Static Knowledge Distillation
The visualization of semantic vectors allows for a qualitative explanation of the neural network.
A Subword Guided Neural Word Segmentation Model for Sindhi
The word segmentation is a fundamental and inevitable prerequisite for many languages.
Revisiting Representation Degeneration Problem in Language Modeling
They call it the representation degeneration problem and propose a cosine regularization to solve it.
An Online Semantic-enhanced Dirichlet Model for Short Text Stream Clustering
Clustering short text streams is a challenging task due to its unique properties: infinite length, sparse data representation and cluster evolution.
Large-scale Multi-view Subspace Clustering in Linear Time
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years.
Learning in High-Dimensional Multimedia Data: The State of the Art
Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis.
Graph Clustering with Density-Cut
We demonstrate that our method has several attractive benefits: (a) Dcut provides an intuitive criterion to evaluate the goodness of a graph clustering in a more natural and precise way; (b) Built upon the density-connected tree, Dcut allows identifying the meaningful graph clusters of densely connected vertices efficiently; (c) The density-connected tree provides a connectivity map of vertices in a graph from a local density perspective.
Social and Information Networks Physics and Society
