1.1k citations · 2.5k across the 39 of their papers we have counts for
20 papers · 1 filter
Nonparametric Iterative Machine Teaching
Chen Zhang, Xiaofeng Cao, Weiyang Liu +2
In this paper, we consider the problem of Iterative Machine Teaching (IMT), where the teacher provides examples to the learner iteratively such that the learner can achieve fast co…
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
Weiyang Liu, Longhui Yu, Adrian Weller +1
The neural collapse (NC) phenomenon describes an underlying geometric symmetry for deep neural networks, where both deeply learned features and classifiers converge to a simplex eq…
Human-in-the-Loop Mixup
Katherine M. Collins, Umang Bhatt, Weiyang Liu +4
Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data i…
Iterative Teaching by Data Hallucination
Zeju Qiu, Weiyang Liu, Tim Z. Xiao +5
We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i.e., a pool of…
Continual Learning by Modeling Intra-Class Variation
Longhui Yu, Tianyang Hu, Lanqing Hong +3
It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetti…
Structural Causal 3D Reconstruction
Weiyang Liu, Zhen Liu, Liam Paull +2
This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images. Due to ambiguity and intrinsic ill-posedness, this problem is inheren…
Data-Efficient Learning via Minimizing Hyperspherical Energy
Xiaofeng Cao, Weiyang Liu, Ivor W. Tsang
Deep learning on large-scale data is dominant nowadays. The unprecedented scale of data has been arguably one of the most important driving forces for the success of deep learning.…
Towards Principled Disentanglement for Domain Generalization
Hanlin Zhang, Yi-Fan Zhang, Weiyang Liu +3
A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data, in part due to spurious correlations. To tackle this challenge, we first form…
Iterative Teaching by Label Synthesis
Weiyang Liu, Zhen Liu, Hanchen Wang +3
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous…
Provable Lifelong Learning of Representations
Xinyuan Cao, Weiyang Liu, Santosh S. Vempala
In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transfer…
Pre-training Molecular Graph Representation with 3D Geometry
Shengchao Liu, Hanchen Wang, Weiyang Liu +3
Molecular graph representation learning is a fundamental problem in modern drug and material discovery. Molecular graphs are typically modeled by their 2D topological structures, b…
Learning with Hyperspherical Uniformity
Weiyang Liu, Rongmei Lin, Zhen Liu +3
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation. In order to achieve good generalization on unseen data, a suitabl…
Iterative Graph Self-Distillation
Hanlin Zhang, Shuai Lin, Weiyang Liu +4
Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distilla…
Orthogonal Over-Parameterized Training
Weiyang Liu, Rongmei Lin, Zhen Liu +5
The inductive bias of a neural network is largely determined by the architecture and the training algorithm. To achieve good generalization, how to effectively train a neural netwo…
Angular Visual Hardness
Beidi Chen, Weiyang Liu, Zhiding Yu +4
Recent convolutional neural networks (CNNs) have led to impressive performance but often suffer from poor calibration. They tend to be overconfident, with the model confidence not…
Neural Similarity Learning
Weiyang Liu, Zhen Liu, James M. Rehg +1
Inner product-based convolution has been the founding stone of convolutional neural networks (CNNs), enabling end-to-end learning of visual representation. By generalizing inner pr…
Meta Architecture Search
Albert Shaw, Wei Wei, Weiyang Liu +2
Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks. Unfortunately, the computational cost can make it difficul…
Learning towards Minimum Hyperspherical Energy
Weiyang Liu, Rongmei Lin, Zhen Liu +4
Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on various applications. While the over-parametrization nature in many neural networks re…
Deep Hyperspherical Learning
Weiyang Liu, Yan-Ming Zhang, Xingguo Li +4
Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper ar…
Robust Elastic Net Regression
Weiyang Liu, Rongmei Lin, Meng Yang
We propose a robust elastic net (REN) model for high-dimensional sparse regression and give its performance guarantees (both the statistical error bound and the optimization bound)…