513 citations · 1.8k across the 73 of their papers we have counts for
24 papers · 1 filter
Rethinking State Disentanglement in Causal Reinforcement Learning
Haiyao Cao, Zhen Zhang, Panpan Cai +7
One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical supp…
Towards Identifiable Latent Additive Noise Models
Yuhang Liu, Zhen Zhang, Dong Gong +6
Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing…
Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning
Yuhang Liu, Zhen Zhang, Dong Gong +6
Directed Acyclic Graphs (DAGs) are a standard tool in causal modeling, but their suitability for capturing the complexity of large-scale multimodal data is questionable. In practic…
Identifiable Latent Polynomial Causal Models Through the Lens of Change
Yuhang Liu, Zhen Zhang, Dong Gong +5
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of id…
A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi
Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the de…
Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
Bao Gia Doan, Ehsan Abbasnejad, Javen Qinfeng Shi +1
We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network…
Truncated Matrix Power Iteration for Differentiable DAG Learning
Zhen Zhang, Ignavier Ng, Dong Gong +5
Recovering underlying Directed Acyclic Graph (DAG) structures from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization prob…
Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation
Yuhang Liu, Zhen Zhang, Dong Gong +5
Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain by leveraging both the labeled data from multip…
Identifying Weight-Variant Latent Causal Models
Yuhang Liu, Zhen Zhang, Dong Gong +5
The task of causal representation learning aims to uncover latent higher-level causal variables that affect lower-level observations. Identifying the true latent causal variables f…
Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning
Dong Gong, Qingsen Yan, Yuhang Liu +2
Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL ap…
Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors
Alireza Abedin, Mahsa Ehsanpour, Qinfeng Shi +2
Wearables are fundamental to improving our understanding of human activities, especially for an increasing number of healthcare applications from rehabilitation to fine-grained gai…
SparseSense: Human Activity Recognition from Highly Sparse Sensor Data-streams Using Set-based Neural Networks
Alireza Abedin, S. Hamid Rezatofighi, Qinfeng Shi +1
Batteryless or so called passive wearables are providing new and innovative methods for human activity recognition (HAR), especially in healthcare applications for older people. Pa…
Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning
Ehsan Abbasnejad, Iman Abbasnejad, Qi Wu +2
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. On…
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables
Alireza Abedin Varamin, Ehsan Abbasnejad, Qinfeng Shi +2
Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing. Most recent research in the field…
Variational Bayesian Dropout with a Hierarchical Prior
Yuhang Liu, Wenyong Dong, Lei Zhang +2
Variational dropout (VD) is a generalization of Gaussian dropout, which aims at inferring the posterior of network weights based on a log-uniform prior on them to learn these weigh…
Bayesian Conditional Generative Adverserial Networks
M. Ehsan Abbasnejad, Qinfeng Shi, Iman Abbasnejad +2
Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input to a sample that the discriminator seeks to…
Learning from Imbalanced Multiclass Sequential Data Streams Using Dynamically Weighted Conditional Random Fields
Roberto L. Shinmoto Torres, Damith C. Ranasinghe, Qinfeng Shi +1
The present study introduces a method for improving the classification performance of imbalanced multiclass data streams from wireless body worn sensors. Data imbalance is an inher…
Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Mingkui Tan, Shijie Xiao, Junbin Gao +3
Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR). Solving this problem directly can b…
Worst-Case Linear Discriminant Analysis as Scalable Semidefinite Feasibility Problems
Hui Li, Chunhua Shen, Anton van den Hengel +1
In this paper, we propose an efficient semidefinite programming (SDP) approach to worst-case linear discriminant analysis (WLDA). Compared with the traditional LDA, WLDA considers…
A Hybrid Loss for Multiclass and Structured Prediction
Qinfeng Shi, Mark Reid, Tiberio Caetano +2
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hi…
Inductive Hashing on Manifolds
Fumin Shen, Chunhua Shen, Qinfeng Shi +2
Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these meth…
RandomBoost: Simplified Multi-class Boosting through Randomization
Sakrapee Paisitkriangkrai, Chunhua Shen, Qinfeng Shi +1
We propose a novel boosting approach to multi-class classification problems, in which multiple classes are distinguished by a set of random projection matrices in essence. The appr…
Is margin preserved after random projection?
Qinfeng Shi, Chunhua Shen, Rhys Hill +1
Random projections have been applied in many machine learning algorithms. However, whether margin is preserved after random projection is non-trivial and not well studied. In this…
Conditional Random Fields and Support Vector Machines: A Hybrid Approach
Qinfeng Shi, Mark D. Reid, Tiberio Caetano
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of log loss for Conditional Random Fields (CRFs) and a multiclass hing…