1.4k citations · 4.2k across the 73 of their papers we have counts for
32 papers · 1 filter
SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts
Shanglin Li, Shiwen Chu, Okan Koç +5
Electroencephalography (EEG) based brain-computer interfaces enable direct brain-to-device communication for applications such as rehabilitation and communication. However, their p…
EEG-Based Multimodal Learning via Hyperbolic Mixture-of-Curvature Experts
Runhe Zhou, Shanglin Li, Guanxiang Huang +5
Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential…
Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner
Wei Chen, Yubing Wu, Junmei Yang +5
Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they…
Nonconvex Latent Optimally Partitioned Block-Sparse Recovery via Log-Sum and Minimax Concave Penalties
Takanobu Furuhashi, Hiroki Kuroda, Masahiro Yukawa +3
We propose two nonconvex regularization methods, LogLOP-l2/l1 and AdaLOP-l2/l1, for recovering block-sparse signals with unknown block partitions. These methods address the underes…
HEEGNet: Hyperbolic Embeddings for EEG
Shanglin Li, Shiwen Chu, Okan Koç +4
Electroencephalography (EEG)-based brain-computer interfaces facilitate direct communication with a computer, enabling promising applications in human-computer interactions. Howeve…
Efficient Low Rank Attention for Long-Context Inference in Large Language Models
Tenghui Li, Guoxu Zhou, Xuyang Zhao +2
As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Exis…
Diffusion Bridge Variational Inference for Deep Gaussian Processes
Jian Xu, Qibin Zhao, John Paisley +1
Deep Gaussian processes (DGPs) enable expressive hierarchical Bayesian modeling but pose substantial challenges for posterior inference, especially over inducing variables. Denoisi…
Neural Bridge Processes
Jian Xu, Yican Liu, Delu Zeng +2
Learning stochastic functions from partially observed context-target pairs requires models that are expressive, uncertainty-aware, and strongly conditioned on inputs. Neural Diffus…
WEEP: A Differentiable Nonconvex Sparse Regularizer via Weakly-Convex Envelope
Takanobu Furuhashi, Hidekata Hontani, Qibin Zhao +1
Sparse regularization is fundamental in signal processing and feature extraction but often relies on non-differentiable penalties, conflicting with gradient-based optimizers. We pr…
NeuronSeek: On Stability and Expressivity of Task-driven Neurons
Hanyu Pei, Jing-Xiao Liao, Qibin Zhao +4
Drawing inspiration from our human brain that designs different neurons for different tasks, recent advances in deep learning have explored modifying a network's neurons to develop…
Domain-Aware Tensor Network Structure Search
Giorgos Iacovides, Wuyang Zhou, Chao Li +2
Tensor networks (TNs) provide efficient representations of high-dimensional data, yet identification of the optimal TN structures, the so called tensor network structure search (TN…
Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation
Guang Lin, Duc Thien Nguyen, Zerui Tao +3
Deep neural networks are known to be vulnerable to well-designed adversarial attacks. Although numerous defense strategies have been proposed, many are tailored to the specific att…
Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models
Zerui Tao, Yuhta Takida, Naoki Murata +2
Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptat…
Scalable Bayesian Tensor Ring Factorization for Multiway Data Analysis
Zerui Tao, Toshihisa Tanaka, Qibin Zhao
Tensor decompositions play a crucial role in numerous applications related to multi-way data analysis. By employing a Bayesian framework with sparsity-inducing priors, Bayesian Ten…
Jacobian Regularizer-based Neural Granger Causality
Wanqi Zhou, Shuanghao Bai, Shujian Yu +2
With the advancement of neural networks, diverse methods for neural Granger causality have emerged, which demonstrate proficiency in handling complex data, and nonlinear relationsh…
tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
Junhua Zeng, Chao Li, Zhun Sun +2
Tensor networks are efficient for extremely high-dimensional representation, but their model selection, known as tensor network structure search (TN-SS), is a challenging problem.…
Efficient Nonparametric Tensor Decomposition for Binary and Count Data
Zerui Tao, Toshihisa Tanaka, Qibin Zhao
In numerous applications, binary reactions or event counts are observed and stored within high-order tensors. Tensor decompositions (TDs) serve as a powerful tool to handle such hi…
SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG
Reinmar J Kobler, Jun-ichiro Hirayama, Qibin Zhao +1
Electroencephalography (EEG) provides access to neuronal dynamics non-invasively with millisecond resolution, rendering it a viable method in neuroscience and healthcare. However,…
Efficient Tensor Robust PCA under Hybrid Model of Tucker and Tensor Train
Yuning Qiu, Guoxu Zhou, Zhenhao Huang +2
Tensor robust principal component analysis (TRPCA) is a fundamental model in machine learning and computer vision. Recently, tensor train (TT) decomposition has been verified effec…
Fast Hypergraph Regularized Nonnegative Tensor Ring Factorization Based on Low-Rank Approximation
Xinhai Zhao, Yuyuan Yu, Guoxu Zhou +2
For the high dimensional data representation, nonnegative tensor ring (NTR) decomposition equipped with manifold learning has become a promising model to exploit the multi-dimensio…
On the Memory Mechanism of Tensor-Power Recurrent Models
Hejia Qiu, Chao Li, Ying Weng +3
Tensor-power (TP) recurrent model is a family of non-linear dynamical systems, of which the recurrence relation consists of a p-fold (a.k.a., degree-p) tensor product. Despite such…
Learning from Incomplete Features by Simultaneous Training of Neural Networks and Sparse Coding
Cesar F. Caiafa, Ziyao Wang, Jordi Solé-Casals +1
In this paper, the problem of training a classifier on a dataset with incomplete features is addressed. We assume that different subsets of features (random or structured) are avai…
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
Paul Pu Liang, Zhun Liu, Yao-Hung Hubert Tsai +3
There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, natural…
Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation
Giuseppe G. Calvi, Ahmad Moniri, Mahmoud Mahfouz +2
This work aims to help resolve the two main stumbling blocks in the application of Deep Neural Networks (DNNs), that is, the exceedingly large number of trainable parameters and th…