output
20122026
most citedLarge-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit

639 citations

Showing cs.LGShow all

16 papers · 1 filter

cs.LG2026

Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition

Huqin Weng, Jiayang Huang, Yimin Wen +3

Self-supervised learning (SSL) shows strong potential for cross-dataset transfer by improving feature representation and generalization. However, its application to EEG-based emoti…

cs.LG2026

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval

Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9

Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriev…

cs.LG2025

Exploring Topological Bias in Heterogeneous Graph Neural Networks

Yihan Zhang

Graph Neural Networks (GNNs) are characterized by their capacity of processing graph-structured data. However, due to the sparsity of labels under semi-supervised learning, they ha…

cs.LG2025★ 1 cited

TRACE: Time SeRies PArameter EffiCient FinE-tuning

Yuze Li, Wei Zhu

We propose an efficient fine-tuning method for time series foundation models, termed TRACE: Time Series Parameter Efficient Fine-tuning. While pretrained time series foundation mod…

cs.LG2025★ 4 cited

Prediction of the Most Fire-Sensitive Point in Building Structures with Differentiable Agents for Thermal Simulators

Yuan Xinjie, Khalid M. Mosalam

Fire safety is crucial for ensuring the stability of building structures, yet evaluating whether a structure meets fire safety requirement is challenging. Fires can originate at an…

cs.LG2024★ 2 cited

Ister: Linear Transformer for Efficient Multivariate Time Series Forecasting

Fanpu Cao, Shu Yang, Zhengjian Chen +2

Transformer-based models have achieved remarkable success in multivariate time series forecasting (MTSF) by capturing long-range dependencies. However, their widespread adoption is…

cs.LG2024★ 2 cited

Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models

Wei Chen, Shian Du, Shigui Li +2

Normalizing Flows (NFs) are widely used in deep generative models for their exact likelihood estimation and efficient sampling. However, they require substantial memory since the l…

cs.LG2024★ 37 cited

Generative Pretrained Hierarchical Transformer for Time Series Forecasting

Zhiding Liu, Jiqian Yang, Mingyue Cheng +2

Recent efforts have been dedicated to enhancing time series forecasting accuracy by introducing advanced network architectures and self-supervised pretraining strategies. Neverthel…

cs.LG2024★ 16 cited

Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network

Lin Chen, Fengli Xu, Nian Li +4

Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are propo…

cs.LG2023★ 4 cited

Data-Aware Gradient Compression for FL in Communication-Constrained Mobile Computing

Rongwei Lu, Yutong Jiang, Yinan Mao +4

Federated Learning (FL) in mobile environments faces significant communication bottlenecks. Gradient compression has proven as an effective solution to this issue, offering substan…

cs.LG2023★ 75 cited

Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design

Zezhou Zhang, Chuanchuan Yang, Yifeng Qin +3

Conventional meta-atom designs rely heavily on researchers' prior knowledge and trial-and-error searches using full-wave simulations, resulting in time-consuming and inefficient pr…

cs.LG2022★ 8 cited

Optical Neural Ordinary Differential Equations

Yun Zhao, Hang Chen, Min Lin +5

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively cascading of network hidden layers r…

cs.LG2021★ 18 cited

Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation

Tiantian Zhang, Xueqian Wang, Bin Liang +1

The powerful learning ability of deep neural networks enables reinforcement learning agents to learn competent control policies directly from continuous environments. In theory, to…

cs.LG2021★ 29 cited

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

Jiawang Bai, Baoyuan Wu, Yong Zhang +3

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the…

cs.LG2020★ 9 cited

Learning from a Complementary-label Source Domain: Theory and Algorithms

Yiyang Zhang, Feng Liu, Zhen Fang +3

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain…

cs.LG2020★ 17 cited

Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation

Li Zhong, Zhen Fang, Feng Liu +3

In the unsupervised open set domain adaptation (UOSDA), the target domain contains unknown classes that are not observed in the source domain. Researchers in this area aim to train…