Search Results for author: Weijun Li

Found 22 papers, 6 papers with code

Operator Feature Neural Network for Symbolic Regression

no code implementations14 Aug 2024 Yusong Deng, Min Wu, Lina Yu, Jingyi Liu, Shu Wei, YanJie Li, Weijun Li

Symbolic regression is a task aimed at identifying patterns in data and representing them through mathematical expressions, generally involving skeleton prediction and constant optimization.

regression Symbolic Regression

DN-CL: Deep Symbolic Regression against Noise via Contrastive Learning

no code implementations21 Jun 2024 Jingyi Liu, YanJie Li, Lina Yu, Min Wu, Weijun Li, Wenqiang Li, Meilan Hao, Yusong Deng, Shu Wei

Traditional methods of symbolic regression, such as genetic programming or deep learning models, aim to find the most fitting expressions for these signals.

Contrastive Learning regression +1

MLLM-SR: Conversational Symbolic Regression base Multi-Modal Large Language Models

no code implementations8 Jun 2024 YanJie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Shu Wei, Yusong Deng

The existing symbolic regression methods directly generate expressions according to the given observation data, and we cannot require the algorithm to generate expressions that meet specific requirements according to the known prior knowledge.

regression Symbolic Regression

Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients

1 code implementation3 Jun 2024 Weijun Li, Qiongkai Xu, Mark Dras

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training.

Closed-form Symbolic Solutions: A New Perspective on Solving Partial Differential Equations

no code implementations23 May 2024 Shu Wei, YanJie Li, Lina Yu, Min Wu, Weijun Li, Meilan Hao, Wenqiang Li, Jingyi Liu, Yusong Deng

Solving partial differential equations (PDEs) in Euclidean space with closed-form symbolic solutions has long been a dream for mathematicians.

Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning

no code implementations9 Apr 2024 YanJie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng

However, its performance is very dependent on the training data and performs poorly on data outside the training set, which leads to poor noise robustness and Versatility of such methods.

Combinatorial Optimization regression +3

MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task

1 code implementation28 Feb 2024 YanJie Li, Jingyi Liu, Weijun Li, Lina Yu, Min Wu, Wenqiang Li, Meilan Hao, Su Wei, Yusong Deng

The SR problem is solved as a pure multi-modal problem, and contrastive learning is also introduced in the training process for modal alignment to facilitate later modal feature fusion.

Combinatorial Optimization Contrastive Learning +2

PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning

1 code implementation26 Jan 2024 Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Li Li, Xin Ning

In this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of FSCIL effectively.

class-incremental learning Few-Shot Class-Incremental Learning +1

PruneSymNet: A Symbolic Neural Network and Pruning Algorithm for Symbolic Regression

1 code implementation25 Jan 2024 Min Wu, Weijun Li, Lina Yu, Wenqiang Li, Jingyi Liu, YanJie Li, Meilan Hao

Therefore, a greedy pruning algorithm is proposed to prune the network into a subnetwork while ensuring the accuracy of data fitting.

Interpretable Machine Learning regression +1

Discovering Mathematical Formulas from Data via GPT-guided Monte Carlo Tree Search

no code implementations24 Jan 2024 YanJie Li, Weijun Li, Lina Yu, Min Wu, Jingyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng

To optimize the trade-off between efficiency and versatility, we introduce SR-GPT, a novel algorithm for symbolic regression that integrates Monte Carlo Tree Search (MCTS) with a Generative Pre-Trained Transformer (GPT).

regression Symbolic Regression

A Novel Paradigm for Neural Computation: X-Net with Learnable Neurons and Adaptable Structure

no code implementations3 Jan 2024 YanJie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng, Liping Zhang, Xiaoli Dong, Hong Qin, Xin Ning, Yugui Zhang, Baoli Lu, Jian Xu, Shuang Li

Multilayer perception (MLP) has permeated various disciplinary domains, ranging from bioinformatics to financial analytics, where their application has become an indispensable facet of contemporary scientific research endeavors.

scientific discovery

MetaSymNet: A Dynamic Symbolic Regression Network Capable of Evolving into Arbitrary Formulations

no code implementations13 Nov 2023 YanJie Li, Weijun Li, Lina Yu, Min Wu, Jinyi Liu, Wenqiang Li, Meilan Hao, Shu Wei, Yusong Deng

To address these issues, we propose MetaSymNet, a novel neural network that dynamically adjusts its structure in real-time, allowing for both expansion and contraction.

regression Symbolic Regression

A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data

1 code implementation24 Sep 2023 Wenqiang Li, Weijun Li, Lina Yu, Min Wu, Linjun Sun, Jingyi Liu, YanJie Li, Shu Wei, Yusong Deng, Meilan Hao

Instead of searching for expressions within a large search space, we explore symbolic networks with various structures, guided by reinforcement learning, and optimize them to identify expressions that better-fitting the data.

Symbolic Regression

A Survey on Few-Shot Class-Incremental Learning

no code implementations17 Apr 2023 Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective.

class-incremental learning Few-Shot Class-Incremental Learning +8

Learning Continuous Face Representation with Explicit Functions

no code implementations25 Oct 2021 Liping Zhang, Weijun Li, Linjun Sun, Lina Yu, Xin Ning, Xiaoli Dong, Jian Xu, Hong Qin

First, we propose an explicit model (EmFace) for human face representation in the form of a finite sum of mathematical terms, where each term is an analytic function element.

Decoder Denoising +1

NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection

no code implementations8 Jan 2021 Liang Xu, Liying Zheng, Weijun Li, Zhenbo Chen, Weishun Song, Yue Deng, Yongzhe Chang, Jing Xiao, Bo Yuan

In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).

Anomaly Detection Time Series +1

Visual-speech Synthesis of Exaggerated Corrective Feedback

no code implementations12 Sep 2020 Yaohua Bu, Weijun Li, Tianyi Ma, Shengqi Chen, Jia Jia, Kun Li, Xiaobo Lu

To provide more discriminative feedback for the second language (L2) learners to better identify their mispronunciation, we propose a method for exaggerated visual-speech feedback in computer-assisted pronunciation training (CAPT).

Speech Synthesis

GmFace: A Mathematical Model for Face Image Representation Using Multi-Gaussian

no code implementations3 Aug 2020 Liping Zhang, Weijun Li, Lina Yu, Xiaoli Dong, Linjun Sun, Xin Ning, Jian Xu, Hong Qin

The GmNet is then designed using Gaussian functions as neurons, with parameters that correspond to each of the parameters of GmFace in order to transform the problem of GmFace parameter solving into a network optimization problem of GmNet.

Face Model

A Local Descriptor with Physiological Characteristic for Finger Vein Recognition

no code implementations16 Apr 2020 Liping Zhang, Weijun Li, Xin Ning

In this work, we propose a finger vein-specific local feature descriptors based physiological characteristic of finger vein patterns, i. e., histogram of oriented physiological Gabor responses (HOPGR), for finger vein recognition.

Finger Vein Recognition

Continuous learning of face attribute synthesis

no code implementations15 Apr 2020 Xin Ning, Shaohui Xu, Xiaoli Dong, Weijun Li, Fangzhe Nan, Yuanzhou Yao

To overcome the limitations of a single network in new attribute synthesis, a continuous learning method for face attribute synthesis is proposed in this work.

Attribute Decoder +1

Cannot find the paper you are looking for? You can Submit a new open access paper.