Search Results for author: Yu Song

Found 31 papers, 8 papers with code

A Pure Transformer Pretraining Framework on Text-attributed Graphs

1 code implementation19 Jun 2024 Yu Song, Haitao Mao, Jiachen Xiao, Jingzhe Liu, Zhikai Chen, Wei Jin, Carl Yang, Jiliang Tang, Hui Liu

Pretraining plays a pivotal role in acquiring generalized knowledge from large-scale data, achieving remarkable successes as evidenced by large models in CV and NLP.

Link Prediction Node Classification

Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights

1 code implementation15 Jun 2024 Zhikai Chen, Haitao Mao, Jingzhe Liu, Yu Song, Bingheng Li, Wei Jin, Bahare Fatemi, Anton Tsitsulin, Bryan Perozzi, Hui Liu, Jiliang Tang

First, the absence of a comprehensive benchmark with unified problem settings hinders a clear understanding of the comparative effectiveness and practical value of different text-space GFMs.

Robust Latent Representation Tuning for Image-text Classification

no code implementations10 Jun 2024 Hao Sun, Yu Song

Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation.

Image-text Classification text-classification +1

IB-AdCSCNet:Adaptive Convolutional Sparse Coding Network Driven by Information Bottleneck

no code implementations23 May 2024 He Zou, Meng'en Qin, Yu Song, XiaoHui Yang

In this paper, we introduce IB-AdCSCNet, a deep learning model grounded in information bottleneck theory.

A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model

no code implementations17 May 2024 Mingxiang Fu, Yu Song, Jiameng Lv, Liang Cao, Peng Jia, Nan Li, Xiangru Li, Jifeng Liu, A-Li Luo, Bo Qiu, Shiyin Shen, Liangping Tu, Lili Wang, Shoulin Wei, Haifeng Yang, Zhenping Yi, Zhiqiang Zou

Hence, as an example to present how to overcome the issue, we built a framework for general analysis of galaxy images, based on a large vision model (LVM) plus downstream tasks (DST), including galaxy morphological classification, image restoration, object detection, parameter extraction, and more.

Astronomy Few-Shot Learning +4

Densely Distilling Cumulative Knowledge for Continual Learning

no code implementations16 May 2024 Zenglin Shi, Pei Liu, Tong Su, Yunpeng Wu, Kuien Liu, Yu Song, Meng Wang

It partitions the output logits of the model into dense groups, each corresponding to a task in the task pool.

Continual Learning Knowledge Distillation +1

An Image Quality Evaluation and Masking Algorithm Based On Pre-trained Deep Neural Networks

no code implementations6 May 2024 Peng Jia, Yu Song, Jiameng Lv, Runyu Ning

With the growing amount of astronomical data, there is an increasing need for automated data processing pipelines, which can extract scientific information from observation data without human interventions.

Graph Machine Learning in the Era of Large Language Models (LLMs)

no code implementations23 Apr 2024 Wenqi Fan, Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li

Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.

Few-Shot Learning Knowledge Graphs +1

MEDPNet: Achieving High-Precision Adaptive Registration for Complex Die Castings

no code implementations15 Mar 2024 Yu Du, Yu Song, Ce Guo, Xiaojing Tian, Dong Liu, Ming Cong

Due to their complex spatial structure and diverse geometric features, achieving high-precision and robust point cloud registration for complex Die Castings has been a significant challenge in the die-casting industry.

Computational Efficiency Point Cloud Registration

HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science

1 code implementation12 Oct 2023 Yu Song, Santiago Miret, huan zhang, Bang Liu

We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee).

Language Modelling

Learning on Graphs with Out-of-Distribution Nodes

1 code implementation13 Aug 2023 Yu Song, Donglin Wang

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs.

Graph Attention Graph Learning +1

4D Feet: Registering Walking Foot Shapes Using Attention Enhanced Dynamic-Synchronized Graph Convolutional LSTM Network

no code implementations23 Jul 2023 Farzam Tajdari, Toon Huysmans, Xinhe Yao, Jun Xu, Yu Song

4D scans of dynamic deformable human body parts help researchers have a better understanding of spatiotemporal features.

MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling

1 code implementation14 May 2023 Yu Song, Santiago Miret, Bang Liu

Our experiments in this low-resource training setting show that language models pretrained on scientific text outperform BERT trained on general text.

named-entity-recognition Named Entity Recognition +2

Tailored Multi-Organ Segmentation with Model Adaptation and Ensemble

no code implementations14 Apr 2023 Jiahua Dong, Guohua Cheng, Yue Zhang, Chengtao Peng, Yu Song, Ruofeng Tong, Lanfen Lin, Yen-Wei Chen

Multi-organ segmentation, which identifies and separates different organs in medical images, is a fundamental task in medical image analysis.

Organ Segmentation Segmentation

Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited

1 code implementation24 Mar 2023 Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yunzhu Pan, Yongxin Ni

In fact, this question was answered ten years ago when IDRec beats MoRec by a strong margin in both recommendation accuracy and efficiency.

Recommendation Systems

Impact of Event Encoding and Dissimilarity Measures on Traffic Crash Characterization Based on Sequence of Events

no code implementations22 Feb 2023 Yu Song, Madhav V. Chitturi, David A. Noyce

Two encoding schemes and five optimal matching based dissimilarity measures were compared by evaluating the sequence clustering results.

Clustering

Temporal-spatial Representation Learning Transformer for EEG-based Emotion Recognition

no code implementations16 Nov 2022 Zhe Wang, Yongxiong Wang, Chuanfei Hu, Zhong Yin, Yu Song

Both the temporal dynamics and spatial correlations of Electroencephalogram (EEG), which contain discriminative emotion information, are essential for the emotion recognition.

EEG Emotion Recognition +1

Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers

no code implementations11 Nov 2022 Peng Jia, Ruiqi Sun, Nan Li, Yu Song, Runyu Ning, Hongyan Wei, Rui Luo

We embed prior information of strongly lensed arcs at cluster-scale into the training data through simulation and then train the detection algorithm with simulated images.

A Framework for Multi-stage Bonus Allocation in meal delivery Platform

no code implementations22 Feb 2022 Zhuolin Wu, Li Wang, Fangsheng Huang, Linjun Zhou, Yu Song, Chengpeng Ye, Pengyu Nie, Hao Ren, Jinghua Hao, Renqing He, Zhizhao Sun

The semi-black-box acceptance probability model is employed to forecast the relationship between the bonus allocated to order and its acceptance probability, the Lagrangian dual-based dynamic programming algorithm aims to calculate the empirical Lagrangian multiplier for each allocation stage offline based on the historical data set, and the online allocation algorithm uses the results attained in the offline part to calculate a proper delivery bonus for each order.

Convolutional Networks on Enhanced Message-Passing Graph Improve Semi-Supervised Classification with Few Labels

no code implementations29 Sep 2021 Yu Song, Shan Lu, Dehong Qiu

The key idea is node classification can benefit from various variants of the original graph that are more efficient for message propagation, based upon the assumption that each variant is a potential structure as more nodes are properly labeled.

Graph Embedding Node Classification

Interplay between charge order and superconductivity in the kagome metal KV$_3$Sb$_5$

no code implementations22 Feb 2021 Feng Du, Shuaishuai Luo, Brenden R. Ortiz, Ye Chen, Weiyin Duan, Dongting Zhang, Xin Lu, Stephen D. Wilson, Yu Song, Huiqiu Yuan

Beyond $p\approx10$ GPa, a second superconducting dome emerges with maximum $T_{\rm c}\approx1. 0$ K at $p_{\rm c2}\approx22$ GPa, which becomes fully suppressed at $p\approx28$ GPa.

Superconductivity

Globally Optimal and Efficient Manhattan Frame Estimation by Delimiting Rotation Search Space

no code implementations ICCV 2021 Wuwei Ge, Yu Song, Baichao Zhang, Zehua Dong

This paper proves that the volume of the space that just contains all MF rotations (called the "MFR space") is only 1 / 24 of that of the whole rotation space, and then an exact MFR space is delimited from the rotation space.

Computational Efficiency

Deep Learning-Based Automated Image Segmentation for Concrete Petrographic Analysis

no code implementations21 May 2020 Yu Song, Zilong Huang, Chuanyue Shen, Humphrey Shi, David A Lange

The standard petrography test method for measuring air voids in concrete (ASTM C457) requires a meticulous and long examination of sample phase composition under a stereomicroscope.

Image Segmentation Segmentation +1

Learning from Sparse Datasets: Predicting Concrete's Strength by Machine Learning

no code implementations29 Apr 2020 Boya Ouyang, Yuhai Li, Yu Song, Feishu Wu, Huizi Yu, Yongzhe Wang, Mathieu Bauchy, Gaurav Sant

Here, based on the analysis of a large dataset (>10, 000 observations) of measured compressive strengths from industrially-produced concretes, we compare the ability of select ML algorithms to "learn" how to reliably predict concrete strength as a function of the size of the dataset.

BIG-bench Machine Learning

Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks

no code implementations8 Jan 2019 Yu Song, Shengping Gong

In the preliminary trajectory design of the multi-target rendezvous problem, a model that can quickly estimate the cost of the orbital transfer is essential.

Pop-up SLAM: Semantic Monocular Plane SLAM for Low-texture Environments

no code implementations21 Mar 2017 Shichao Yang, Yu Song, Michael Kaess, Sebastian Scherer

In this paper, we propose real-time monocular plane SLAM to demonstrate that scene understanding could improve both state estimation and dense mapping especially in low-texture environments.

Motion Planning Scene Understanding +1

Laplacian regularized low rank subspace clustering

no code implementations24 Oct 2016 Yu Song, Yiquan Wu

This problem is solved in the low rank subspace clustering model which decomposes the corrupted data matrix as the sum of a clean and self-expressive dictionary plus a matrix of noise and gross errors.

Clustering

Subspace clustering based on low rank representation and weighted nuclear norm minimization

no code implementations12 Oct 2016 Yu Song, Yiquan Wu

Subspace clustering refers to the problem of segmenting a set of data points approximately drawn from a union of multiple linear subspaces.

Clustering

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