papers

Publications (48)

cs.LG2026

MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training

Ziyu Zheng, Yaming Yang, Ziyu Guan +2

Multi-domain graph pre-training is a crucial step in constructing foundational graph models with cross-domain generalization capabilities. However, existing methods predominantly r…

q-fin.CP2017

Price Optimisation for New Business

Maissa Tamraz, Yaming Yang

This contribution is concerned with price optimisation of the new business for a non-life product. Due to high competition in the insurance market, non-life insurers are interested…

cs.CL2022

Multimodal Dialogue Response Generation

Qingfeng Sun, Yujing Wang, Can Xu +7

Responsing with image has been recognized as an important capability for an intelligent conversational agent. Yet existing works only focus on exploring the multimodal dialogue mod…

cs.CL2020

LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression

Yihuan Mao, Yujing Wang, Chufan Wu +6

BERT is a cutting-edge language representation model pre-trained by a large corpus, which achieves superior performances on various natural language understanding tasks. However, a…

cs.LG2022

Creating Training Sets via Weak Indirect Supervision

Jieyu Zhang, Bohan Wang, Xiangchen Song +4

Creating labeled training sets has become one of the major roadblocks in machine learning. To address this, recent \emph{Weak Supervision (WS)} frameworks synthesize training label…

cs.LG2025

Discrepancy-Aware Graph Mask Auto-Encoder

Ziyu Zheng, Yaming Yang, Ziyu Guan +2

Masked Graph Auto-Encoder, a powerful graph self-supervised training paradigm, has recently shown superior performance in graph representation learning. Existing works typically re…

cs.LG2022

Graph Pointer Neural Networks

Tianmeng Yang, Yujing Wang, Zhihan Yue +3

Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invarian…

cs.LG2021

Evolving Attention with Residual Convolutions

Yujing Wang, Yaming Yang, Jiangang Bai +6

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model…

cs.LG2023

Pseudo Contrastive Learning for Graph-based Semi-supervised Learning

Weigang Lu, Ziyu Guan, Wei Zhao +5

Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions…

cs.CV2022

Privacy-preserving Online AutoML for Domain-Specific Face Detection

Chenqian Yan, Yuge Zhang, Quanlu Zhang +4

Despite the impressive progress of general face detection, the tuning of hyper-parameters and architectures is still critical for the performance of a domain-specific face detector…

cs.CL2022

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation

Jiazhan Feng, Qingfeng Sun, Can Xu +5

Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to bett…

cs.SI2025

Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs

Ziyu Zheng, Yaming Yang, Ziyu Guan +2

Real-world networks usually have a property of node heterophily, that is, the connected nodes usually have different features or different labels. This heterophily issue has been e…

cs.LG2023

Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering

Yaming Yang, Ziyu Guan, Zhe Wang +4

Recent self-supervised pre-training methods on Heterogeneous Information Networks (HINs) have shown promising competitiveness over traditional semi-supervised Heterogeneous Graph N…

cs.CV2022

Entropy Induced Pruning Framework for Convolutional Neural Networks

Yiheng Lu, Ziyu Guan, Yaming Yang +3

Structured pruning techniques have achieved great compression performance on convolutional neural networks for image classification task. However, the majority of existing methods…

cs.IT2024

Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels

Guochen Ma, Xiaopeng Jiao, Jianjun Mu +2

Marker code is an effective coding scheme to protect data from insertions and deletions. It has potential applications in future storage systems, such as DNA storage and racetrack…

cs.LG2025

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

Yaming Yang, Dilxat Muhtar, Yelong Shen +9

Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. Ho…

cs.LG2019

TextNAS: A Neural Architecture Search Space tailored for Text Representation

Yujing Wang, Yaming Yang, Yiren Chen +7

Learning text representation is crucial for text classification and other language related tasks. There are a diverse set of text representation networks in the literature, and how…

cs.LG2024

Token-level Proximal Policy Optimization for Query Generation

Yichen Ouyang, Lu Wang, Fangkai Yang +13

Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Langua…

cs.CL2021

Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees

Jiangang Bai, Yujing Wang, Yiren Chen +4

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information h…

cs.IR2026

TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation

Ziyu Zheng, Zhengshun Du, Yaming Yang +5

The paper proposes TopoGR, a generative recommendation framework that uses binary semantic IDs with explicit Hamming geometry to preserve the latent topology of item representation…

#generative recommendation#semantic ids#hamming topology#binary encoding
cs.IR2022

Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation

Yankai Chen, Yaming Yang, Yujing Wang +3

To alleviate data sparsity and cold-start problems of traditional recommender systems (RSs), incorporating knowledge graphs (KGs) to supplement auxiliary information has attracted…

cs.LG2023

Convolution-enhanced Evolving Attention Networks

Yujing Wang, Yaming Yang, Zhuo Li +7

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series anal…

cs.IR2025

Direct Preference Optimization for LLM-Enhanced Recommendation Systems

Chao Sun, Yaobo Liang, Yaming Yang +3

Large Language Models (LLMs) have exhibited remarkable performance across a wide range of domains, motivating research into their potential for recommendation systems. Early effort…

cs.LG2025

ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs

Weigang Lu, Ziyu Guan, Wei Zhao +5

GNN-to-MLP (G2M) methods have emerged as a promising approach to accelerate Graph Neural Networks (GNNs) by distilling their knowledge into simpler Multi-Layer Perceptrons (MLPs).…

cs.LG2024

AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification

Weigang Lu, Ziyu Guan, Wei Zhao +4

Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio in the image domain. Recently, the concept…

cs.CL2024

StreamAdapter: Efficient Test Time Adaptation from Contextual Streams

Dilxat Muhtar, Yelong Shen, Yaming Yang +11

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances…

cs.LG2021

WRENCH: A Comprehensive Benchmark for Weak Supervision

Jieyu Zhang, Yue Yu, Yinghao Li +4

Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple pot…

cs.CV2022

Learning to Rank Ace Neural Architectures via Normalized Discounted Cumulative Gain

Yuge Zhang, Quanlu Zhang, Li Lyna Zhang +4

One of the key challenges in Neural Architecture Search (NAS) is to efficiently rank the performances of architectures. The mainstream assessment of performance rankers uses rankin…

cs.LG2021

Interpretable and Efficient Heterogeneous Graph Convolutional Network

Yaming Yang, Ziyu Guan, Jianxin Li +3

Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes in graphs. However, regarding Heterogeneous Inform…

cs.AI2025

Unsupervised Entity Alignment Based on Personalized Discriminative Rooted Tree

Yaming Yang, Zhe Wang, Ziyu Guan +3

Entity Alignment (EA) is to link potential equivalent entities across different knowledge graphs (KGs). Most existing EA methods are supervised as they require the supervision of s…

cs.CL2025

SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels

Guancheng Du, Yong Hu, Wenqing Wang +2

Large Language Models (LLMs) have shown significant progress, but understanding long and complex documents remains challenging. Many long-context benchmarks have been proposed, but…

cs.SI2026

Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment

Ziyu Zheng, Yaming Yang, Zhe Wang +2

While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challe…

cs.LG2024

AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation

Weigang Lu, Ziyu Guan, Wei Zhao +1

Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical…

cs.IR2022

Learning Multi-granularity User Intent Unit for Session-based Recommendation

Jiayan Guo, Yaming Yang, Xiangchen Song +4

Session-based recommendation aims to predict a user's next action based on previous actions in the current session. The major challenge is to capture authentic and complete user pr…

cs.CL2020

AutoADR: Automatic Model Design for Ad Relevance

Yiren Chen, Yaming Yang, Hong Sun +7

Large-scale pre-trained models have attracted extensive attention in the research community and shown promising results on various tasks of natural language processing. However, th…

cs.SI2025

H-NeiFi: Non-Invasive and Consensus-Efficient Multi-Agent Opinion Guidance

Shijun Guo, Haoran Xu, Yaming Yang +4

The openness of social media enables the free exchange of opinions, but it also presents challenges in guiding opinion evolution towards global consensus. Existing methods often di…

cs.LG2024

SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

Weigang Lu, Yibing Zhan, Binbin Lin +6

Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing…

cs.CL2025

Aligning Multiple Knowledge Graphs in a Single Pass

Yaming Yang, Zhe Wang, Ziyu Guan +5

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods m…

cs.IR2023

Self-Supervised Multi-Modal Sequential Recommendation

Kunzhe Song, Qingfeng Sun, Can Xu +2

With the increasing development of e-commerce and online services, personalized recommendation systems have become crucial for enhancing user satisfaction and driving business reve…

cs.LG2022

Binary Classification with Positive Labeling Sources

Jieyu Zhang, Yujing Wang, Yaming Yang +2

To create a large amount of training labels for machine learning models effectively and efficiently, researchers have turned to Weak Supervision (WS), which uses programmatic label…

cs.LG2021

How Does Supernet Help in Neural Architecture Search?

Yuge Zhang, Quanlu Zhang, Yaming Yang

Weight sharing, as an approach to speed up architecture performance estimation has received wide attention. Instead of training each architecture separately, weight sharing builds…

cs.CL2026

SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

Zhenliang Zhang, Wenqing Wang, Yong Hu +4

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token c…

cs.LG2020

DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang +17

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing pro…

cs.LG2023

NodeMixup: Tackling Under-Reaching for Graph Neural Networks

Weigang Lu, Ziyu Guan, Wei Zhao +2

Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. However, due to the uneven location distribution of labeled…

cs.LG2020

Deeper Insights into Weight Sharing in Neural Architecture Search

Yuge Zhang, Zejun Lin, Junyang Jiang +5

With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scrat…

cs.CL2026

Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph

Ziyu Zheng, Yaming Yang, Ziyu Guan +3

The ``pre-train, prompt" paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the NLP domain to the graph domain and ha…

cs.IR2025

Dynamic Network-Based Two-Stage Time Series Forecasting for Affiliate Marketing

Zhe Wang, Yaming Yang, Ziyu Guan +4

In recent years, affiliate marketing has emerged as a revenue-sharing strategy where merchants collaborate with promoters to promote their products. It not only increases product e…

cs.LG2024

You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning

Tianmeng Yang, Jiahao Meng, Min Zhou +4

Recent research on the robustness of Graph Neural Networks (GNNs) under noises or attacks has attracted great attention due to its importance in real-world applications. Most previ…