Publications (67)
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
Haoyu Han, Li Ma, Yu Wang +9
Retrieval-Augmented Generation (RAG) improves large language models (LLMs) by retrieving relevant information from external sources and has been widely adopted for text-based tasks…
A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
Yu Song, Zhigang Hua, Harry Shomer +4
Link Prediction (LP) is a critical task in graph machine learning. While Graph Neural Networks (GNNs) have significantly advanced LP performance recently, existing methods face key…
Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation
Yitong Pang, Lingfei Wu, Qi Shen +6
Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition pattern…
Automatic Product Copywriting for E-Commerce
Xueying Zhang, Yanyan Zou, Hainan Zhang +10
Product copywriting is a critical component of e-commerce recommendation platforms. It aims to attract users' interest and improve user experience by highlighting product character…
Memory-efficient Embedding for Recommendations
Xiangyu Zhao, Haochen Liu, Hui Liu +6
Practical large-scale recommender systems usually contain thousands of feature fields from users, items, contextual information, and their interactions. Most of them empirically al…
Sequential Search with Off-Policy Reinforcement Learning
Dadong Miao, Yanan Wang, Guoyu Tang +6
Recent years have seen a significant amount of interests in Sequential Recommendation (SR), which aims to understand and model the sequential user behaviors and the interactions be…
VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
Dongqi Fu, Zhigang Hua, Yan Xie +7
Graph transformer has been proven as an effective graph learning method for its adoption of attention mechanism that is capable of capturing expressive representations from complex…
Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
Jelena Markovic-Voronov, Wenhui Zhu, Bo Long +5
We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-l…
Query Rewriting via Cycle-Consistent Translation for E-Commerce Search
Yiming Qiu, Kang Zhang, Han Zhang +5
Nowadays e-commerce search has become an integral part of many people's shopping routines. One critical challenge in today's e-commerce search is the semantic matching problem wher…
Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
Bo Long, Deepak Agarwal, Jelena Markovic-Voronov +2
The Transformer is the foundational building block of modern AI, yet offers no principled handling of \emph{uncertainty}, which is prevalent in real applications: cold-start tokens…
Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks
Hanning Gao, Lingfei Wu, Hongyun Zhang +4
Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence mod…
Multi-behavior Graph Contextual Aware Network for Session-based Recommendation
Qi Shen, Lingfei Wu, Yitong Pang +4
Predicting the next interaction of a short-term sequence is a challenging task in session-based recommendation (SBR).Multi-behavior session recommendation considers session sequenc…
InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
Zhichen Zeng, Xiaolong Liu, Mengyue Hang +25
Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous informati…
Constructing Contrastive samples via Summarization for Text Classification with limited annotations
Yangkai Du, Tengfei Ma, Lingfei Wu +4
Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct…
Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking
Ilqar Ramazanli, Hamid Eghbalzadeh, Xiaoyi Liu +6
Perturbation-based regularization techniques address many challenges in industrial-scale large models, particularly with sparse labels, and emphasize consistency and invariance for…
Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization
Xuxing Chen, Yun He, Jiayi Xu +9
In machine learning, the goal of multi-task learning (MTL) is to optimize multiple objectives together. Recent works, for example, Multiple Gradient Descent Algorithm (MGDA) and it…
DSGPT: Domain-Specific Generative Pre-Training of Transformers for Text Generation in E-commerce Title and Review Summarization
Xueying Zhang, Yunjiang Jiang, Yue Shang +5
We propose a novel domain-specific generative pre-training (DS-GPT) method for text generation and apply it to the product titleand review summarization problems on E-commerce mobi…
Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes
Yunjiang Jiang, Han Zhang, Yiming Qiu +3
Product quantization (PQ) coupled with a space rotation, is widely used in modern approximate nearest neighbor (ANN) search systems to significantly compress the disk storage for e…
Automatic Controllable Product Copywriting for E-Commerce
Xiaojie Guo, Qingkai Zeng, Meng Jiang +3
Automatic product description generation for e-commerce has witnessed significant advancement in the past decade. Product copywriting aims to attract users' interest and improve us…
How to Make LMs Strong Node Classifiers?
Zhe Xu, Kaveh Hassani, Si Zhang +7
Language Models (LMs) are increasingly challenging the dominance of domain-specific models, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs), in graph learning tas…
Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search
Ziyang Liu, Zhaomeng Cheng, Yunjiang Jiang +5
Result relevance prediction is an essential task of e-commerce search engines to boost the utility of search engines and ensure smooth user experience. The last few years eyewitnes…
Efficient Neural Query Auto Completion
Sida Wang, Weiwei Guo, Huiji Gao +1
Query Auto Completion (QAC), as the starting point of information retrieval tasks, is critical to user experience. Generally it has two steps: generating completed query candidates…
Quantizing Intent: Cross-Domain Semantic IDs from Organic Activity for Industrial Ranking
Julie Choi, Haoran Ye, Zhiwei Ding +3
Ads click-through rate (CTR) prediction is constrained by sparse user supervision: most users engage with ads infrequently while generating dense behavioral evidence in organic sur…
Learning Graph Quantized Tokenizers
Limei Wang, Kaveh Hassani, Si Zhang +7
Transformers serve as the backbone architectures of Foundational Models, where domain-specific tokenizers allow them to adapt to various domains. Graph Transformers (GTs) have rece…
Deep Search Query Intent Understanding
Xiaowei Liu, Weiwei Guo, Huiji Gao +1
Understanding a user's query intent behind a search is critical for modern search engine success. Accurate query intent prediction allows the search engine to better serve the user…
Learning Multi-Stage Multi-Grained Semantic Embeddings for E-Commerce Search
Binbin Wang, Mingming Li, Zhixiong Zeng +5
Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) metho…
SearchGCN: Powering Embedding Retrieval by Graph Convolution Networks for E-Commerce Search
Xinlin Xia, Shang Wang, Han Zhang +5
Graph convolution networks (GCN), which recently becomes new state-of-the-art method for graph node classification, recommendation and other applications, has not been successfully…
Feeding What You Need by Understanding What You Learned
Xiaoqiang Wang, Bang Liu, Fangli Xu +3
Machine Reading Comprehension (MRC) reveals the ability to understand a given text passage and answer questions based on it. Existing research works in MRC rely heavily on large-si…
Scenario-based Multi-product Advertising Copywriting Generation for E-Commerce
Xueying Zhang, Kai Shen, Chi Zhang +5
In this paper, we proposed an automatic Scenario-based Multi-product Advertising Copywriting Generation system (SMPACG) for E-Commerce, which has been deployed on a leading Chinese…
Reducing Flipping Errors in Deep Neural Networks
Xiang Deng, Yun Xiao, Bo Long +1
Deep neural networks (DNNs) have been widely applied in various domains in artificial intelligence including computer vision and natural language processing. A DNN is typically tra…
APOLLO: SGD-like Memory, AdamW-level Performance
Hanqing Zhu, Zhenyu Zhang, Wenyan Cong +7
Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-e…
Improving Sequential Recommendation Consistency with Self-Supervised Imitation
Xu Yuan, Hongshen Chen, Yonghao Song +4
Most sequential recommendation models capture the features of consecutive items in a user-item interaction history. Though effective, their representation expressiveness is still h…
Deep Natural Language Processing for LinkedIn Search Systems
Weiwei Guo, Xiaowei Liu, Sida Wang +6
Many search systems work with large amounts of natural language data, e.g., search queries, user profiles and documents, where deep learning based natural language processing techn…
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
Dong Chen, Lingfei Wu, Siliang Tang +3
Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner is prone to overfitting since the…
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Mingfu Liang, Xi Liu, Rong Jin +104
Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommenda…
SPAR: Personalized Content-Based Recommendation via Long Engagement Attention
Chiyu Zhang, Yifei Sun, Jun Chen +7
Leveraging users' long engagement histories is essential for personalized content recommendations. The success of pretrained language models (PLMs) in NLP has led to their use in e…
Retrieval-Augmented Generation with Graphs (GraphRAG)
Haoyu Han, Yu Wang, Harry Shomer +15
Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from…
Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce
Juan Gong, Zhenlin Chen, Chaoyi Ma +7
Ranking model plays an essential role in e-commerce search and recommendation. An effective ranking model should give a personalized ranking list for each user according to the use…
Context-Consistent Semantic Image Editing with Style-Preserved Modulation
Wuyang Luo, Su Yang, Hong Wang +2
Semantic image editing utilizes local semantic label maps to generate the desired content in the edited region. A recent work borrows SPADE block to achieve semantic image editing.…
Deep Natural Language Processing for LinkedIn Search
Weiwei Guo, Xiaowei Liu, Sida Wang +7
Many search systems work with large amounts of natural language data, e.g., search queries, user profiles, and documents. Building a successful search system requires a thorough un…
GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
Yu Song, Zhigang Hua, Yan Xie +3
Self-supervised learning (SSL) has shown great promise in graph representation learning. However, most existing graph SSL methods are developed and evaluated under a single-dataset…
Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learning
Yangkai Du, Tengfei Ma, Lingfei Wu +4
Towards real-world information extraction scenario, research of relation extraction is advancing to document-level relation extraction(DocRE). Existing approaches for DocRE aim to…
Graph Neural Networks for Natural Language Processing: A Survey
Lingfei Wu, Yu Chen, Kai Shen +5
Deep learning has become the dominant approach in coping with various tasks in Natural LanguageProcessing (NLP). Although text inputs are typically represented as a sequence of tok…
Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index
Han Zhang, Hongwei Shen, Yiming Qiu +6
Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches…
Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation
Yiming Zhang, Lingfei Wu, Qi Shen +5
Conversational recommendation system (CRS) is able to obtain fine-grained and dynamic user preferences based on interactive dialogue. Previous CRS assumes that the user has a clear…
Intelligent Online Selling Point Extraction for E-Commerce Recommendation
Xiaojie Guo, Shugen Wang, Hanqing Zhao +8
In the past decade, automatic product description generation for e-commerce have witnessed significant advancement. As the services provided by e-commerce platforms become diverse,…
Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search
Yiming Qiu, Chenyu Zhao, Han Zhang +7
BERT-style models pre-trained on the general corpus (e.g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: qu…
R1-Ranker: Teaching LLM Rankers to Reason
Tao Feng, Zhigang Hua, Zijie Lei +4
Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tas…
Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
Kai Shen, Lingfei Wu, Siliang Tang +4
The visual question generation (VQG) task aims to generate human-like questions from an image and potentially other side information (e.g. answer type). Previous works on VQG fall…
DeText: A Deep Text Ranking Framework with BERT
Weiwei Guo, Xiaowei Liu, Sida Wang +8
Ranking is the most important component in a search system. Mostsearch systems deal with large amounts of natural language data,hence an effective ranking system requires a deep un…
A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems
Hamid Eghbalzadeh, Yang Wang, Rui Li +9
Industrial ads ranking systems conventionally rely on labeled impression data, which leads to challenges such as overfitting, slower incremental gain from model scaling, and biases…
Preference Discerning with LLM-Enhanced Generative Retrieval
Fabian Paischer, Liu Yang, Linfeng Liu +12
In sequential recommendation, models recommend items based on user's interaction history. To this end, current models usually incorporate information such as item descriptions and…
Ultrawide color gamut single-pixel dynamic color manipulation based on yarn muscles-graphene MEMS
Hongxu Li, Bo Long, Tao Wang +2
This work investigated the single pixel color modulation in a composite structure of yarn muscles graphene mechanical system and photonic crystal multimode microcavity. The positio…
Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation
Yiming Zhang, Lingfei Wu, Qi Shen +5
Social recommendation based on social network has achieved great success in improving the performance of recommendation system. Since social network (user-user relations) and user-…
A Collaborative Ensemble Framework for CTR Prediction
Xiaolong Liu, Zhichen Zeng, Xiaoyi Liu +13
Recent advances in foundation models have established scaling laws that enable the development of larger models to achieve enhanced performance, motivating extensive research into…
Meta Policy Learning for Cold-Start Conversational Recommendation
Zhendong Chu, Hongning Wang, Yun Xiao +2
Conversational recommender systems (CRS) explicitly solicit users' preferences for improved recommendations on the fly. Most existing CRS solutions count on a single policy trained…
Probabilistic Residual Learning for Online Recommendations
Wenyuan Wang, Yusong Zhao, Zihao Xu +11
Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffe…
Automatic Generation of Product-Image Sequence in E-commerce
Xiaochuan Fan, Chi Zhang, Yong Yang +6
Product images are essential for providing desirable user experience in an e-commerce platform. For a platform with billions of products, it is extremely time-costly and labor-expe…
Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability
Ninghao Liu, Yunsong Meng, Xia Hu +2
Recent years have witnessed an increasing number of interpretation methods being developed for improving transparency of NLP models. Meanwhile, researchers also try to answer the q…
Unified Semantic and ID Representation Learning for Deep Recommenders
Guanyu Lin, Zhigang Hua, Tao Feng +3
Effective recommendation is crucial for large-scale online platforms. Traditional recommendation systems primarily rely on ID tokens to uniquely identify items, which can effective…
A Scalable and Effective Alternative to Graph Transformers
Kaan Sancak, Zhigang Hua, Jin Fang +5
Graph Neural Networks (GNNs) have shown impressive performance in graph representation learning, but they face challenges in capturing long-range dependencies due to their limited…
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit
Huixue Zhou, Hengrui Gu, Xi Liu +15
The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and…
Unifying Generative and Dense Retrieval for Sequential Recommendation
Liu Yang, Fabian Paischer, Kaveh Hassani +11
Sequential dense retrieval models utilize advanced sequence learning techniques to compute item and user representations, which are then used to rank relevant items for a user thro…
MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System
Yun He, Xuxing Chen, Jiayi Xu +11
In industrial recommendation systems, multi-task learning (learning multiple tasks simultaneously on a single model) is a predominant approach to save training/serving resources an…
Graph-augmented Learning to Rank for Querying Large-scale Knowledge Graph
Hanning Gao, Lingfei Wu, Po Hu +3
Knowledge graph question answering (KGQA) based on information retrieval aims to answer a question by retrieving answer from a large-scale knowledge graph. Most existing methods fi…
EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations
Chiyu Zhang, Yifei Sun, Minghao Wu +9
Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world. In this work, we introduce EmbSum, a novel framework that…
Automatic Scene-based Topic Channel Construction System for E-Commerce
Peng Lin, Yanyan Zou, Lingfei Wu +3
Scene marketing that well demonstrates user interests within a certain scenario has proved effective for offline shopping. To conduct scene marketing for e-commerce platforms, this…