Search Results for author: Defu Lian

Found 34 papers, 16 papers with code

Matching-oriented Embedding Quantization For Ad-hoc Retrieval

1 code implementation EMNLP 2021 Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, Xing Xie

In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.

Quantization

Self-Supervised Text Erasing with Controllable Image Synthesis

no code implementations27 Apr 2022 Gangwei Jiang, Shiyao Wang, Tiezheng Ge, Yuning Jiang, Ying WEI, Defu Lian

The synthetic training images with erasure ground-truth are then fed to train a coarse-to-fine erasing network.

Image Generation

BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction

1 code implementation18 Apr 2022 Bisheng Li, Min Zhou, Shengzhong Zhang, Menglin Yang, Defu Lian, Zengfeng Huang

Regarding missing link inference of diverse networks, we revisit the link prediction techniques and identify the importance of both the structural and attribute information.

Graph Classification Link Prediction +1

HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization

no code implementations18 Apr 2022 Menglin Yang, Min Zhou, Jiahong Liu, Defu Lian, Irwin King

Through theoretical analysis, we further show that our proposal is able to tackle the over-smoothing problem caused by hyperbolic aggregation and also brings the models a better discriminative ability.

Collaborative Filtering Recommendation Systems

A Mutually Reinforced Framework for Pretrained Sentence Embeddings

no code implementations28 Feb 2022 Junhan Yang, Zheng Liu, Shitao Xiao, Jianxun Lian, Lijun Wu, Defu Lian, Guangzhong Sun, Xing Xie

Instead of relying on annotation heuristics defined by humans, it leverages the sentence representation model itself and realizes the following iterative self-supervision process: on one hand, the improvement of sentence representation may contribute to the quality of data annotation; on the other hand, more effective data annotation helps to generate high-quality positive samples, which will further improve the current sentence representation model.

Contrastive Learning Sentence Embeddings

Reinforcement Routing on Proximity Graph for Efficient Recommendation

no code implementations23 Jan 2022 Chao Feng, Defu Lian, Xiting Wang, Zheng Liu, Xing Xie, Enhong Chen

Instead of searching the nearest neighbor for the query, we search the item with maximum inner product with query on the proximity graph.

Imitation Learning Recommendation Systems

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

2 code implementations14 Jan 2022 Shitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang, Yingxia Shao, Defu Lian, Chaozhuo Li, Hao Sun, Denvy Deng, Liangjie Zhang, Qi Zhang, Xing Xie

In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.

Quantization

Meta-learning with an Adaptive Task Scheduler

1 code implementation NeurIPS 2021 Huaxiu Yao, Yu Wang, Ying WEI, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn

In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.

Drug Discovery Meta-Learning

Learned Index with Dynamic $\epsilon$

no code implementations29 Sep 2021 Daoyuan Chen, Wuchao Li, Yaliang Li, Bolin Ding, Kai Zeng, Defu Lian, Jingren Zhou

We theoretically analyze prediction error bounds that link $\epsilon$ with data characteristics for an illustrative learned index method.

Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering

no code implementations13 Sep 2021 Jin Chen, Binbin Jin, Xu Huang, Defu Lian, Kai Zheng, Enhong Chen

Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering.

Collaborative Filtering

Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation

1 code implementation28 May 2021 Yongji Wu, Defu Lian, Neil Zhenqiang Gong, Lu Yin, Mingyang Yin, Jingren Zhou, Hongxia Yang

Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention.

Quantization Sequential Recommendation

Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention

no code implementations28 May 2021 Yongji Wu, Lu Yin, Defu Lian, Mingyang Yin, Neil Zhenqiang Gong, Jingren Zhou, Hongxia Yang

With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data.

Sequential Recommendation

Assessing Dialogue Systems with Distribution Distances

1 code implementation Findings (ACL) 2021 Jiannan Xiang, Yahui Liu, Deng Cai, Huayang Li, Defu Lian, Lemao Liu

An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.

Dialogue Evaluation

GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph

no code implementations NeurIPS 2021 Junhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li, Defu Lian, Sanjay Agrawal, Amit Singh, Guangzhong Sun, Xing Xie

The representation learning on textual graph is to generate low-dimensional embeddings for the nodes based on the individual textual features and the neighbourhood information.

Language Modelling Pretrained Language Models +2

A Unified Transferable Model for ML-Enhanced DBMS

1 code implementation6 May 2021 Ziniu Wu, Pei Yu, Peilun Yang, Rong Zhu, Yuxing Han, Yaliang Li, Defu Lian, Kai Zeng, Jingren Zhou

We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks.

Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks

no code implementations22 Apr 2021 Junhan Yang, Zheng Liu, Bowen Jin, Jianxun Lian, Defu Lian, Akshay Soni, Eun Yong Kang, Yajun Wang, Guangzhong Sun, Xing Xie

For the sake of efficient recommendation, conventional methods would generate user and advertisement embeddings independently with a siamese transformer encoder, such that approximate nearest neighbour search (ANN) can be leveraged.

Matching-oriented Product Quantization For Ad-hoc Retrieval

2 code implementations16 Apr 2021 Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, Xing Xie

In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated.

Quantization

Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure

1 code implementation2 Mar 2021 Jin Chen, Tiezheng Ge, Gangwei Jiang, Zhiqiang Zhang, Defu Lian, Kai Zheng

Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.

Efficient Exploration

Automated Creative Optimization for E-Commerce Advertising

1 code implementation28 Feb 2021 Jin Chen, Ju Xu, Gangwei Jiang, Tiezheng Ge, Zhiqiang Zhang, Defu Lian, Kai Zheng

However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback.

AutoML Click-Through Rate Prediction +1

Sampling-Decomposable Generative Adversarial Recommender

no code implementations NeurIPS 2020 Binbin Jin, Defu Lian, Zheng Liu, Qi Liu, Jianhui Ma, Xing Xie, Enhong Chen

The GAN-style recommenders (i. e., IRGAN) addresses the challenge by learning a generator and a discriminator adversarially, such that the generator produces increasingly difficult samples for the discriminator to accelerate optimizing the discrimination objective.

Deep Pairwise Hashing for Cold-start Recommendation

no code implementations2 Nov 2020 Yan Zhang, Ivor W. Tsang, Hongzhi Yin, Guowu Yang, Defu Lian, Jingjing Li

Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation.

Denoising

Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation

no code implementations24 May 2020 Le Wu, Yonghui Yang, Lei Chen, Defu Lian, Richang Hong, Meng Wang

The transfer network is designed to approximate the learned item embeddings from graph neural networks by taking each item's visual content as input, in order to tackle the new segment problem in the test phase.

Transfer Learning

GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions

1 code implementation12 May 2020 Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xuemin Lin

We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model.

Lightrec: A memory and search-efficient recommender system

1 code implementation International World Wide Web Conference 2020 Defu Lian, Haoyu Wang, Zheng Liu, Jianxun Lian, Enhong Chen, Xing Xie

On top of such a structure, LightRec will have an item represented as additive composition of B codewords, which are optimally selected from each of the codebooks.

Recommendation Systems

Binarized Graph Neural Network

no code implementations19 Apr 2020 Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xiangjian He, Yiguang Lin, Xuemin Lin

Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding.

Graph Embedding

A Novel User Representation Paradigm for Making Personalized Candidate Retrieval

no code implementations15 Jul 2019 Zheng Liu, Yu Xing, Jianxun Lian, Defu Lian, Ziyao Li, Xing Xie

Our work is undergoing a anonymous review, and it will soon be released after the notification.

Metric Learning

Binarized Collaborative Filtering with Distilling Graph Convolutional Networks

no code implementations5 Jun 2019 Haoyu Wang, Defu Lian, Yong Ge

Then we distill the ranking information derived from GCN into binarized collaborative filtering, which makes use of binary representation to improve the efficiency of online recommendation.

Collaborative Filtering Recommendation Systems

MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network

no code implementations27 May 2019 Hao Wang, Tong Xu, Qi Liu, Defu Lian, Enhong Chen, Dongfang Du, Han Wu, Wen Su

Recently, the Network Representation Learning (NRL) techniques, which represent graph structure via low-dimension vectors to support social-oriented application, have attracted wide attention.

Multi-Task Learning Representation Learning

A Survey on Session-based Recommender Systems

1 code implementation13 Feb 2019 Shoujin Wang, Longbing Cao, Yan Wang, Quan Z. Sheng, Mehmet Orgun, Defu Lian

In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs.

Collaborative Filtering Decision Making +1

Binarized Attributed Network Embedding

2 code implementations ICDM 2018 Hong Yang, Shirui Pan, Peng Zhang, Ling Chen, Defu Lian, Chengqi Zhang

To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation.

Graph Embedding Link Prediction +2

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