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.
no code implementations • 27 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.
1 code implementation • 18 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.
no code implementations • 18 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.
1 code implementation • 1 Apr 2022 • Shitao Xiao, Zheng Liu, Weihao Han, Jianjin Zhang, Defu Lian, Yeyun Gong, Qi Chen, Fan Yang, Hao Sun, Yingxia Shao, Denvy Deng, Qi Zhang, Xing Xie
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
no code implementations • Findings (ACL) 2022 • Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
no code implementations • Findings (ACL) 2022 • Jiannan Xiang, Huayang Li, Yahui Liu, Lemao Liu, Guoping Huang, Defu Lian, Shuming Shi
Current practices in metric evaluation focus on one single dataset, e. g., Newstest dataset in each year's WMT Metrics Shared Task.
no code implementations • 28 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.
no code implementations • 23 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.
2 code implementations • 14 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.
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.
no code implementations • 29 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.
no code implementations • 13 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.
1 code implementation • 28 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.
no code implementations • 28 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.
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.
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.
1 code implementation • 6 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.
no code implementations • 22 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.
2 code implementations • 16 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.
1 code implementation • 2 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.
1 code implementation • 28 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.
1 code implementation • 8 Feb 2021 • Shiyao Wang, Qi Liu, Tiezheng Ge, Defu Lian, Zhiqiang Zhang
Creative plays a great important role in e-commerce for exhibiting products.
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.
no code implementations • 2 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.
no code implementations • 24 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.
1 code implementation • 12 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.
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.
no code implementations • 19 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.
no code implementations • 15 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.
no code implementations • 5 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.
no code implementations • 27 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.
1 code implementation • 13 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.
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.
Ranked #1 on
Link Prediction
on Wiki