no code implementations • COLING 2022 • Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, HuaWei Shen, Xueqi Cheng
Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints.
no code implementations • 26 Apr 2024 • Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, HuaWei Shen, Bolin Ding
Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality.
no code implementations • 13 Apr 2024 • Jia Gu, Liang Pang, HuaWei Shen, Xueqi Cheng
In the first case, the agent is required to give the type and parameters of the probability distribution through the problem description, and then give the sampling sequence.
2 code implementations • 7 Apr 2024 • Zihao Wei, Jingcheng Deng, Liang Pang, Hanxing Ding, HuaWei Shen, Xueqi Cheng
We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
1 code implementation • 28 Mar 2024 • Junkai Zhou, Liang Pang, Ya Jing, Jia Gu, HuaWei Shen, Xueqi Cheng
For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action.
1 code implementation • 28 Feb 2024 • Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, HuaWei Shen, Xueqi Cheng, Jie zhou
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval.
no code implementations • 23 Feb 2024 • Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Zixuan Li, Jian Guo, HuaWei Shen, Yuanzhuo Wang
To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy.
1 code implementation • 22 Feb 2024 • Yan Lei, Liang Pang, Yuanzhuo Wang, HuaWei Shen, Xueqi Cheng
Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure.
no code implementations • 21 Feb 2024 • Danyang Hou, Liang Pang, HuaWei Shen, Xueqi Cheng
Video Corpus Moment Retrieval (VCMR) is a practical video retrieval task focused on identifying a specific moment within a vast corpus of untrimmed videos using the natural language query.
1 code implementation • 21 Feb 2024 • Danyang Hou, Liang Pang, HuaWei Shen, Xueqi Cheng
We argue that effectively capturing the partial relevance between the query and video is essential for the VCMR task.
1 code implementation • 20 Feb 2024 • Zihao Wei, Liang Pang, Hanxing Ding, Jingcheng Deng, HuaWei Shen, Xueqi Cheng
The premise of localization results in an incomplete knowledge editing, whereas an isolated assumption may impair both other knowledge and general abilities.
1 code implementation • 16 Feb 2024 • Jiajun Tan, Fei Sun, Ruichen Qiu, Du Su, HuaWei Shen
As concerns over data privacy intensify, unlearning in Graph Neural Networks (GNNs) has emerged as a prominent research frontier in academia.
no code implementations • 16 Feb 2024 • Hanxing Ding, Liang Pang, Zihao Wei, HuaWei Shen, Xueqi Cheng
A careful and balanced integration of the parametric knowledge within LLMs with external information is crucial to alleviate hallucinations.
1 code implementation • 5 Feb 2024 • Shicheng Xu, Liang Pang, Jun Xu, HuaWei Shen, Xueqi Cheng
First, it is hard to share the contextual information of the ranking list between the two tasks.
1 code implementation • 1 Feb 2024 • Boshen Shi, Yongqing Wang, Fangda Guo, Bingbing Xu, HuaWei Shen, Xueqi Cheng
To the best of our knowledge, this paper is the first survey for graph domain adaptation.
no code implementations • 31 Jan 2024 • Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, HuaWei Shen, Xueqi Cheng
Traditional defense strategies predominantly depend on predefined assumptions or rules extracted from specific known attacks, limiting their generalizability to unknown attack types.
1 code implementation • 24 Nov 2023 • Yige Yuan, Bingbing Xu, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng
To address this, we propose a novel energy-based perspective, enhancing the model's perception of target data distributions without requiring access to training data or processes.
no code implementations • 23 Nov 2023 • Shicheng Xu, Danyang Hou, Liang Pang, Jingcheng Deng, Jun Xu, HuaWei Shen, Xueqi Cheng
Furthermore, our subsequent exploration reveals that the inclusion of AI-generated images in the training data of the retrieval models exacerbates the invisible relevance bias.
1 code implementation • 13 Nov 2023 • Junkai Zhou, Liang Pang, HuaWei Shen, Xueqi Cheng
The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses.
no code implementations • 3 Nov 2023 • Shicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, HuaWei Shen, Xueqi Cheng, Jie zhou
Readers usually only give an abstract and vague description as the query based on their own understanding, summaries, or speculations of the plot, which requires the retrieval model to have a strong ability to estimate the abstract semantic associations between the query and candidate plots.
1 code implementation • journal 2023 • Jianian Li, Peng Bao, Rong Yan, HuaWei Shen
In this paper, we propose a novel Dynamic graph representation framework via Tempo-Structural Contrastive Learning, DyTSCL, which trains the model by identifying three different subgraphs as a task, named Tempo-Structural subgraph, Non-Temporal subgraph and Non-Structural subgraph.
1 code implementation • 16 Oct 2023 • Jingcheng Deng, Liang Pang, HuaWei Shen, Xueqi Cheng
It encodes the text corpus into a latent space, capturing current and future information from both source and target text.
1 code implementation • 14 Oct 2023 • Guoxin Chen, Yongqing Wang, Fangda Guo, Qinglang Guo, Jiangli Shao, HuaWei Shen, Xueqi Cheng
Most existing methods that address out-of-distribution (OOD) generalization for node classification on graphs primarily focus on a specific type of data biases, such as label selection bias or structural bias.
no code implementations • 5 Sep 2023 • Kaike Zhang, Qi Cao, Fei Sun, Yunfan Wu, Shuchang Tao, HuaWei Shen, Xueqi Cheng
With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload.
no code implementations • 18 Aug 2023 • Wendong Bi, Xueqi Cheng, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen
Transfer learning has been a feasible way to transfer knowledge from high-quality external data of source domains to limited data of target domains, which follows a domain-level knowledge transfer to learn a shared posterior distribution.
1 code implementation • 21 Jul 2023 • Boshen Shi, Yongqing Wang, Fangda Guo, Jiangli Shao, HuaWei Shen, Xueqi Cheng
Overall, OpenGDA provides a user-friendly, scalable and reproducible benchmark for evaluating graph domain adaptation models.
no code implementations • 25 May 2023 • Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu, Bingbing Xu, Xueqi Cheng
To address these limitations, we analyze the causalities in graph adversarial attacks and conclude that causal features are key to achieve graph adversarial robustness, owing to their determinedness for labels and invariance across attacks.
1 code implementation • 25 May 2023 • Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, HuaWei Shen, Xueqi Cheng
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones.
1 code implementation • 24 May 2023 • Kangxi Wu, Liang Pang, HuaWei Shen, Xueqi Cheng, Tat-Seng Chua
By jointly analyzing the proxy perplexities of LLMs, we can determine the source of the generated text.
1 code implementation • 22 May 2023 • Hanxing Ding, Liang Pang, Zihao Wei, HuaWei Shen, Xueqi Cheng, Tat-Seng Chua
Multi-aspect controllable text generation aims to generate fluent sentences that possess multiple desired attributes simultaneously.
1 code implementation • 18 May 2023 • Junkai Zhou, Liang Pang, HuaWei Shen, Xueqi Cheng
Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue.
no code implementations • 18 May 2023 • Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng
Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
1 code implementation • 9 May 2023 • YuanHao Liu, Qi Cao, HuaWei Shen, Yunfan Wu, Shuchang Tao, Xueqi Cheng
In this paper, we propose a new criterion for popularity debiasing, i. e., in an unbiased recommender system, both popular and unpopular items should receive Interactions Proportional to the number of users who Like it, namely IPL criterion.
1 code implementation • 28 Apr 2023 • Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng, Tat-Seng Chua
This paper proposes a novel framework named \textbf{Search-in-the-Chain} (SearChain) for the interaction between LLM and IR to solve the challenges.
1 code implementation • 7 Apr 2023 • Xuhui Jiang, Chengjin Xu, Yinghan Shen, Yuanzhuo Wang, Fenglong Su, Fei Sun, Zixuan Li, Zhichao Shi, Jian Guo, HuaWei Shen
Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios.
1 code implementation • 16 Feb 2023 • Shuchang Tao, HuaWei Shen, Qi Cao, Yunfan Wu, Liang Hou, Xueqi Cheng
In this paper, we propose and formulate graph adversarial immunization, i. e., vaccinating part of graph structure to improve certifiable robustness of graph against any admissible adversarial attack.
1 code implementation • 5 Feb 2023 • JunJie Huang, Qi Cao, Ruobing Xie, Shaoliang Zhang, Feng Xia, HuaWei Shen, Xueqi Cheng
To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance.
1 code implementation • 2 Feb 2023 • Wendong Bi, Bingbing Xu, Xiaoqian Sun, Li Xu, HuaWei Shen, Xueqi Cheng
To combat the above challenges, we propose Knowledge Transferable Graph Neural Network (KT-GNN), which models distribution shifts during message passing and representation learning by transferring knowledge from vocal nodes to silent nodes.
1 code implementation • 31 Jan 2023 • Wendong Bi, Bingbing Xu, Xiaoqian Sun, Zidong Wang, HuaWei Shen, Xueqi Cheng
However, most nodes in the tribe-style graph lack attributes, making it difficult to directly adopt existing graph learning methods (e. g., Graph Neural Networks(GNNs)).
no code implementations • 29 Jan 2023 • Danyang Hou, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng
In this paper, we focus on improving two problems of two-stage method: (1) Moment prediction bias: The predicted moments for most queries come from the top retrieved videos, ignoring the possibility that the target moment is in the bottom retrieved videos, which is caused by the inconsistency of Shared Normalization during training and inference.
1 code implementation • 10 Jan 2023 • Yunchang Zhu, Liang Pang, Kangxi Wu, Yanyan Lan, HuaWei Shen, Xueqi Cheng
Comparative loss is essentially a ranking loss on top of the task-specific losses of the full and ablated models, with the expectation that the task-specific loss of the full model is minimal.
1 code implementation • 1 Dec 2022 • Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng
Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they share the same schema to estimate the relationship between texts.
no code implementations • 20 Nov 2022 • Yige Yuan, Bingbing Xu, HuaWei Shen, Qi Cao, Keting Cen, Wen Zheng, Xueqi Cheng
Guided by the bound, we design a GCL framework named InfoAdv with enhanced generalization ability, which jointly optimizes the generalization metric and InfoMax to strike the right balance between pretext task fitting and the generalization ability on downstream tasks.
no code implementations • 16 Nov 2022 • Yang Li, Bingbing Xu, Qi Cao, Yige Yuan, HuaWei Shen
On account that previous studies either lacks variance analysis or only focus on a particular sampling paradigm, we firstly propose an unified node sampling variance analysis framework and analyze the core challenge "circular dependency" for deriving the minimum variance sampler, i. e., sampling probability depends on node embeddings while node embeddings can not be calculated until sampling is finished.
1 code implementation • 19 Oct 2022 • Kaike Zhang, Qi Cao, Gaolin Fang, Bingbing Xu, Hongjian Zou, HuaWei Shen, Xueqi Cheng
Unsupervised representation learning for dynamic graphs has attracted a lot of research attention in recent years.
1 code implementation • 3 Aug 2022 • Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu, Liang Hou, Fei Sun, Xueqi Cheng
In this paper, we first propose and define camouflage as distribution similarity between ego networks of injected nodes and normal nodes.
no code implementations • 4 Jul 2022 • Houquan Zhou, Shenghua Liu, Danai Koutra, HuaWei Shen, Xueqi Cheng
Recent works try to improve scalability via graph summarization -- i. e., they learn embeddings on a smaller summary graph, and then restore the node embeddings of the original graph.
no code implementations • 27 Jun 2022 • Yan Jiang, Jinhua Gao, HuaWei Shen, Xueqi Cheng
The main challenge of this task comes two-fold: few-shot learning resulting from the varying targets and the lack of contextual information of the targets.
1 code implementation • NeurIPS 2023 • Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao, Chongyang Ma, Siyuan Pan, Pengfei Wan, Zhongyuan Wang, HuaWei Shen, Xueqi Cheng
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
1 code implementation • 25 Apr 2022 • Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng
Ideally, if a PRF model can distinguish between irrelevant and relevant information in the feedback, the more feedback documents there are, the better the revised query will be.
no code implementations • 18 Apr 2022 • Quan Ding, Shenghua Liu, Bin Zhou, HuaWei Shen, Xueqi Cheng
Given a multivariate big time series, can we detect anomalies as soon as they occur?
1 code implementation • 6 Apr 2022 • Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng
In generalization stage, matching model explores the essential matching signals by being trained on diverse matching tasks.
no code implementations • 26 Mar 2022 • Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han, Zhenghao Liu, Ning Ding, Yongming Rao, Yizhao Gao, Liang Zhang, Ming Ding, Cong Fang, Yisen Wang, Mingsheng Long, Jing Zhang, Yinpeng Dong, Tianyu Pang, Peng Cui, Lingxiao Huang, Zheng Liang, HuaWei Shen, HUI ZHANG, Quanshi Zhang, Qingxiu Dong, Zhixing Tan, Mingxuan Wang, Shuo Wang, Long Zhou, Haoran Li, Junwei Bao, Yingwei Pan, Weinan Zhang, Zhou Yu, Rui Yan, Chence Shi, Minghao Xu, Zuobai Zhang, Guoqiang Wang, Xiang Pan, Mengjie Li, Xiaoyu Chu, Zijun Yao, Fangwei Zhu, Shulin Cao, Weicheng Xue, Zixuan Ma, Zhengyan Zhang, Shengding Hu, Yujia Qin, Chaojun Xiao, Zheni Zeng, Ganqu Cui, Weize Chen, Weilin Zhao, Yuan YAO, Peng Li, Wenzhao Zheng, Wenliang Zhao, Ziyi Wang, Borui Zhang, Nanyi Fei, Anwen Hu, Zenan Ling, Haoyang Li, Boxi Cao, Xianpei Han, Weidong Zhan, Baobao Chang, Hao Sun, Jiawen Deng, Chujie Zheng, Juanzi Li, Lei Hou, Xigang Cao, Jidong Zhai, Zhiyuan Liu, Maosong Sun, Jiwen Lu, Zhiwu Lu, Qin Jin, Ruihua Song, Ji-Rong Wen, Zhouchen Lin, LiWei Wang, Hang Su, Jun Zhu, Zhifang Sui, Jiajun Zhang, Yang Liu, Xiaodong He, Minlie Huang, Jian Tang, Jie Tang
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
no code implementations • 22 Mar 2022 • Zhaohui Wang, Qi Cao, HuaWei Shen, Bingbing Xu, Xueqi Cheng
The expressive power of message passing GNNs is upper-bounded by Weisfeiler-Lehman (WL) test.
1 code implementation • EMNLP 2021 • Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, HuaWei Shen, Xueqi Cheng
The proposed transductive learning approach is general and effective to the task of unsupervised style transfer, and we will apply it to the other two typical methods in the future.
1 code implementation • EMNLP 2021 • Yunchang Zhu, Liang Pang, Yanyan Lan, HuaWei Shen, Xueqi Cheng
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus.
Ranked #3 on Question Answering on HotpotQA
1 code implementation • 30 Aug 2021 • Shuchang Tao, Qi Cao, HuaWei Shen, JunJie Huang, Yunfan Wu, Xueqi Cheng
In this paper, we focus on an extremely limited scenario of single node injection evasion attack, i. e., the attacker is only allowed to inject one single node during the test phase to hurt GNN's performance.
1 code implementation • 22 Aug 2021 • JunJie Huang, HuaWei Shen, Qi Cao, Shuchang Tao, Xueqi Cheng
Signed bipartite networks are different from classical signed networks, which contain two different node sets and signed links between two node sets.
2 code implementations • 21 Jul 2021 • Liang Hou, Qi Cao, HuaWei Shen, Siyuan Pan, Xiaoshuang Li, Xueqi Cheng
Specifically, the proposed auxiliary discriminative classifier becomes generator-aware by recognizing the class-labels of the real data and the generated data discriminatively.
Ranked #1 on Conditional Image Generation on Tiny ImageNet
1 code implementation • 12 Jul 2021 • Yunfan Wu, Qi Cao, HuaWei Shen, Shuchang Tao, Xueqi Cheng
INMO generates the inductive embeddings for users (items) by characterizing their interactions with some template items (template users), instead of employing an embedding lookup table.
2 code implementations • NeurIPS 2021 • Liang Hou, HuaWei Shen, Qi Cao, Xueqi Cheng
Recently, transformation-based self-supervised learning has been applied to generative adversarial networks (GANs) to mitigate catastrophic forgetting in the discriminator by introducing a stationary learning environment.
1 code implementation • 21 Apr 2021 • Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, HuaWei Shen, Yuanzhuo Wang, Xueqi Cheng
To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently.
no code implementations • 19 Apr 2021 • Jiangli Shao, Yongqing Wang, Hao Gao, HuaWei Shen, Yangyang Li, Xueqi Cheng
However, encouraged by online services, users would also post asymmetric information across networks, such as geo-locations and texts.
no code implementations • 19 Mar 2021 • Hao Gao, Yongqing Wang, Shanshan Lyu, HuaWei Shen, Xueqi Cheng
However, the low quality of observed user data confuses the judgment on anchor links, resulting in the matching collision problem in practice.
no code implementations • 15 Jan 2021 • Fabin Shi, Nathan Aden, Shengda Huang, Neil Johnson, Xiaoqian Sun, Jinhua Gao, Li Xu, HuaWei Shen, Xueqi Cheng, Chaoming Song
Understanding the emergence of universal features such as the stylized facts in markets is a long-standing challenge that has drawn much attention from economists and physicists.
1 code implementation • 7 Jan 2021 • JunJie Huang, HuaWei Shen, Liang Hou, Xueqi Cheng
Guided by related sociological theories, we propose a novel Signed Directed Graph Neural Networks model named SDGNN to learn node embeddings for signed directed networks.
1 code implementation • 4 Jan 2021 • Deyu Bo, Xiao Wang, Chuan Shi, HuaWei Shen
For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks.
no code implementations • 1 Jan 2021 • Xu Bingbing, HuaWei Shen, Qi Cao, YuanHao Liu, Keting Cen, Xueqi Cheng
For a target node, diverse sampling offers it diverse neighborhoods, i. e., rooted sub-graphs, and the representation of target node is finally obtained via aggregating the representation of diverse neighborhoods obtained using any GNN model.
1 code implementation • 21 Dec 2020 • Chao Yang, Su Feng, Dongsheng Li, HuaWei Shen, Guoqing Wang, Bin Jiang
Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context.
no code implementations • 20 Dec 2020 • Chao Yang, Guoqing Wang, Dongsheng Li, HuaWei Shen, Su Feng, Bin Jiang
Reference expression comprehension (REC) aims to find the location that the phrase refer to in a given image.
1 code implementation • 10 Dec 2020 • Liang Hou, Zehuan Yuan, Lei Huang, HuaWei Shen, Xueqi Cheng, Changhu Wang
In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.
1 code implementation • 3 Dec 2020 • Jiabao Zhang, Shenghua Liu, Wenting Hou, Siddharth Bhatia, HuaWei Shen, Wenjian Yu, Xueqi Cheng
Therefore, we propose a fast streaming algorithm, AugSplicing, which can detect the top dense blocks by incrementally splicing the previous detection with the incoming ones in new tuples, avoiding re-runs over all the history data at every tracking time step.
no code implementations • 19 Oct 2020 • Houquan Zhou, Shenghua Liu, Kyuhan Lee, Kijung Shin, HuaWei Shen, Xueqi Cheng
As a solution, graph summarization, which aims to find a compact representation that preserves the important properties of a given graph, has received much attention, and numerous algorithms have been developed for it.
Social and Information Networks
1 code implementation • CIKM 2017 • Qi Cao, HuaWei Shen, Keting Cen, Wentao Ouyang, Xueqi Cheng
In this paper, we propose DeepHawkes to combat the defects of existing methods, leveraging end-to-end deep learning to make an analogy to interpretable factors of Hawkes process — a widely-used generative process to model information cascade.
1 code implementation • 1 May 2017 • Yongqing Wang, HuaWei Shen, Shenghua Liu, Jinhua Gao, and Xueqi Cheng
However, for cascade prediction, each cascade generally corresponds to a diffusion tree, causing cross-dependence in cascade— one sharing behavior could be triggered by its non-immediate predecessor in the memory chain.