Yajing Xu

Yajing Xu

Auto-generated profile, based on publicly available information

Yajing Xu

Zhejiang University, Hangzhou, Zhejiang, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
YZYichi Zhang
Yichi Zhang
ZCZhuo Chen
Zhuo Chen
LGLingbing Guo
Lingbing Guo
YXYajing Xu
Yajing Xu
WZWen Zhang
Wen Zhang
HCHuajun Chen
Huajun Chen
Large language model (LLM) based knowledge graph completion (KGC) aims to predict the missing triples in the KGs with LLMs. However, research about LLM-based KGC fails to sufficiently harness LLMs' inference proficiencies, overlooking critical structural information integral to KGs. In this paper, we explore methods to incorporate structural information into the LLMs, with the overarching goal of facilitating structure-aware reasoning. We first discuss on the existing LLM paradigms like in-context learning and instruction tuning, proposing basic structural information injection approaches. Then we propose a Knowledge Prefix Adapter (KoPA) to fulfill this stated goal. KoPA uses a structural pre-training phase to comprehend the intricate entities and relations within KGs, representing them as structural embeddings. Then KoPA communicates such cross-modal structural information understanding to the LLMs through a knowledge prefix adapter which projects the structural embeddings into the textual space and obtains virtual knowledge tokens positioned as a prefix of the input prompt. We conduct comprehensive experiments and provide incisive analysis. Our code and data are available at https://github.com/zjukg/KoPA.

10 July 2024
Verified
Conference Paper
Open access
YZYichi Zhang
Yichi Zhang
ZCZhuo Chen
Zhuo Chen
LGLingbing Guo
Lingbing Guo
YXYajing Xu
Yajing Xu
BHBinbin Hu
Binbin Hu
HCHuajun Chen
Huajun Chen
Multi-modal knowledge graph completion (MMKGC) aims to automatically discover the unobserved factual knowledge from a given multi-modal knowledge graph by collaboratively modeling the triple structure and multi-modal information from entities. However, real-world MMKGs present challenges due to their diverse and imbalanced nature, which means that the modality information can span various types (e.g., image, text, numeric, audio, video) but its distribution among entities is uneven, leading to missing modalities for certain entities. Existing works usually focus on common modalities like image and text while neglecting the imbalanced distribution phenomenon of modal information. To address these issues, we propose a comprehensive framework NativE to achieve MMKGC in the wild. NativE proposes a relation-guided dual adaptive fusion module that enables adaptive fusion for any modalities and employs a collaborative modality adversarial training framework to augment the imbalanced modality information. We construct a new benchmark called WildKGC with five datasets to evaluate our method. The empirical results compared with 21 recent baselines confirm the superiority of our method, consistently achieving state-of-the-art performance across different datasets and various scenarios while keeping efficient and generalizable. Our code and data are released at https://github.com/zjukg/NATIVE.

14 August 2022
Verified
Conference Paper
Open access
YGYuxia Geng
Yuxia Geng
JCJiaoyan Chen
Jiaoyan Chen
WZWen Zhang
Wen Zhang
YXYajing Xu
Yajing Xu
ZCZhuo Chen
Zhuo Chen
HCHua-Jun Chen
Hua-Jun Chen
Knowledge Graph (KG) and its variant of ontology have been widely used for knowledge representation, and have shown to be quite effective in augmenting Zero-shot Learning (ZSL). However, existing ZSL methods that utilize KGs all neglect the intrinsic complexity of inter-class relationships represented in KGs. One typical feature is that a class is often related to other classes in different semantic aspects. In this paper, we focus on ontologies for augmenting ZSL, and propose to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects. We also contribute a new ZSL framework named DOZSL, which contains two new ZSL solutions based on generative models and graph propagation models, respectively, for effectively utilizing the disentangled ontology embeddings. Extensive evaluations have been conducted on five benchmarks across zero-shot image classification (ZS-IMGC) and zero-shot KG completion (ZS-KGC). DOZSL often achieves better performance than the state-of-the-art, and its components have been verified by ablation studies and case studies. Our codes and datasets are available at https://github.com/zjukg/DOZSL.

30 April 2023
Verified
Conference Paper
Open access
WZWen Zhang
Wen Zhang
YZYushan Zhu
Yushan Zhu
MCMingyang Chen
Mingyang Chen
YGYuxia Geng
Yuxia Geng
YHYufeng Huang
Yufeng Huang
HCHuajun Chen
Huajun Chen
Knowledge graphs (KG) are essential background knowledge providers in many tasks. When designing models for KG-related tasks, one of the key tasks is to devise the Knowledge Representation and Fusion (KRF) module that learns the representation of elements from KGs and fuses them with task representations. While due to the difference of KGs and perspectives to be considered during fusion across tasks, duplicate and ad hoc KRF modules design are conducted among tasks. In this paper, we propose a novel knowledge graph pretraining model KGTransformer that could serve as a uniform KRF module in diverse KG-related tasks. We pretrain KGTransformer with three self-supervised tasks with sampled sub-graphs as input. For utilization, we propose a general prompt-tuning mechanism regarding task data as a triple prompt to allow flexible interactions between task KGs and task data. We evaluate pretrained KGTransformer on three tasks, triple classification, zero-shot image classification, and question answering. KGTransformer consistently achieves better results than specifically designed task models. Through experiments, we justify that the pretrained KGTransformer could be used off the shelf as a general and effective KRF module across KG-related tasks. The code and datasets are available at https://github.com/zjukg/KGTransformer.

13 May 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
WZWen Zhang
Wen Zhang
YXYajing Xu
Yajing Xu
PYPeng Ye
Peng Ye
ZHZhiwei Huang
Zhiwei Huang
ZXZezhong Xu
Zezhong Xu
HCHuajun Chen
Huajun Chen
Knowledge graph (KG) completion aims to find out missing triples in a KG. Some tasks, such as link prediction and instance completion, have been proposed for KG completion. They are triple-level tasks with some elements in a missing triple given to predict the missing element of the triple. However, knowing some elements of the missing triple in advance is not always a realistic setting. In this paper, we propose a novel graph-level automatic KG completion task called Triple Set Prediction (TSP) which assumes none of the elements in the missing triples is given. TSP is to predict a set of missing triples given a set of known triples. To properly and accurately evaluate this new task, we propose 4 evaluation metrics including 3 classification metrics and 1 ranking metric, considering both the partial-open-world and the closed-world assumptions. Furthermore, to tackle the huge candidate triples for prediction, we propose a novel and efficient subgraph-based method GPHT that can predict the triple set fast. To fairly compare the TSP results, we also propose two types of methods RuleTensor-TSP and KGE-TSP applying the existing rule- and embedding-based methods for TSP as baselines. During experiments, we evaluate the proposed methods on two datasets extracted from Wikidata following the relation-similarity partial-open-world assumption proposed by us, and also create a complete family data set to evaluate TSP results following the closed-world assumption. Results prove that the methods can successfully generate a set of missing triples and achieve reasonable scores on the new task, and GPHTperforms better than the baselines with significantly shorter prediction time.

14 January 2020 in Scandinavian Actuarial Journal
Verified
Journal Article
Open access
MSMichael Sherris
Michael Sherris
YXYajing Xu
Yajing Xu
JZJonathan Ziveyi
Jonathan Ziveyi
Multi-country risk management of longevity risk provides new opportunities to hedge mortality and interest rate risks in guaranteed lifetime income streams. This requires consideration of both interest rate and mortality risks in multiple countries. For this purpose, we develop value-based longevity indexes for multiple cohorts in two different countries that take into account the major sources of risks impacting life insurance portfolios, mortality and interest rates. To construct the indexes we propose a cohort-based affine model for multi-country mortality and use an arbitrage-free multi-country Nelson–Siegel model for the dynamics of interest rates. Index-based longevity hedging strategies have the advantages of efficiency, liquidity and lower cost but introduce basis risk. Graphical risk metrics are a way to effectively capture the relationship between an insurer's portfolio and hedging strategies. We illustrate the effectiveness of using a value-based index for longevity risk management between two countries using graphical basis risk metrics. To show the impact of both interest rate and mortality risk we use Australia and the UK as domestic and foreign countries, and, to show the impact of mortality only, we use the male populations of the Netherlands and France with common interest rates and basis risk arising only from differences in mortality risks.