Author name cluster

Ji Xiang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2025 Conference Paper

Relation Also Knows: Rethinking the Recall and Editing of Factual Associations in Auto-Regressive Transformer Language Models

Xiyu Liu
Zhengxiao Liu
Naibin Gu
Zheng Lin
Wanli Ma
Ji Xiang
Weiping Wang

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most editing works achieve knowledge editing under the guidance of existing interpretations of knowledge recall that mainly focus on subject knowledge. However, these interpretations are seriously flawed, neglecting relation information and leading to the *over-generalizing* problem for editing. In this work, we discover a novel relation-focused perspective to interpret the knowledge recall of transformer LMs during inference and apply it on single knowledge editing to avoid over-generalizing. Experimental results on the dataset supplemented with a new R-Specificity criterion demonstrate that our editing approach significantly alleviates over-generalizing while remaining competitive on other criteria, breaking the domination of subject-focused editing for future research.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Gaode Chen
Xinghua Zhang
Yijun Su
Yantong Lai
Ji Xiang
Junbo Zhang
Yu Zheng

Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge from an informative source domain to the target domain, which inevitably proposes stern challenges to data privacy and transferability during the transfer process. A small amount of recent CDR works have investigated privacy protection, while they still suffer from satisfying practical requirements (e.g., limited privacy-preserving ability) and preventing the potential risk of negative transfer. To address the above challenging problems, we propose a novel and unified privacy-preserving federated framework for dual-target CDR, namely P2FCDR. We design P2FCDR as peer-to-peer federated network architecture to ensure the local data storage and privacy protection of business partners. Specifically, for the special knowledge transfer process in CDR under federated settings, we initialize an optimizable orthogonal mapping matrix to learn the embedding transformation across domains and adopt the local differential privacy technique on the transformed embedding before exchanging across domains, which provides more reliable privacy protection. Furthermore, we exploit the similarity between in-domain and cross-domain embedding, and develop a gated selecting vector to refine the information fusion for more accurate dual transfer. Extensive experiments on three real-world datasets demonstrate that P2FCDR significantly outperforms the state-of-the-art methods and effectively protects data privacy.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation

Gaode Chen
Xinghua Zhang
Yanyan Zhao
Cong Xue
Ji Xiang

Sequential recommendation systems alleviate the problem of information overload, and have attracted increasing attention in the literature. Most prior works usually obtain an overall representation based on the user’s behavior sequence, which can not sufficiently reflect the multiple interests of the user. To this end, we propose a novel method called PIMI to mitigate this issue. PIMI can model the user’s multi-interest representation effectively by considering both the periodicity and interactivity in the item sequence. Specifically, we design a periodicity-aware module to utilize the time interval information between user’s behaviors. Meanwhile, an ingenious graph is proposed to enhance the interactivity between items in user’s behavior sequence, which can capture both global and local item features. Finally, a multi-interest extraction module is applied to describe user’s multiple interests based on the obtained item representation. Extensive experiments on two real-world datasets Amazon and Taobao show that PIMI outperforms state-of-the-art methods consistently.

PDF Details DOI

AAAI Conference 2019 Conference Paper

TransGate: Knowledge Graph Embedding with Shared Gate Structure

Jun Yuan
Neng Gao
Ji Xiang

Embedding knowledge graphs (KGs) into continuous vector space is an essential problem in knowledge extraction. Current models continue to improve embedding by focusing on discriminating relation-specific information from entities with increasingly complex feature engineering. We noted that they ignored the inherent relevance between relations and tried to learn unique discriminate parameter set for each relation. Thus, these models potentially suffer from high time complexity and large parameters, preventing them from efficiently applying on real-world KGs. In this paper, we follow the thought of parameter sharing to simultaneously learn more expressive features, reduce parameters and avoid complex feature engineering. Based on gate structure from LSTM, we propose a novel model TransGate and develop shared discriminate mechanism, resulting in almost same space complexity as indiscriminate models. Furthermore, to develop a more effective and scalable model, we reconstruct the gate with weight vectors making our method has comparative time complexity against indiscriminate model. We conduct extensive experiments on link prediction and triplets classification. Experiments show that TransGate not only outperforms state-of-art baselines, but also reduces parameters greatly. For example, TransGate outperforms ConvE and R- GCN with 6x and 17x fewer parameters, respectively. These results indicate that parameter sharing is a superior way to further optimize embedding and TransGate finds a better trade-off between complexity and expressivity.

PDF Details

ICRA Conference 2011 Conference Paper

A lower dimensional task function method for point-to-point control of non-redundant manipulators

Cong-wei Zhong
Ji Xiang
Wei Wei 0024
Yuan-hui Zhang

This paper proposed a task function method for the point-to-point (PTP) control problem of non-redundant robot manipulators. A task function to compress the conventional task space to a new one with lower dimensions increases the redundancy degree so that the original manipulator becomes a redundant one, such that we can apply redundant control laws to achieve online subtasks, such as obstacle avoidance without trajectory replanning. The four basic properties of the task function method which are necessary to ensure the good performance of the PTP control problem are presented. The experiment results verify the effectiveness of the presented method.

Details