Dong Yang

Mr. Dong Yang

NUDT
orcid

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
1 July 2020
Verified
Conference Paper
Closed access
DYDong Yang
Dong Yang
YTYuhua Tang
Yuhua Tang
Reinforcement learning focuses on goal-directed learning from interaction and the success of its applications strongly depends on how well the reward signal frames the problem and how well it assesses progress in solving it. But in many real-world scenarios, the agent is supplied with extremely sparse or even no rewards which makes learning fail and fall into ineffective exploration. In psychology, shaping is a method of animal training by reinforcing successive approximations of rewards to finally achieve the desired complex behavior. Inspired by this phenomenon of animal learning and reward as a signal in neuroscience, in this paper we solve the sparse reward problem by constructing a reward generator to generate inner-rewards and guide the agent learning control policies with deep neural networks. The proposed learning-based reward shaping does not require specific domain knowledge, but rather enable the agent to learn how to generate inner rewards to guide itself in any scenarios online jointly with the actual reinforcement learning process. To validate the performance in complex sparse reward problems, the proposed approach is evaluated in a challenging scenario, Football Academy in Google Research Football Environment, a newly released reinforcement learning environment with physics-based 3D simulator, instead of maze environments or grid world that are commonly used in research which are not sufficiently challenging. We compare the performance of our inner-rewards approach with two reinforcement algorithms (PPO and ICM + PPO). Experimental results show that our method improves the learning performance in terms of speed and quality, and also enables the agent to learn generalized skills applied to novel scenarios.

31 January 2021 in Computer Animation and Virtual Worlds
Verified
Journal Article
Closed access
PDF file
DYDong Yang
Dong Yang
WYWenjing Yang
Wenjing Yang
MLMinglong Li
Minglong Li
QYQiong Yang
Qiong Yang

1 August 2023
Verified
Conference Paper
Open access
PDF file
YWYilin Wang
Yilin Wang
MHMinghao Hu
Minghao Hu
ZHZhen Huang
Zhen Huang
DLDongsheng Li
Dongsheng Li
WLWei Luo
Wei Luo
XLXicheng Lu
Xicheng Lu
Electronic proceedings of IJCAI 2023

1 January 2023 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
YWYilin Wang
Yilin Wang
ZHZhen Huang
Zhen Huang
MHMinghao Hu
Minghao Hu
DLDongsheng Li
Dongsheng Li
XLXicheng Lu
Xicheng Lu
DYDong Yang
Dong Yang
Knowledge graphs are crucial foundations for building intelligent systems, such as question answering and recommendation. However, their performance is hampered by the incompleteness of KGs, so the knowledge graph completion arises to infer whether a triple of the form (head entity, relation, tail entity) is a missing fact. The path‐based approach that encodes paths from the head entity to the tail entity for reasoning achieves good performance. Previous work suggests that entity type is beneficial for learning path representations. Nevertheless, the semantics of entities are not captured accurately, as many entities are not typed or loosely typed. In addition, previous methods tend to model paths only from the forward direction but fail to capture new path patterns from the reverse direction (i.e., tail entity to head entity). In this paper, we introduce a structure enhanced path reasoning (SPR) framework to address the above‐given problems. First, the model uilizes the structure of entities, i.e., their relational contexts (the relations linked from the given entity), to obtain a reliable path representation that captures correct entity semantics. This information is accessible to all nonisolated entities in all KGs, so that it can compensate the semantics for entities or KGs that have no type available. Second, we leverage the structure of paths to derive their reverse paths, so as to enhance the path representation by additionally encoding the new patterns embedded in them through a dual path encoding method. In order to verify the effectiveness of the proposed methods, we design different architectures based on LSTM and Transformer, respectively. Experimental results on two benchmark datasets, WN18RR, and FB15k‐237, show that our approach apparently outperforms state‐of‐the‐art methods on fact prediction task and relation prediction task. Furthermore, extensive experiments illustrate the benefits of enhancing path reasoning by exploiting structure information from entity relational contexts and the dual path encoding method.

26 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
YWYilin Wang
Yilin Wang
MHMinghao Hu
Minghao Hu
ZHZhen Huang
Zhen Huang
DLDongsheng Li
Dongsheng Li
DYDong Yang
Dong Yang
XLXicheng Lu
Xicheng Lu
The goal of knowledge graph completion (KGC) is to predict missing facts among entities. Previous methods for KGC re-ranking are mostly built on non-generative language models to obtain the probability of each candidate. Recently, generative large language models (LLMs) have shown outstanding performance on several tasks such as information extraction and dialog systems. Leveraging them for KGC re-ranking is beneficial for leveraging the extensive pre-trained knowledge and powerful generative capabilities. However, it may encounter new problems when accomplishing the task, namely mismatch, misordering and omission. To this end, we introduce KC-GenRe, a knowledge-constrained generative re-ranking method based on LLMs for KGC. To overcome the mismatch issue, we formulate the KGC re-ranking task as a candidate identifier sorting generation problem implemented by generative LLMs. To tackle the misordering issue, we develop a knowledge-guided interactive training method that enhances the identification and ranking of candidates. To address the omission issue, we design a knowledge-augmented constrained inference method that enables contextual prompting and controlled generation, so as to obtain valid rankings. Experimental results show that KG-GenRe achieves state-of-the-art performance on four datasets, with gains of up to 6.7% and 7.7% in the MRR and Hits@1 metric compared to previous methods, and 9.0% and 11.1% compared to that without re-ranking. Extensive analysis demonstrates the effectiveness of components in KG-GenRe.