Author name cluster

Lu Su

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

1 author row

EAAI Journal 2026 Journal Article

A domain-specific language model for engineering-scale geological reasoning and mineral exploration in the Qin-Hang belt

Jianhua Ma
Yongzhang Zhou
Lu Su
Huanrong Yang
Luhao He

The Qin–Hang metallogenic belt in South China features complex tectono-magmatic systems and multi-stage mineralization, posing persistent challenges for engineering-scale geological reasoning. General-purpose large language models (LLMs) struggle to capture domain-specific terminology, causal relationships, and hierarchical geological logic. To address these limitations, we developed Qin–Hang Geological Generative Pretrained Transformer (QHGeoGPT), a domain-specific language model integrating three core innovations: Low-Rank Adaptation (LoRA) for parameter-efficient tuning, Retrieval-Augmented Generation (RAG) with an external geological corpus, and a knowledge-graph-based reasoning framework. Together, these components form a Graph-RAG architecture that enhances factual precision, causal inference, and interpretability in geological question answering. Built upon the DeepSeek-R1-7B backbone, QHGeoGPT was evaluated on 1201 expert-designed questions spanning structural interpretation, ore genesis, and tectonic evolution. It achieved 89. 99 % accuracy and 62. 79 % terminology coverage, outperforming the base model and approaching GPT-4o. By effectively modeling engineering-scale causal chains (e. g. , fault zones → fluid migration → orebody formation), QHGeoGPT demonstrates practical value for knowledge-driven mineral exploration and decision-making, offering a reproducible artificial intelligence (AI) framework for geological modeling, mineral prediction, and exploration strategy design.

Details DOI

NeurIPS Conference 2024 Conference Paper

FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

Feijie Wu
Xingchen Wang
Yaqing Wang
Tianci Liu
Lu Su
Jing Gao

In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming the limitations of previous static and dynamic submodel extraction methods. Compared to existing works, the proposed method offers a theoretical foundation for the submodel extraction and eliminates the need for additional information beyond the model parameters themselves to determine parameter importance, significantly reducing the overhead on clients. Extensive experiments are conducted on various datasets to showcase the superior performance of the proposed FIARSE.

PDF Details DOI

AAAI Conference 2023 Conference Paper

SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification

Tianci Liu
Haoyu Wang
Yaqing Wang
Xiaoqian Wang
Lu Su
Jing Gao

Recent years have witnessed increasing concerns towards unfair decisions made by machine learning algorithms. To improve fairness in model decisions, various fairness notions have been proposed and many fairness-aware methods are developed. However, most of existing definitions and methods focus only on single-label classification. Fairness for multi-label classification, where each instance is associated with more than one labels, is still yet to establish. To fill this gap, we study fairness-aware multi-label classification in this paper. We start by extending Demographic Parity (DP) and Equalized Opportunity (EOp), two popular fairness notions, to multi-label classification scenarios. Through a systematic study, we show that on multi-label data, because of unevenly distributed labels, EOp usually fails to construct a reliable estimate on labels with few instances. We then propose a new framework named Similarity s-induced Fairness (sγ -SimFair). This new framework utilizes data that have similar labels when estimating fairness on a particular label group for better stability, and can unify DP and EOp. Theoretical analysis and experimental results on real-world datasets together demonstrate the advantage of sγ -SimFair over existing methods on multi-label classification tasks.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Data Poisoning Attack against Knowledge Graph Embedding

Hengtong Zhang
Tianhang Zheng
Jing Gao
Chenglin Miao
Lu Su
Yaliang Li
Kui Ren

Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph. Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently. Despite its effectiveness in a benign environment, KGE's robustness to adversarial attacks is not well-studied. Existing attack methods on graph data cannot be directly applied to attack the embeddings of knowledge graph due to its heterogeneity. To fill this gap, we propose a collection of data poisoning attack strategies, which can effectively manipulate the plausibility of arbitrary targeted facts in a knowledge graph by adding or deleting facts on the graph. The effectiveness and efficiency of the proposed attack strategies are verified by extensive evaluations on two widely-used benchmarks.

PDF Details

IJCAI Conference 2019 Conference Paper

Deep Metric Learning: The Generalization Analysis and an Adaptive Algorithm

Mengdi Huai
Hongfei Xue
Chenglin Miao
Liuyi Yao
Lu Su
Changyou Chen
Aidong Zhang

As an effective way to learn a distance metric between pairs of samples, deep metric learning (DML) has drawn significant attention in recent years. The key idea of DML is to learn a set of hierarchical nonlinear mappings using deep neural networks, and then project the data samples into a new feature space for comparing or matching. Although DML has achieved practical success in many applications, there is no existing work that theoretically analyzes the generalization error bound for DML, which can measure how good a learned DML model is able to perform on unseen data. In this paper, we try to fill up this research gap and derive the generalization error bound for DML. Additionally, based on the derived generalization bound, we propose a novel DML method (called ADroDML), which can adaptively learn the retention rates for the DML models with dropout in a theoretically justified way. Compared with existing DML works that require predefined retention rates, ADroDML can learn the retention rates in an optimal way and achieve better performance. We also conduct experiments on real-world datasets to verify the findings derived from the generalization error bound and demonstrate the effectiveness of the proposed adaptive DML method.

PDF Details