Author name cluster

Xuan Lu

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.

4 papers

2 author rows

ICLR Conference 2025 Conference Paper

DeepSeek-Prover-V1. 5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Huajian Xin
Z. Z. Ren
Junxiao Song
Zhihong Shao
Wanjia Zhao
Haocheng Wang
Bo Liu
Liyue Zhang

Lean is an advanced proof assistant designed to facilitate formal theorem proving by providing a variety of interactive feedback. In this paper, we explore methodologies to leverage proof assistant feedback to augment the capabilities of large language models in constructing formal proofs. First, we deploy online reinforcement learning using Lean verification outcomes as the reward signal to improve the proof completion policy. This straightforward approach shows great promise in enhancing the model's alignment with the formal verification system. In addition, we propose RMaxTS, a variant of Monte-Carlo tree search that employs an intrinsic-reward-driven exploration strategy to generate diverse proof paths. The tree structure is organized to represent the transitions of intermediate tactic states, extracted from the compilation messages given by Lean's tactic mode. The intrinsic reward is constructed to incentivize the discovery of novel tactic states, which helps to to mitigate the sparse-reward problem inherent in proof search. These techniques lead to a more efficient planning scheme for formal proof generation, achieving new state-of-the-art results on both miniF2F and ProofNet benchmarks.

Details

EAAI Journal 2024 Journal Article

An overlapping minimization-based over-sampling algorithm for binary imbalanced classification

Xuan Lu
Xuan Ye
Yingchao Cheng

Imbalanced learning is an important branch of machine learning. It addresses the challenge of improving classifier accuracy for minority classes in imbalanced data sets. Currently, the mainstream methods for handling imbalanced learning are the synthetic minority oversampling technique (SMOTE) and its variants, which generate synthetic minority class samples to balance the dataset. However, existing methods suffer from issues such as increased sample overlap, exacerbated intra-class imbalance, and are sensitive to parameter settings. These issues make it challenging to generate high-quality minority class samples and can adversely affect the dataset. To address these challenges, this study proposes a novel overlapping minimization-based over-sampling (OMOS) algorithm for binary imbalanced classification. The OMOS algorithm consists of four steps: clustering, filtering, auto-encoding, and oversampling. In the clustering step, the mean shift algorithm is utilized to cluster the original dataset and identify clusters that belong to the minority class. In the filtering step, safe samples are selected that maintain consistent labels before and after clustering. Then, in the auto-encoding step, autoencoders are utilized to capture the distribution characteristics of safe samples within each minority class cluster. Finally, in the last step, minority class samples are generated based on the probability distribution learned from safe samples. Furthermore, OMOS introduces a novel approach to compute suitable sampling rates for each minority class cluster to handle intra-class imbalance. Experimental results show that the proposed OMOS algorithm outperforms six state-of-the-art SMOTE-based oversampling algorithms on 20 real-world imbalanced datasets and four classifiers: naive Bayes classifier, support vector machine, logistic regression, and decision trees. This demonstrates that OMOS is effective for binary imbalanced classification tasks.

Details DOI

AAAI Conference 2024 Conference Paper

Cross-Domain Contrastive Learning for Time Series Clustering

Furong Peng
Jiachen Luo
Xuan Lu
Sheng Wang
Feijiang Li

Most deep learning-based time series clustering models concentrate on data representation in a separate process from clustering. This leads to that clustering loss cannot guide feature extraction. Moreover, most methods solely analyze data from the temporal domain, disregarding the potential within the frequency domain. To address these challenges, we introduce a novel end-to-end Cross-Domain Contrastive learning model for time series Clustering (CDCC). Firstly, it integrates the clustering process and feature extraction using contrastive constraints at both cluster-level and instance-level. Secondly, the data is encoded simultaneously in both temporal and frequency domains, leveraging contrastive learning to enhance within-domain representation. Thirdly, cross-domain constraints are proposed to align the latent representations and category distribution across domains. With the above strategies, CDCC not only achieves end-to-end output but also effectively integrates frequency domains. Extensive experiments and visualization analysis are conducted on 40 time series datasets from UCR, demonstrating the superior performance of the proposed model.

PDF Details DOI

IJCAI Conference 2020 Conference Paper

Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification (Extended Abstract)

Zhenpeng Chen
Sheng Shen
Ziniu Hu
Xuan Lu
Qiaozhu Mei
Xuanzhe Liu

Sentiment classification typically relies on a large amount of labeled data. In practice, the availability of labels is highly imbalanced among different languages. To tackle this problem, cross-lingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i. e. , the source language, usually English) to another language with fewer labels (i. e. , the target language). The source and the target languages are usually bridged through off-the-shelf machine translation tools. Through such a channel, cross-language sentiment patterns can be successfully learned from English and transferred into the target languages. This approach, however, often fails to capture sentiment knowledge specific to the target language. In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. We propose a novel representation learning method that uses emoji prediction as an instrument to learn respective sentiment-aware representations for each language. The learned representations are then integrated to facilitate cross-lingual sentiment classification.

PDF Details DOI