Author name cluster

Xinyue Liu

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.

10 papers

2 author rows

EAAI Journal 2026 Journal Article

Perceptive scale and selective attention few-shot learning network for hyperspectral and light detection and ranging fusion classification

Xianghai Wang
Tingting Geng
Xinyue Liu
Xiaohan Xie
Xiaoyang Zhao
Siyao Li

The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data provides complementary information for advanced Earth observation. However, acquiring sufficient labeled samples to train deep learning models is often prohibitively expensive, creating a major bottleneck. To address this, we propose a Perceptive Scale and Selective Attention Few-Shot Learning Network (PS2A-FSLNet) for HSI-LiDAR fusion classification. Our framework leverages a richly labeled HSI source domain to assist a sparsely labeled HSI-LiDAR target domain. Its key innovations are: (1) A Scale-Aware Feature Enhancement (SAFE) module that refines multi-scale LiDAR features via self-attention; (2) A Selective Attention-driven Multi-modal Fusion (SAMMF) module that adaptively selects and fuses the most complementary HSI and LiDAR features at the fusion stage; and (3) A cross-domain few-shot learning strategy that alternates meta-learning between domains for effective knowledge transfer. Extensive experiments under an extreme few-shot setting (5 labeled samples per class) show PS2A-FSLNet achieves overall accuracy improvements of 0. 92% on Houston2013, 0. 27% on Trento, and 0. 58% on the MUUFL dataset, which significantly demonstrates the advancement of the proposed method in hyperspectral and LiDAR fusion classification. The code will be available at https: //github. com/TingtingGeng/PS2A-FSLNet.

Details DOI

AAAI Conference 2025 Conference Paper

Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection

Linlin Zong
Wenmin Lin
Jiahui Zhou
Xinyue Liu
Xianchao Zhang
Bo Xu
Shimin Wu

Detecting fake news in short videos is crucial for combating misinformation. Existing methods utilize topic modeling and co-attention mechanism, overlooking the modality heterogeneity and resulting in suboptimal performance. To address this issue, we introduce Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News detection (TGFC-SVFN). TGFC-SVFN leverages modality bias removal and teacher-model-enhanced inter-modal knowledge distillation to integrate the heterogeneous modalities in short videos. Specifically, we use causality-based reasoning prompts guided text as teacher model, which then transfers knowledge to the video and audio student models. Subsequently, a multi-head attention mechanism is employed to fuse information from different modalities. In each module, we utilize fine-grained counterfactual inference based on a diffusion model to eliminate modality bias. Experimental results on publicly available fake short video news datasets demonstrate that our method outperforms state-of-the-art techniques.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Unlocking the Potential of Reverse Distillation for Anomaly Detection

Xinyue Liu
Jianyuan Wang
Biao Leng
Shuo Zhang

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To address this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student network, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student's ability to generate normal features and optimizes the teacher's differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD’s potential.

PDF Details DOI

AAAI Conference 2024 Conference Paper

A Goal Interaction Graph Planning Framework for Conversational Recommendation

Xiaotong Zhang
Xuefang Jia
Han Liu
Xinyue Liu
Xianchao Zhang

Multi-goal conversational recommender system (MG-CRS) which is more in line with realistic scenarios has attracted a lot of attention. MG-CRS can dynamically capture the demands of users in conversation, continuously engage their interests, and make recommendations. The key of accomplishing these tasks is to plan a reasonable goal sequence which can naturally guide the user to accept the recommended goal. Previous works have demonstrated that mining the correlations of goals from the goal sequences in the dialogue corpus is helpful for recommending the goal that the user is interested in. However, they independently model correlations for each level of goal (i.e., goal type or entity) and neglect the order of goals appear in the dialogue. In this paper, we propose a goal interaction graph planning framework which constructs a directed heterogeneous graph to flexibly model the correlations between any level of goals and retain the order of goals. We design a goal interaction graph learning module to model the goal correlations and propagate goal representations via directed edges, then use an encoder and a dual-way fusion decoder to extract the most relevant information with the current goal from the conversation and domain knowledge, making the next-goal prediction fully exploit the prior goal correlations and user feedback. Finally we generate engaging responses based on the predicted goal sequence to complete the recommendation task. Experiments on two benchmark datasets show that our method achieves significant improvements in both the goal planning and response generation tasks.

PDF Details DOI

ICLR Conference 2024 Conference Paper

General Stability Analysis for Zeroth-Order Optimization Algorithms

Xinyue Liu
Hualin Zhang
Bin Gu 0001
Hong Chen 0004

Zeroth-order optimization algorithms are widely used for black-box optimization problems, such as those in machine learning and prompt engineering, where the gradients are approximated using function evaluations. Recently, a generalization result was provided for zeroth-order stochastic gradient descent (SGD) algorithms through stability analysis. However, this result was limited to the vanilla 2-point zeroth-order estimate of Gaussian distribution used in SGD algorithms. To address these limitations, we propose a general proof framework for stability analysis that applies to convex, strongly convex, and non-convex conditions, and yields results for popular zeroth-order optimization algorithms, including SGD, GD, and SVRG, as well as various zeroth-order estimates, such as 1-point and 2-point with different distributions and coordinate estimates. Our general analysis shows that coordinate estimation can lead to tighter generalization bounds for SGD, GD, and SVRG versions of zeroth-order optimization algorithms, due to the smaller expansion brought by coordinate estimates to stability analysis.

Details

AAAI Conference 2024 Conference Paper

Video-Context Aligned Transformer for Video Question Answering

Linlin Zong
Jiahui Wan
Xianchao Zhang
Xinyue Liu
Wenxin Liang
Bo Xu

Video question answering involves understanding video content to generate accurate answers to questions. Recent studies have successfully modeled video features and achieved diverse multimodal interaction, yielding impressive outcomes. However, they have overlooked the fact that the video contains richer instances and events beyond the scope of the stated question. Extremely imbalanced alignment of information from both sides leads to significant instability in reasoning. To address this concern, we propose the Video-Context Aligned Transformer (V-CAT), which leverages the context to achieve semantic and content alignment between video and question. Specifically, the video and text are encoded into a shared semantic space initially. We apply contrastive learning to global video token and context token to enhance the semantic alignment. Then, the pooled context feature is utilized to obtain corresponding visual content. Finally, the answer is decoded by integrating the refined video and question features. We evaluate the effectiveness of V-CAT on MSVD-QA and MSRVTT-QA dataset, both achieving state-of-the-art performance. Extended experiments further analyze and demonstrate the effectiveness of each proposed module.

PDF Details DOI

AIIM Journal 2021 Journal Article

A progressive deep wavelet cascade classification model for epilepsy detection

Hong He
Xinyue Liu
Yong Hao

Automatic epileptic seizure detection according to EEG recordings is helpful for neurologists to identify an epilepsy occurrence in the initial anti-epileptic treatment. To quickly and accurately detect epilepsy, we proposed a progressive deep wavelet cascade classification model (PDWC) based on the discrete wavelet transform (DWT) and Random Forest (RF). Different from current deep networks, the PDWC mimics the progressive object identification process of human beings with recognition cycles. In every cycle, enhanced wavelet energy features at a specific scale were extracted by DWT and input into a set of cascade RF classifiers to realize one recognition. The recognition accuracy of PDWC is gradually improved by the fusion of classification results produced by multiple recognition cycles. Moreover, the cascade structure of PDWC can be automatically determined by the classification accuracy increment between layers. To verify the performance of the PDWC, we respectively applied five traditional schemes and four deep learning schemes to four public datasets. The results show that the PDWC is not only superior than five traditional schemes, including KNN, Bayes, DT, SVM, and RF, but also better than deep learning methods, i. e. convolutional neural network (CNN), Long Short-Term Memory (LSTM), multi-Grained Cascade Forest (gcForest) and wavelet cascade model (WCM). The mean accuracy of PDWC for all subjects of all datasets reaches to 0. 9914. With a flexible structure and less parameters, the PDWC is more suitable for the epilepsy detection of diverse EEG signals.

Details DOI

AAAI Conference 2018 Conference Paper

Weighted Multi-View Spectral Clustering Based on Spectral Perturbation

Linlin Zong
Xianchao Zhang
Xinyue Liu
Hong Yu

Considering the diversity of the views, assigning the multiviews with different weights is important to multi-view clustering. Several multi-view clustering algorithms have been proposed to assign different weights to the views. However, the existing weighting schemes do not simultaneously consider the characteristic of multi-view clustering and the characteristic of related single-view clustering. In this paper, based on the spectral perturbation theory of spectral clustering, we propose a weighted multi-view spectral clustering algorithm which employs the spectral perturbation to model the weights of the views. The proposed weighting scheme follows the two basic principles: 1) the clustering results on each view should be close to the consensus clustering result, and 2) views with similar clustering results should be assigned similar weights. According to spectral perturbation theory, the largest canonical angle is used to measure the difference between spectral clustering results. In this way, the weighting scheme can be formulated into a standard quadratic programming problem. Experimental results demonstrate the superiority of the proposed algorithm.

PDF Details

AAAI Conference 2015 Conference Paper

Constrained NMF-Based Multi-View Clustering on Unmapped Data

Xianchao Zhang
Linlin Zong
Xinyue Liu
Hong Yu

Existing multi-view clustering algorithms require that the data is completely or partially mapped between each pair of views. However, this requirement could not be satisﬁed in most practical settings. In this paper, we tackle the problem of multi-view clustering for unmapped data in the framework of NMF based clustering. With the help of inter-view constraints, we deﬁne the disagreement between each pair of views by the fact that the indicator vectors of two instances from two different views should be similar if they belong to the same cluster and dissimilar otherwise. The overall objective of our algorithm is to minimize the loss function of NMF in each view as well as the disagreement between each pair of views. Experimental results show that, with a small number of constraints, the proposed algorithm gets good performance on unmapped data, and outperforms existing algorithms on partially mapped data and completely mapped data.

PDF Details

AAAI Conference 2014 Conference Paper

Novel Density-Based Clustering Algorithms for Uncertain Data

Xianchao Zhang
Han Liu
Xiaotong Zhang
Xinyue Liu

Density-based techniques seem promising for handling data uncertainty in uncertain data clustering. Nevertheless, some issues have not been addressed well in existing algorithms. In this paper, we firstly propose a novel density-based uncertain data clustering algorithm, which improves upon existing algorithms from the following two aspects: (1) it employs an exact method to compute the probability that the distance between two uncertain objects is less than or equal to a boundary value, instead of the sampling-based method in previous work; (2) it introduces new definitions of core object probability and direct reachability probability, thus reducing the complexity and avoiding sampling. We then further improve the algorithm by using a novel assignment strategy to ensure that every object will be assigned to the most appropriate cluster. Experimental results show the superiority of our proposed algorithms over existing ones.

PDF Details