Author name cluster

Yanan Cao

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.

15 papers

1 author row

AAAI Conference 2026 Conference Paper

Breaking One-Size-Fits-All: Revisiting Out-of-Distribution Detection on Graphs Under Diverse Distribution Shifts

Chuancheng Song
Hanyang Shen
Yan Dong
Xixun Lin
Yanmin Shang
Yanan Cao

Graph OOD detection is crucial in open-world scenarios, where OOD samples may manifest in diverse forms such as open-set deviations, feature-similar shifts, and structural anomalies, each exhibiting distinct geometric characteristics. However, most existing methods adopt a one-size-fits-all geometric assumption (typically Euclidean space), which inadequately captures the diverse nature of real-world distribution shifts. Therefore, adaptively selecting geometric spaces according to the properties of OOD samples is critical for their effective representation and reliable identification. Motivated by this, we revisit the graph OOD detection task under diverse distribution shifts and propose UniGOD, a unified framework serving as a graph foundation model for this task. UniGOD comprises two core modules: GeoUP and DynEVO. GeoUP module adaptively perceives the geometric space (such as Euclidean, hyperbolic, and hyperspherical space) by learning the curvature k of Riemannian manifolds. DynEVO module leverages the dynamic nature of neural SDEs to reveal pronounced uncertainty differences between ID/OOD samples, which are reflected in the divergent evolutionary trajectories of node embeddings induced by k-GNN iterations. With the geometry-dynamics coupling mechanism of the above two modules, UniGOD effectively captures the diverse distribution shifts. Extensive experiments demonstrate its superior performance over existing SOTA methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MetaGDPO: Alleviating Catastrophic Forgetting with Metacognitive Knowledge Through Group Direct Preference Optimization

Lanxue Zhang
Yuqiang Xie
Fang Fang
Fanglong Dong
Rui Liu
Yanan Cao

Large Language Models demonstrate strong reasoning capabilities, which can be effectively compressed into smaller models. However, existing datasets and fine-tuning approaches still face challenges that lead to catastrophic forgetting, particularly for models smaller than 8B. First, most datasets typically ignore the relationship between training data knowledge and the model's inherent abilities, making it difficult to preserve prior knowledge. Second, conventional training objectives often fail to constrain inherent knowledge preservation, which can result in forgetting of previously learned skills. To address these issues, we propose a comprehensive solution that alleviates catastrophic forgetting from both the data and fine-tuning approach perspectives. On the data side, we construct a dataset of 5K instances that covers multiple reasoning tasks and incorporates metacognitive knowledge, making it more tolerant and effective for distillation into smaller models. We annotate the metacognitive knowledge required to solve each question and filter the data based on task knowledge and the model's inherent skills. On the training side, we introduce GDPO (Group Direction Preference Optimization), which is better suited for resource-limited scenarios and can efficiently approximate the performance of GRPO. Guided by the large model and by implicitly constraining the optimization path through a reference model, GDPO enables more effective knowledge transfer from the large model and constrains excessive parameter drift. Extensive experiments demonstrate that our approach significantly alleviates catastrophic forgetting and improves reasoning performance on smaller models.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models

Yu Liu
Xixun Lin
Yanmin Shang
Yangxi Li
Shi Wang
Yanan Cao

Knowledge graph reasoning (KGR) is the task of inferring new knowledge by performing logical deductions on knowledge graphs. Recently, large language models (LLMs) have demonstrated remarkable performance in complex reasoning tasks. Despite promising success, current LLM-based KGR methods still face two critical limitations. First, existing methods often extract reasoning paths indiscriminately, without assessing their different importance, which may introduce irrelevant noise that misleads LLMs. Second, while some methods leverage LLMs to dynamically explore potential reasoning paths, they require high retrieval demands and frequent LLM calls. To address these limitations, we propose PathMind, a novel framework designed to enhance faithful and interpretable reasoning by selectively guiding LLMs with important reasoning paths. Specifically, PathMind follows a "Retrieve-Prioritize-Reason" paradigm. First, it retrieves a query subgraph from KG through the retrieval module. Next, it introduces a path prioritization mechanism that identifies important reasoning paths using a semantic-aware path priority function, which simultaneously considers the accumulative cost and the estimated future cost for reaching the target. Finally, PathMind generates accurate and logically consistent responses via a dual-phase training strategy, including task-specific instruction tuning and path-wise preference alignment. Extensive experiments on benchmark datasets demonstrate that PathMind consistently outperforms competitive baselines, particularly on complex reasoning tasks with fewer input tokens, by identifying essential reasoning paths.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

Xiaowei Zhu
Yubing Ren
Fang Fang
Qingfeng Tan
Shi Wang
Yanan Cao

The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring classification boundaries and making accurate detection increasingly challenging. To address the above challenges, we propose a DNA-inspired perspective, leveraging a repair-based process to directly and interpretably capture the intrinsic differences between human-written and AI-generated text. Building on this perspective, we introduce DNA-DetectLLM, a zero-shot detection method for distinguishing AI-generated and human-written text. The method constructs an ideal AI-generated sequence for each input, iteratively repairs non-optimal tokens, and quantifies the cumulative repair effort as an interpretable detection signal. Empirical evaluations demonstrate that our method achieves state-of-the-art detection performance and exhibits strong robustness against various adversarial attacks and input lengths. Specifically, DNA-DetectLLM achieves relative improvements of 5. 55\% in AUROC and 2. 08\% in F1 score across multiple public benchmark datasets. Code and data are available at https: //github. com/Xiaoweizhu57/DNA-DetectLLM.

PDF Details

NeurIPS Conference 2025 Conference Paper

LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models

Hao Sun
Huailiang Peng
Qiong Dai
Xu Bai
Yanan Cao

Activation steering is an efficient technique for aligning the behavior of large language models (LLMs) by injecting steering vectors directly into a model’s residual stream during inference. A pivotal challenge in this approach lies in choosing the right layers to intervene, as inappropriate selection can undermine behavioral alignment and even impair the model’s language fluency and other core capabilities. While single-layer steering allows straightforward evaluation on held-out data to identify the "best" layer, it offers only limited alignment improvements. Multi-layer steering promises stronger control but faces a combinatorial explosion of possible layer subsets, making exhaustive search impractical. To address these challenges, we propose LayerNavigator, which provides a principled and promising layer selection strategy. The core innovation of LayerNavigator lies in its novel, quantifiable criterion that evaluates each layer's steerability by jointly considering two key aspects: discriminability and consistency. By reusing the activations computed during steering vector generation, LayerNavigator requires no extra data and adds negligible overhead. Comprehensive experiments show that LayerNavigator achieves not only superior alignment but also greater scalability and interpretability compared to existing strategies. Our code is available at https: //github. com/Bryson-Arrot/LayerNavigator

PDF Details

NeurIPS Conference 2025 Conference Paper

NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables

Lanrui Wang
Mingyu Zheng
Hongyin Tang
Zheng Lin
Yanan Cao
Jingang Wang
Xunliang Cai
Weiping Wang

Processing structured tabular data, particularly large and lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs). However, existing long-context benchmarks like Needle-in-a-Haystack primarily focus on unstructured text, neglecting the challenge of diverse structured tables. Meanwhile, previous tabular benchmarks mainly consider downstream tasks that require high-level reasoning abilities, and overlook models' underlying fine-grained perception of individual table cells, which is crucial for practical and robust LLM-based table applications. To address this gap, we introduce \textsc{NeedleInATable} (NIAT), a new long-context tabular benchmark that treats each table cell as a ``needle'' and requires models to extract the target cell based on cell locations or lookup questions. Our comprehensive evaluation of various LLMs and multimodal LLMs reveals a substantial performance gap between popular downstream tabular tasks and the simpler NIAT task, suggesting that they may rely on dataset-specific correlations or shortcuts to obtain better benchmark results but lack truly robust long-context understanding towards structured tables. Furthermore, we demonstrate that using synthesized NIAT training data can effectively improve performance on both NIAT task and downstream tabular tasks, which validates the importance of NIAT capability for LLMs' genuine table understanding ability. Our data, code and models will be released to facilitate future research.

PDF Details

AAAI Conference 2025 Conference Paper

UniFORM: Towards Unified Framework for Anomaly Detection on Graphs

Chuancheng Song
Xixun Lin
Hanyang Shen
Yanmin Shang
Yanan Cao

Graph anomaly detection has attracted significant attention due to its critical applications, such as identifying money laundering in financial systems and detecting fake reviews on social networks. However, two major challenges persist: (1) anomaly detection at the node, edge, and graph levels is often addressed in isolation, hindering the integration of complementary information to identify anomalies arising from collective behaviors; and (2) the inherent label sparsity in graph data, coupled with the difficulty of obtaining high-quality annotations, exacerbates bias in detection. To address these challenges, we propose UniFORM, a unified self-supervised anomaly detection framework comprising two modules: UIO and UMC. UIO unifies node-, edge-, and graph-level tasks from a subgraph perspective, leveraging an energy-based GNN for iterative multi-granular anomaly detection. UMC enhances meta-learning through contrastive learning and employs Langevin dynamics to generate phantom samples as substitutes for anomalous data, reducing reliance on labeled data. Extensive experiments on real-world datasets demonstrate that UniFORM significantly outperforms state-of-the-art methods across multiple granularities.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models

Yuanxin Liu
Fandong Meng
Zheng Lin
Jiangnan Li
Peng Fu
Yanan Cao
Weiping Wang
Jie Zhou

Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely on the dataset bias and struggle to generalize to out-of-distribution (OOD) data. In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance. Such subnetworks can be found in three scenarios: 1) the fine-tuned PLMs, 2) the raw PLMs and then fine-tuned in isolation, and even inside 3) PLMs without any parameter fine-tuning. However, these results are only obtained in the in-distribution (ID) setting. In this paper, we extend the study on PLMs subnetworks to the OOD setting, investigating whether sparsity and robustness to dataset bias can be achieved simultaneously. To this end, we conduct extensive experiments with the pre-trained BERT model on three natural language understanding (NLU) tasks. Our results demonstrate that \textbf{sparse and robust subnetworks (SRNets) can consistently be found in BERT}, across the aforementioned three scenarios, using different training and compression methods. Furthermore, we explore the upper bound of SRNets using the OOD information and show that \textbf{there exist sparse and almost unbiased BERT subnetworks}. Finally, we present 1) an analytical study that provides insights on how to promote the efficiency of SRNets searching process and 2) a solution to improve subnetworks' performance at high sparsity. The code is available at \url{https: //github. com/llyx97/sparse-and-robust-PLM}.

PDF Details

AAAI Conference 2022 Conference Paper

How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View

Ren Li
Yanan Cao
Qiannan Zhu
Guanqun Bi
Fang Fang
Yi Liu
Qian Li

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (? , r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNNbased KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k- 237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https: //github. com/renli1024/SE-GNN.

PDF Details

IJCAI Conference 2022 Conference Paper

Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge

Jiangnan Li
Fandong Meng
Zheng Lin
Rui Liu
Peng Fu
Yanan Cao
Weiping Wang
Jie Zhou

Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation. In this work, we build conversations as graphs to overcome implicit contextual modelling of the original entailment style. Following the previous work, we further introduce the emotion information into graphs. Emotion information can markedly promote the detection of causal utterances whose emotion is the same as the targeted utterance. However, it is still hard to detect causal utterances with different emotions, especially neutral ones. The reason is that models are limited in reasoning causal clues and passing them between utterances. To alleviate this problem, we introduce social commonsense knowledge (CSK) and propose a Knowledge Enhanced Conversation graph (KEC). KEC propagates the CSK between two utterances. As not all CSK is emotionally suitable for utterances, we therefore propose a sentiment-realized knowledge selecting strategy to filter CSK. To process KEC, we further construct the Knowledge Enhanced Directed Acyclic Graph networks. Experimental results show that our method outperforms baselines and infers more causes with different emotions from the targeted utterance.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Flexible Non-Autoregressive Extractive Summarization with Threshold: How to Extract a Non-Fixed Number of Summary Sentences

Ruipeng Jia
Yanan Cao
Haichao Shi
Fang Fang
Pengfei Yin
Shi Wang

Sentence-level extractive summarization is a fundamental yet challenging task, and recent powerful approaches prefer to pick sentences sorted by the predicted probabilities until the length limit is reached, a. k. a. “Top-K Strategy”. This length limit is fixed based on the validation set, resulting in the lack of flexibility. In this work, we propose a more flexible and accurate non-autoregressive method for single document extractive summarization, extracting a non-fixed number of summary sentences without the sorting step. We call our approach ThresSum as it picks sentences simultaneously and individually from the source document when the predicted probabilities exceed a threshold. During training, the model enhances sentence representation through iterative refinement and the intermediate latent variables receive some weak supervision with soft labels, which are generated progressively by adjusting the temperature with a knowledge distillation algorithm. Specifically, the temperature is initialized with high value and drops along with the iteration until a temperature of 1. Experimental results on CNN/DM and NYT datasets have demonstrated the effectiveness of ThresSum, which significantly outperforms BERTSUMEXT with a substantial improvement of 0. 74 ROUGE-1 score on CNN/DM.

PDF Details

NeurIPS Conference 2020 Conference Paper

Graph Geometry Interaction Learning

Shichao Zhu
Shirui Pan
Chuan Zhou
Jia Wu
Yanan Cao
Bin Wang

While numerous approaches have been developed to embed graphs into either Euclidean or hyperbolic spaces, they do not fully utilize the information available in graphs, or lack the flexibility to model intrinsic complex graph geometry. To utilize the strength of both Euclidean and hyperbolic geometries, we develop a novel Geometry Interaction Learning (GIL) method for graphs, a well-suited and efficient alternative for learning abundant geometric properties in graph. GIL captures a more informative internal structural features with low dimensions while maintaining conformal invariance of each space. Furthermore, our method endows each node the freedom to determine the importance of each geometry space via a flexible dual feature interaction learning and probability assembling mechanism. Promising experimental results are presented for five benchmark datasets on node classification and link prediction tasks.

PDF Details

AAAI Conference 2020 Conference Paper

Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network

Xiaoxue Li
Yanmin Shang
Yanan Cao
Yangxi Li
Jianlong Tan
Yanbing Liu

Anchor Link Prediction (ALP) across heterogeneous networks plays a pivotal role in inter-network applications. The difﬁculty of anchor link prediction in heterogeneous networks lies in how to consider the factors affecting nodes alignment comprehensively. In recent years, predicting anchor links based on network embedding has become the main trend. For heterogeneous networks, previous anchor link prediction methods ﬁrst integrate various types of nodes associated with a user node to obtain a fusion embedding vector from global perspective, and then predict anchor links based on the similarity between fusion vectors corresponding with different user nodes. However, the fusion vector ignores effects of the local type information on user nodes alignment. To address the challenge, we propose a novel type-aware anchor link prediction across heterogeneous networks (TALP), which models the effect of type information and fusion information on user nodes alignment from local and global perspective simultaneously. TALP can solve the network embedding and type-aware alignment under a uniﬁed optimization framework based on a two-layer graph attention architecture. Through extensive experiments on real heterogeneous network datasets, we demonstrate that TALP signiﬁcantly outperforms the state-of-the-art methods.

PDF Details

AAAI Conference 2014 Conference Paper

Combining Heterogenous Social and Geographical Information for Event Recommendation

Zhi Qiao
Peng Zhang
Yanan Cao
Chuan Zhou
Li Guo
Binxing Fang

With the rapid growth of event-based social networks (EBSNs) like Meetup, the demand for event recommendation becomes increasingly urgent. In EBSNs, event recommendation plays a central role in recommending the most relevant events to users who are likely to participate in. Different from traditional recommendation problems, event recommendation encounters three new types of information, i. e. , heterogenous online+offline social relationships, geographical features of events and implicit rating data from users. Yet combining the three types of data for offline event recommendation has not been considered. Therefore, we present a Bayesian latent factor model that can unify these data for event recommendation. Experimental results on real-world data sets show the performance of our method.

PDF Details

AAAI Conference 2014 Conference Paper

Event Recommendation in Event-Based Social Networks

Zhi Qiao
Peng Zhang
Chuan Zhou
Yanan Cao
Li Guo
Yanchuan Zhang

With the rapid growth of event-based social networks, the demand of event recommendation becomes increasingly important. Different from classic recommendation problems, event recommendation generally faces the problems of heterogenous online and offline social relationships among users and implicit feedback data. In this paper, we present a baysian probability model that can fully unleash the power of heterogenous social relations and efficiently tackle with implicit feedback characteristic for event recommendation. Experimental results on several real-world datasets demonstrate the utility of our method.

PDF Details