Author name cluster

Xin Huang

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.

34 papers

2 author rows

AAAI Conference 2026 Conference Paper

AdaMCoT: Rethinking Cross-Lingual Factual Reasoning Through Adaptive Multilingual Chain-of-Thought

Zheng Weihua
Xin Huang
Zhengyuan Liu
Tarun Kumar Vangani
Bowei Zou
Xiyan Tao
Yuhao Wu
AiTi Aw

Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. While these models show strong reasoning abilities, their performance varies significantly across languages due to imbalanced training data distribution. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce **AdaMCoT** (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary “thinking languages” before generating target-language responses. AdaMCoT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model’s hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high- and low-resource languages while maintaining cultural and linguistic nuances.

PDF Details DOI

JBHI Journal 2026 Journal Article

Delay-Aware Cross-Modal Knowledge Distillation for Driver Vigilance Estimation: Toward Practical Edge Deployment

Yu Sun
Shiwu Li
Tongtong Jin
Yiming Bie
Mengzhu Guo
Minghao Fu
Xin Huang

Efficient vigilance estimation in driving scenarios requires a balance between model performance and practicality. Electroencephalography (EEG), which can directly reflect brain activity, is widely used for vigilance estimation, but its acquisition process is complicated and difficult to apply to real-world driving. In contrast, physiological signals such as electrooculogram, electrodermal activity, and photoplethysmography have more advantages for practical deployment, but the information they provide is relatively limited. To address the above issues, we propose a delay-aware cross-modal knowledge distillation method. EEG signals are only used to train the teacher model. Then, an information-theoretic criterion based on mutual information and response delay is employed to determine which physiological signals are suitable as student modality for knowledge distillation from the EEG-based teacher model. On this basis, considering the inherent temporal differences caused by different physiological signals with varying sensitivities to cognitive responses, a delay-aware soft alignment mechanism (DASA) is proposed, which handles the temporal misalignment of different physiological signals and captures the asynchronous dynamics of the EEG and other physiological signals through the introduction of learnable delay and spread parameters at the patch level, to achieve soft, temporally-aligned supervision from the teacher to the student model. Finally, an objective function incorporating cross-modal consistency, patch level alignment, and smooth regularization is designed to support the effective training of the proposed cross-modal knowledge distillation method. Extensive experiments on MMV and SEED-VIG datasets validates that the proposed method outperforms existing methods in terms of estimation accuracy and temporal alignment while maintaining the real-time performance required for edge deployment.

Details DOI

AAAI Conference 2025 Conference Paper

Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval

Xin Huang
Shilong Wang
Tong Jia
Zhihang Gou
Jingjing Li

In the era of big data, cross-modal retrieval is increasingly important in research and application. Given the latent complexity and non-intuitive nature of cross-modal relationships, leveraging external knowledge such as large models has become a popular approach to facilitate modality alignment. Existing methods typically address these challenges by fine-tuning model encoders or using a fixed number of prompts. However, these approaches struggle with the significant information asymmetry between image-text pairs and the high distribution diversity of image data. These limitations not only introduce noise during training but also reduce the accuracy and generalization capabilities in cross-modal retrieval tasks. To address the above issues, this paper proposes Adaptive Prompt-Based Semantic Embedding with Inspired Potential of Implicit Knowledge (APSE-IPIK). On one hand, we propose an inspired potential strategy to extract fine-grained and multi-perspective text descriptions from large-scale pre-trained multimodal models, which can be seen as implicit knowledge injection. These descriptions are integrated into the visual-semantic embedding through cross-modal semantic alignment with images, balancing the information asymmetry between modalities and reducing the embedding of inaccurate mapping relationships. On the other hand, we construct an instance-level query-based prompt pool strategy to adaptively extract the most relevant prompts, addressing alignment biases caused by intra-modal (especially image) data diversity and improving alignment accuracy. Extensive experiments are conducted on two widely used datasets, Flickr30k and MSCOCO, which show the effectiveness of the proposed method.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Bright-NeRF: Brightening Neural Radiance Field with Color Restoration from Low-Light RAW Images

Min Wang
Xin Huang
Guoqing Zhou
Qifeng Guo
Qing Wang

Neural Radiance Fields (NeRF) have demonstrated prominent performance in novel view synthesis tasks. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene contents in low-light environments where images typically exhibit significant noise and severe color distortion. To address these challenges, we propose a novel approach, Bright-NeRF, which learns enhanced and high-quality radiance fields from multi-view low-light RAW images in an unsupervised manner. Our method simultaneously achieves color restoration, denoising, and enhanced novel view synthesis. Specifically, we leverage a physically-inspired model of the sensor's response to illumination and introduce a chromatic adaptation loss to constrain the learning of response, enabling consistent color perception of objects regardless of lighting conditions. We further utilize the RAW data's properties to expose the scene's intensity automatically. Additionally, we have collected a multi-view low-light RAW image dataset of real-world scenes to advance research in this field. Experimental results demonstrate that our proposed method significantly outperforms existing 2D and 3D approaches. Our code and dataset will be made publicly available.

PDF Details DOI

ICRA Conference 2025 Conference Paper

Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-Based Autonomous Driving

Yichen Xie 0002
Hongge Chen
Gregory P. Meyer
Yong Jae Lee
Eric M. Wolff
Masayoshi Tomizuka
Wei Zhan
Yuning Chai

Multi-frame temporal inputs are important for vision-based autonomous driving. Observations from different angles enable the recovery of 3 D object states from 2 D images as long as we can identify the same instance from different input frames. However, the dynamic nature of driving scenes leads to significant variance in the instance appearance and shape captured by the cameras at different time steps. To this end, we propose a novel contrastive learning algorithm, Cohere3D, to learn coherent instance representations robust to the changes of distance and perspective in a long-term temporal sequence without any human annotations. In the pretraining stage, raw point clouds from LiDAR sensors are utilized to construct the instance-wise long-term temporal correspondence, which serves as guidance for the extraction of instance-level representation from the vision-based bird's-eye-view (BEV) feature map. Cohere3D encourages consistent representation for the same instance at different frames but distinguishes between different instances. We validate the effectiveness and generalizability of our algorithm by finetuning the pretrained model across key downstream autonomous driving tasks: perception, mapping, prediction, and planning. Results show a notable improvement in both data efficiency and final performance in all these tasks.

Details

ICML Conference 2025 Conference Paper

DriveGPT: Scaling Autoregressive Behavior Models for Driving

Xin Huang
Eric M. Wolff
Paul Vernaza
Tung Phan-Minh
Hongge Chen
David S. Hayden
Mark Edmonds
Brian Pierce

We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.

Details

IJCAI Conference 2025 Conference Paper

Dynamic Seed-GrowthCM: A Dynamic Benefit-Oriented Algorithm for Core Maximization on Large Graphs

Dongyuan Ma
Dongxiao He
Xin Huang

The k-core has garnered significant attention in recent research as an effective measure of node importance within a graph. A k-core is defined as the maximal induced subgraph where each node has a degree of at least k. This paper addresses the core maximization problem: given a graph G, an integer k, and a budget b, the objective is to insert b new distinct edges into G to maximize the size of its k-core. This problem is theoretically proven to be NP-hard and APX-hard. However, the existing heuristic methods often struggle to achieve a good balance between efficiency and answer quality. In this paper, we propose a novel dynamic approach that, for the first time, uncovers the dynamic changes in node degrees. We introduce a new concept using the contribution of edges across different λ-shell components to the final solution. Based on these findings, we present the Dynamic Seed-GrowthCM method. This method selects the λ-shell component with the largest estimated benefit as the initial seed. In each iteration, depending on complete/partial growth, either a new seed is incorporated into the solution, or an existing seed undergoes growth, becoming a larger seed by adding connected components of the λ-shell component to the solution. Experimental results on ten datasets demonstrate that our algorithm significantly outperforms state-of-the-art methods in terms of solution quality on large graphs, while achieving a high computational efficiency.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

Haolong Yan
Yeqing Shen
Xin Huang
Jia Wang
Kaijun Tan
Zhixuan Liang
Hongxin Li
Zheng Ge

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents.

PDF Details

AAAI Conference 2025 Conference Paper

Improved Maximin Share Approximations for Chores by Bin Packing

Jugal Garg
Xin Huang
Erel Segal-Halevi

We study fair division of indivisible chores among n agents with additive cost functions using the popular fairness notion of maximin share (MMS). Since MMS allocations do not always exist for more than two agents, the goal has been to improve its approximations and identify interesting special cases where MMS allocations exist. We show the existence of · 1-out-of-9n/11 MMS allocations, which improves the state-of-the-art factor of 1-out-of-3n/4. · MMS allocations for factored instances, which resolves an open question posed by Ebadian et al. (2021). · 15/13-MMS allocations for personalized bivalued instances, improving the state-of-the-art factor of 13/11. We achieve these results by leveraging the HFFD algorithm of Huang and Lu (2021). Our approach also provides polynomial-time algorithms for computing an MMS allocation for factored instances and a 15/13-MMS allocation for personalized bivalued instances.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction

Wenbo Shang
Zihan Feng
Yang Yajun
Xin Huang

Information diffusion prediction, which aims to forecast future infected users during the information spreading process on social platforms, is a challenging and critical task for public opinion analysis. With the development of social platforms, mass communication has become increasingly widespread. However, most existing methods based on GNNs and sequence models mainly focus on structural and temporal patterns in social networks, suffering from spurious diffusion connections and insufficient information for the diffusion analysis. We leverage strong reasoning capability of LLMs and develop a LL**M**-based causal framework for d**i**ffusion inf**l**uence **d**erivation (MILD). Comprehensively integrating four key factors of social diffusion, i. e. , connections, active timelines, user profiles, and comments, MILD causally infers authentic diffusion links to construct a diffusion influence graph $G_I$. To validate the quality and reliability of our constructed graph $G_I$, we proposed a newly designed set of evaluation metrics w. r. t. diffusion prediction. We show MILD provides a reliable information diffusion structure that 12% absolutely better than the social network structure and achieves the state-of-the-art performance on diffusion prediction. MILD is expected to contribute to high-quality, more explainable, and more trustworthy public opinion analysis.

PDF Details

AAAI Conference 2025 Conference Paper

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning

Wenwen Zhuang
Xin Huang
Xiantao Zhang
Jin Zeng

Multimodal Large Language Models (MLLMs) excel in solving text-based mathematical problems, but they struggle with mathematical diagrams since they are primarily trained on natural scene images. For humans, visual aids generally enhance problem-solving, but MLLMs perform worse as information shifts from textual to visual modality. This decline is mainly due to their shortcomings in aligning images and text. To tackle aforementioned challenges, we propose Math-PUMA, a methodology focused on Progressive Upward Multimodal Alignment. This approach is designed to improve the mathematical reasoning skills of MLLMs through a three-stage training process, with the second stage being the critical alignment stage. We first enhance the language model's mathematical reasoning capabilities with extensive set of textual mathematical problems. We then construct a multimodal dataset with varying degrees of textual and visual information, creating data pairs by presenting each problem in at least two forms. By leveraging the Kullback-Leibler (KL) divergence of next-token prediction distributions to align visual and textual modalities, consistent problem-solving abilities are ensured. Finally, we utilize multimodal instruction tuning for MLLMs with high-quality multimodal data. Experimental results on multiple mathematical reasoning benchmarks demonstrate that the MLLMs trained with Math-PUMA surpass most open-source MLLMs. Our approach effectively narrows the performance gap for problems presented in different modalities.

PDF Details DOI

AAAI Conference 2025 Conference Paper

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

Hao Zhou
Zhijun Wang
Shujian Huang
Xin Huang
Xue Han
Junlan Feng
Chao Deng
Weihua Luo

Large Language Models (LLMs) are often English-centric due to the disproportionate distribution of languages in their pre-training data. Enhancing non-English language capabilities through post-pretraining often results in catastrophic forgetting of high-resource languages. Previous methods either achieve good expansion with severe forgetting or slight forgetting with poor expansion, indicating the challenge of balancing language expansion while preventing forgetting. In this paper, we propose a method called MoE-LPR (Mixture-of-Experts with Language Priors Routing) to alleviate this problem. MoE-LPR employs a two-stage training approach to enhance the multilingual capability. First, the model is post-pretrained into a Mixture-of-Experts(MoE) architecture by upcycling, where all the original parameters are frozen and new experts are added. In this stage, we focus improving the ability on expanded languages, without using any original language data. Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages. Evaluations on multiple benchmarks show that MoE-LPR outperforms other post-pretraining methods. Freezing original parameters preserves original language knowledge while adding new experts preserves the learning ability. Reviewing with LPR enables effective utilization of multilingual knowledge within the parameters. Additionally, the MoE architecture maintains the same inference overhead while increasing total model parameters. Extensive experiments demonstrate MoE-LPR’s effectiveness in improving expanded languages and preserving original language proficiency with superior scalability.

PDF Details DOI

AAAI Conference 2025 Conference Paper

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

Hengde Zhu
Xiangyu Kong
Weicheng Xie
Xin Huang
Xilin He
Lu Liu
Linlin Shen
Wei Zhang

In dyadic human-human interactions, individuals may express multiple different facial reactions in response to the same/similar behaviours expressed by their conversational partners depending on their personalised behaviour patterns. As a result, frequently-employed reconstruction loss-based strategies lead the training of previous automatic facial reaction generation (FRG) models to not only suffer from the 'one-to-many mapping' problem, but also fail to comprehensively consider the quality of the generated facial reactions. Besides, none of them considered such personalised behaviour patterns in generating facial reactions. In this paper, we propose the first adversarial FRG model training strategy which jointly learns appropriateness and realism discriminators to provide comprehensive task-specific supervision for training the target facial reaction generators, and reformulates the 'one-to-many (facial reactions) mapping' training problem as a 'one-to-one (distribution) mapping' training task, i.e., the FRG model is trained to output a distribution representing multiple appropriate/plausible facial reaction from each input human behaviour. In addition, our approach also serves as the first offline FRG approach that considers personalised behaviour patterns in generating of target individuals' facial reactions. Experiments show that our PerReactor not only largely outperformed all existing offline solutions for generating more appropriate, diverse and realistic facial reactions, but also is the first approach that can effectively generate personalised appropriate facial reactions.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

PROFIT: A Specialized Optimizer for Deep Fine Tuning

Anirudh Chakravarthy
Shuai Zheng
Xin Huang
Sachithra Hemachandra
Xiao Zhang
Yuning Chai
Zhao Chen

The fine-tuning of pre-trained models has become ubiquitous in generative AI, computer vision, and robotics. Although much attention has been paid to improving the efficiency of fine-tuning model, there has been less scholarship around fine-tuning specifically for improved model performance. To remedy this gap, we present PROFIT, one of the first optimizers designed to incrementally fine-tune converged models on new tasks and/or datasets. Unlike traditional optimizers such as SGD or Adam, which make minimal assumptions due to random initializations, PROFIT takes the properties of a converged model into account explicitly to regularize the optimization process. Employing a temporal gradient-orthogonalization process, PROFIT outperforms fine-tuning methods in various tasks, from image classification to multimodal language model training to large-scale motion prediction. Moreover, PROFIT is encapsulated as a modular optimizer, which makes it easy to integrate directly into any training pipeline with minimal engineering effort.

PDF Details

EAAI Journal 2025 Journal Article

Selecting after sales provider of complex product based on game and matching framework

Xin Huang
Xiaoyan Qi
Xiaojuan Xu

As a strategic enabler of high-end manufacturing, the high-quality evolution of complex equipment is indispensable for any nation aspiring to industrial leadership. After sales service (AS) long relegated to a support function, which has emerged as a decisive determinant of product life-cycle value and, consequently, of this transformative journey. This study therefore investigates the technological innovation of AS for complex products through a Stackelberg game that captures the collaborative dynamics between an original equipment manufacturer (OEM) and an after-sales service provider (ASP). We derive the necessary and sufficient conditions under which an ASP finds participation economically viable, then embed these conditions into a multi-criteria matching framework that links ASP capabilities with spare-part requirements. Leveraging an entropy weighted DEMATEL (Decision-making Trial and Evaluation Laboratory) hybrid and we first quantify the causal salience of matching attributes and build a parsimonious evaluation index system. Next, by explicitly encoding bilateral attribute preferences, we formulate a two-sided matching model that identifies the Pareto-optimal ASP portfolio for any given product architecture. Finally, backward induction over the integrated game-matching structure yields a prescriptive tool that not only screens ASPs but also prescribes contractual levers to sustain long-term co-innovation. The proposed framework thus unifies strategic participation incentives with operational compatibility, offering OEMs a rigorous, implementable roadmap for selecting and governing after-sales partners in the era of servitized, high-stakes manufacturing.

Details DOI

IJCAI Conference 2025 Conference Paper

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models

Xin Huang
Ruibin Li
Tong Jia
Wei Zheng
Ya Wang

Vision-Language Models (VLMs) are essential for multimodal tasks, especially compositional reasoning (CR) tasks, which require distinguishing fine-grained semantic differences between visual and textual embeddings. However, existing methods primarily fine-tune the model by generating text-based hard negative samples, neglecting the importance of image-based negative samples, which results in insufficient training of the visual encoder and ultimately impacts the overall performance of the model. Moreover, negative samples are typically treated uniformly, without considering their difficulty levels, and the alignment of positive samples is insufficient, which leads to challenges in aligning difficult sample pairs. To address these issues, we propose Adaptive Hard Negative Perturbation Learning (AHNPL). AHNPL translates text-based hard negatives into the visual domain to generate semantically disturbed image-based negatives for training the model, thereby enhancing its overall performance. AHNPL also introduces a contrastive learning approach using a multimodal hard negative loss to improve the model's discrimination of hard negatives within each modality and a dynamic margin loss that adjusts the contrastive margin according to sample difficulty to enhance the distinction of challenging sample pairs. Experiments on three public datasets demonstrate that our method effectively boosts VLMs' performance on complex CR tasks. The source code is available at https: //github. com/nynu-BDAI/AHNPL.

PDF Details DOI

AAMAS Conference 2025 Conference Paper

Weighted Envy-free Allocation with Subsidy

Haris Aziz
Xin Huang
Kei Kimura
Indrajit Saha
Zhaohong Sun
Mashbat Suzuki
Makoto Yokoo

We consider the problem of fair allocation of indivisible items with subsidies when agents have weighted entitlements. Specifically, we extend the envy-freeability studied in the unweighted case to the weighted envy-freeability and delve deeper into its properties. We first highlight various important differences from the unweighted case, e. g. , the sufficient conditions that lead to envy-freeability in the unweighted case do not lead to weighted envy-freeability in the weighted case. We then present various results concerning weighted envy-freeability including general characterizations, algorithms for achieving and testing weighted envy-freeability, lower and upper bounds of the amount of subsidies for weighted envy-freeable allocations. Additionally, we design algorithms that ensure weighted envy-freeability while incorporating other fairness properties, such as weighted envy-freeness up to one item transfer.

PDF

AAAI Conference 2024 Conference Paper

G2L-CariGAN: Caricature Generation from Global Structure to Local Features

Xin Huang
Yunfeng Bai
Dong Liang
Feng Tian
Jinyuan Jia

Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character's identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Joint Domain Adaptive Graph Convolutional Network

Niya Yang
Ye Wang
Zhizhi Yu
Dongxiao He
Xin Huang
Di Jin

In the realm of cross-network tasks, graph domain adaptation is an effective tool due to its ability to transfer abundant labels from nodes in the source domain to those in the target domain. Existing adversarial domain adaptation methods mainly focus on domain-wise alignment. These approaches, while effective in mitigating the marginal distribution shift between the two domains, often ignore the integral aspect of structural alignment, potentially leading to negative transfer. To address this issue, we propose a joint adversarial domain adaptive graph convolutional network (JDA-GCN) that is uniquely augmented with structural graph alignment, so as to enhance the efficacy of knowledge transfer. Specifically, we construct a structural graph to delineate the interconnections among nodes within identical categories across the source and target domains. To further refine node representation, we integrate the local consistency matrix with the global consistency matrix, thereby leveraging the learning of the sub-structure similarity of nodes to enable more robust and effective representation of nodes. Empirical evaluation on diverse real-world datasets substantiates the superiority of our proposed method, marking a significant advancement over existing state-of-the-art graph domain adaptation algorithms.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Privileged Prior Information Distillation for Image Matting

Cheng Lyu
Jiake Xie
Bo Xu
Cheng Lu
Han Huang
Xin Huang
Ming Wu
Chuang Zhang

Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance. In this paper, we propose a novel framework named Privileged Prior Information Distillation for Image Matting (PPID-IM) that can effectively transfer privileged prior environment-aware information to improve the performance of trimap-free students in solving hard foregrounds. The prior information of trimap regulates only the teacher model during the training stage, while not being fed into the student network during actual inference. To achieve effective privileged cross-modality (i.e. trimap and RGB) information distillation, we introduce a Cross-Level Semantic Distillation (CLSD) module that reinforces the students with more knowledgeable semantic representations and environment-aware information. We also propose an Attention-Guided Local Distillation module that efficiently transfers privileged local attributes from the trimap-based teacher to trimap-free students for the guidance of local-region optimization. Extensive experiments demonstrate the effectiveness and superiority of our PPID on image matting. The code will be released soon.

PDF Details DOI

TIST Journal 2022 Journal Article

Graph Neural Networks: Taxonomy, Advances, and Trends

Yu Zhou
Haixia Zheng
Xin Huang
Shufeng Hao
Dengao Li
Jumin Zhao

Graph neural networks provide a powerful toolkit for embedding real-world graphs into low-dimensional spaces according to specific tasks. Up to now, there have been several surveys on this topic. However, they usually lay emphasis on different angles so that the readers cannot see a panorama of the graph neural networks. This survey aims to overcome this limitation and provide a systematic and comprehensive review on the graph neural networks. First of all, we provide a novel taxonomy for the graph neural networks, and then refer to up to 327 relevant literatures to show the panorama of the graph neural networks. All of them are classified into the corresponding categories. In order to drive the graph neural networks into a new stage, we summarize four future research directions so as to overcome the challenges faced. It is expected that more and more scholars can understand and exploit the graph neural networks and use them in their research community.

Details DOI

IJCAI Conference 2020 Conference Paper

A Two-level Reinforcement Learning Algorithm for Ambiguous Mean-variance Portfolio Selection Problem

Xin Huang
Duan Li

Traditional modeling on the mean-variance portfolio selection often assumes a full knowledge on statistics of assets' returns. It is, however, not always the case in real financial markets. This paper deals with an ambiguous mean-variance portfolio selection problem with a mixture model on the returns of risky assets, where the proportions of different component distributions are assumed to be unknown to the investor, but being constants (in any time instant). Taking into consideration the updates of proportions from future observations is essential to find an optimal policy with active learning feature, but makes the problem intractable when we adopt the classical methods. Using reinforcement learning, we derive an investment policy with a learning feature in a two-level framework. In the lower level, the time-decomposed approach (dynamic programming) is adopted to solve a family of scenario subcases where in each case the series of component distributions along multiple time periods is specified. At the upper level, a scenario-decomposed approach (progressive hedging algorithm) is applied in order to iteratively aggregate the scenario solutions from the lower layer based on the current knowledge on proportions, and this two-level solution framework is repeated in a manner of rolling horizon. We carry out experimental studies to illustrate the execution of our policy scheme.

PDF Details DOI

TCS Journal 2020 Journal Article

Binary-decision-diagram-based decomposition of Boolean functions into reversible logic elements

Jia Lee
Ya-Hui Ye
Xin Huang
Rui-Long Yang

A binary decision diagram (BDDs) is a compact data structure used to represent a Boolean function, which facilitates scalable constructions of Boolean functions using reversible logic gates. Motivated by the scalable synthesis approach, this paper proposes an effective scheme for transforming the BDD representation of a Boolean function into a reversible circuit composed by reversible logic elements. Unlike a logic gate, a reversible logic element carries a memory to record a finite number of states. Especially, logic circuits composed by reversible elements can operate in asynchronous mode, thereby no need of a clock signal to drive all elements operating simultaneously.

Details DOI

AAAI Conference 2020 Conference Paper

Hyperbolic Interaction Model for Hierarchical Multi-Label Classification

Boli Chen
Xin Huang
Lin Xiao
Zixin Cai
Liping Jing

Different from the traditional classiﬁcation tasks which assume mutual exclusion of labels, hierarchical multi-label classiﬁcation (HMLC) aims to assign multiple labels to every instance with the labels organized under hierarchical relations. Besides the labels, since linguistic ontologies are intrinsic hierarchies, the conceptual relations between words can also form hierarchical structures. Thus it can be a challenge to learn mappings from word hierarchies to label hierarchies. We propose to model the word and label hierarchies by embedding them jointly in the hyperbolic space. The main reason is that the tree-likeness of the hyperbolic space matches the complexity of symbolic data with hierarchical structures. A new Hyperbolic Interaction Model (HyperIM) is designed to learn the label-aware document representations and make predictions for HMLC. Extensive experiments are conducted on three benchmark datasets. The results have demonstrated that the new model can realistically capture the complex data structures and further improve the performance for HMLC comparing with the state-of-the-art methods. To facilitate future research, our code is publicly available.

PDF Details

IJCAI Conference 2019 Conference Paper

Fast Algorithm for K-Truss Discovery on Public-Private Graphs

Soroush Ebadian
Xin Huang

In public-private graphs, users share one public graph and have their own private graphs. A private graph consists of personal private contacts that only can be visible to its owner, e. g. , hidden friend lists on Facebook and secret following on Sina Weibo. However, existing public-private analytic algorithms have not yet investigated the dense subgraph discovery of k-truss, where each edge is contained in at least k-2 triangles. This paper aims at finding k-truss efficiently in public-private graphs. The core of our solution is a novel algorithm to update k-truss with node insertions. We develop a classification-based hybrid strategy of node insertions and edge insertions to incrementally compute k-truss in public-private graphs. Extensive experiments validate the superiority of our proposed algorithms against state-of-the-art methods on real-world datasets.

PDF Details

IJCAI Conference 2019 Conference Paper

IRC-GAN: Introspective Recurrent Convolutional GAN for Text-to-video Generation

Kangle Deng
Tianyi Fei
Xin Huang
Yuxin Peng

Automatically generating videos according to the given text is a highly challenging task, where visual quality and semantic consistency with captions are two critical issues. In existing methods, when generating a specific frame, the information in those frames generated before is not fully exploited. And an effective way to measure the semantic accordance between videos and captions remains to be established. To address these issues, we present a novel Introspective Recurrent Convolutional GAN (IRC-GAN) approach. First, we propose a recurrent transconvolutional generator, where LSTM cells are integrated with 2D transconvolutional layers. As 2D transconvolutional layers put more emphasis on the details of each frame than 3D ones, our generator takes both the definition of each video frame and temporal coherence across the whole video into consideration, and thus can generate videos with better visual quality. Second, we propose mutual information introspection to semantically align the generated videos to text. Unlike other methods simply judging whether the video and the text match or not, we further take mutual information to concretely measure the semantic consistency. In this way, our model is able to introspect the semantic distance between the generated video and the corresponding text, and try to minimize it to boost the semantic consistency. We conduct experiments on 3 datasets and compare with state-of-the-art methods. Experimental results demonstrate the effectiveness of our IRC-GAN to generate plausible videos from given text.

PDF Details

ICML Conference 2018 Conference Paper

Adversarial Attack on Graph Structured Data

Hanjun Dai
Hui Li
Tian Tian 0001
Xin Huang
Lin Wang
Jun Zhu 0001
Le Song

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool deep learning models by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. We further propose attack methods based on genetic algorithms and gradient descent in the scenario where additional prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers.

Details

AAAI Conference 2018 Conference Paper

Community Detection in Attributed Graphs: An Embedding Approach

Ye Li
Chaofeng Sha
Xin Huang
Yanchun Zhang

Community detection is a fundamental and widely-studied problem that ﬁnds all densely-connected groups of nodes and well separates them from others in graphs. With the proliferation of rich information available for entities in real-world networks, it is useful to discover communities in attributed graphs where nodes tend to have attributes. However, most existing attributed community detection methods directly utilize the original network topology leading to poor results due to ignoring inherent community structures. In this paper, we propose a novel embedding based model to discover communities in attributed graphs. Speciﬁcally, based on the observation of densely-connected structures in communities, we develop a novel community structure embedding method to encode inherent community structures via underlying community memberships. Based on node attributes and community structure embedding, we formulate the attributed community detection as a nonnegative matrix factorization optimization problem. Moreover, we carefully design iterative updating rules to make sure of ﬁnding a converging solution. Extensive experiments conducted on 19 attributed graph datasets with overlapping and non-overlapping ground-truth communities show that our proposed model CDE can accurately identify attributed communities and signiﬁcantly outperform 7 stateof-the-art methods.

PDF Details

IJCAI Conference 2018 Conference Paper

Finding Communities with Hierarchical Semantics by Distinguishing General and Specialized topics

Ge Zhang
Di Jin
Jian Gao
Pengfei Jiao
Françoise Fogelman-Soulié
Xin Huang

Using network topology and semantic contents to find topic-related communities is a new trend in the field of community detection. By analyzing texts in social networks, we find that topics in networked contents are often hierarchical. In most cases, they have a two-level semantic structure with general and specialized topics, to respectively denote common and specific interests of communities. However, the existing community detection methods ignore such a hierarchy and take all words used to describe node semantics from an identical perspective. This indiscriminate use of words leads to natural defects in depicting networked content in which the deep semantics is not fully utilized. To address this problem, we propose a novel probabilistic generative model. By distinguishing the general and specialized topics of words, our model not only can find community structures more accurately, but also provide two-level semantic interpretation for each community. We train the model by deriving an efficient inference method under the framework of variational expectation-maximization. We provide a case study to show the ability of our algorithm in deep semantic interpretability of communities. The superiority of our algorithm for community detection is further demonstrated in comparison with eight state-of-the-art algorithms on eight real-world networks.

PDF Details

IJCAI Conference 2017 Conference Paper

Cross-modal Common Representation Learning by Hybrid Transfer Network

Xin Huang
Yuxin Peng
Mingkuan Yuan

DNN-based cross-modal retrieval is a research hotspot to retrieve across different modalities as image and text, but existing methods often face the challenge of insufficient cross-modal training data. In single-modal scenario, similar problem is usually relieved by transferring knowledge from large-scale auxiliary datasets (as ImageNet). Knowledge from such single-modal datasets is also very useful for cross-modal retrieval, which can provide rich general semantic information that can be shared across different modalities. However, it is challenging to transfer useful knowledge from single-modal (as image) source domain to cross-modal (as image/text) target domain. Knowledge in source domain cannot be directly transferred to both two different modalities in target domain, and the inherent cross-modal correlation contained in target domain provides key hints for cross-modal retrieval which should be preserved during transfer process. This paper proposes Cross-modal Hybrid Transfer Network (CHTN) with two subnetworks: Modal-sharing transfer subnetwork utilizes the modality in both source and target domains as a bridge, for transferring knowledge to both two modalities simultaneously; Layer-sharing correlation subnetwork preserves the inherent cross-modal semantic correlation to further adapt to cross-modal retrieval task. Cross-modal data can be converted to common representation by CHTN for retrieval, and comprehensive experiment on 3 datasets shows its effectiveness.

PDF Details

IJCAI Conference 2017 Conference Paper

Online Roommate Allocation Problem

Guangda Huzhang
Xin Huang
Shengyu Zhang
Xiaohui Bei

We study the online allocation problem under a roommate market model introduced in [Chan et al. , 2016]. Consider a fixed supply of n rooms and a list of 2n applicants arriving sequentially in an online fashion. The problem is to assign a room to each person upon her arrival, such that after the algorithm terminates, each room is shared by exactly two people. We focus on two objectives: (1) maximizing the social welfare, which is defined as the sum of valuations that applicants have for their rooms, plus the happiness value between each pair of roommates; (2) the allocation should satisfy certain stability conditions, such that no group of people would be willing to switch roommates or rooms. We first show a polynomial-time online algorithm that achieves constant competitive ratio for social welfare maximization. We then extend it to the case where each room is assigned to c > 2 people, and achieve a competitive ratio of Ω(1/c^2). Finally, we show both positive and negative results in satisfying different stability conditions in this online setting.

PDF Details

AAAI Conference 2016 Conference Paper

Assignment and Pricing in Roommate Market

Pak Chan
Xin Huang
Zhengyang Liu
Chihao Zhang
Shengyu Zhang

We introduce a roommate market model, in which 2n people need to be assigned to n rooms, with two people in each room. Each person has a valuation to each room, as well as a valuation to each of other people as a roommate. Each room has a rent shared by the two people living in the room, and we need to decide who live together in which room and how much each should pay. Various solution concepts on stability and envy-freeness are proposed, with their existence studied and the computational complexity of the corresponding search problems analyzed. In particular, we show that maximizing the social welfare is NP-hard, and we give a polynomialtime algorithm that achieves at least 2/3 of the maximum social welfare. Finally, we demonstrate a pricing scheme that can achieve envy-freeness for each room.

PDF Details

IJCAI Conference 2016 Conference Paper

Cross-Media Shared Representation by Hierarchical Learning with Multiple Deep Networks

Yuxin Peng
Xin Huang
Jinwei Qi

Inspired by the progress of deep neural network (DNN) in single-media retrieval, the researchers have applied the DNN to cross-media retrieval. These methods are mainly two-stage learning: the first stage is to generate the separate representation for each media type, and the existing methods only model the intra-media information but ignore the inter-media correlation with the rich complementary context to the intra-media information. The second stage is to get the shared representation by learning the cross-media correlation, and the existing methods learn the shared representation through a shallow network structure, which cannot fully capture the complex cross-media correlation. For addressing the above problems, we propose the cross-media multiple deep network (CMDN) to exploit the complex cross-media correlation by hierarchical learning. In the first stage, CMDN jointly models the intra-media and inter-media information for getting the complementary separate representation of each media type. In the second stage, CMDN hierarchically combines the inter-media and intra-media representations to further learn the rich cross-media correlation by a deeper two-level network strategy, and finally get the shared representation by a stacked network style. Experiment results show that CMDN achieves better performance comparing with several state-of-the-art methods on 3 extensively used cross-media datasets.

PDF Details

EAAI Journal 1994 Journal Article

Knowledge-base management system for mine design and evaluation

Xin Huang
F. Hassani
V.S. Lakshmanan

Traditional mining operation design is a multi-level data/information/knowledge intensive procedure. This paper presents a new approach to the efficient feasibility analysis of mining operations, based on a knowledge-base management system. Special attention is given to the design of the backfill mining operation and the main specifications involved. The basic techniques and concepts of the knowledgebase management system are discussed in the context of the Logical Date Language (LDL). In particular, the main issues of backfill design using LDL are illustrated by an example of a hydraulic transportation system design for a backfill operation. Finally, it was concluded that the knowledgebase management system is a useful tool to solve engineering problems like mine design, and the further extension of the technology to the full scope of the mining operation design is recommended.

Details DOI