Author name cluster

Ting Guo

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.

11 papers

1 author row

EAAI Journal 2026 Journal Article

Learning unified market interdependencies via networked attention for stock price forecasting

Kaveesha Hewage
Boyu Li
Ting Guo
Alexis Stenfors
Peter Mere
Fang Chen

Stock price forecasting is challenging due to market volatility and complex, dynamic inter-stock relationships. Existing graph-based approaches often rely primarily on static relational structures or simple time-aligned correlations, which capture only fixed or short-term relationships and fail to model transient cross-temporal dependencies and heterogeneous information sources. We propose a novel artificial intelligence framework for stock price forecasting that integrates heterogeneous data sources, including price co-movements, corporate linkages derived from Wikipedia, and industry affiliations, into a unified dynamic relational graph that combines both structural and behavioral dependencies. The proposed model, named Learning Unified Market Interdependencies (LUMI), adaptively models evolving inter-stock connections and uncovers latent dependencies beyond sectoral or time-aligned patterns. A dual-path temporal attention mechanism disentangles long-term trends from short-term fluctuations, capturing both periodic behaviors and abrupt market shifts. Extensive experiments on four market datasets demonstrate that the proposed deep learning framework outperforms strong baselines in predictive accuracy while providing interpretable insights into market interdependencies. These findings highlight the potential of artificial intelligence for modeling complex financial systems and improving algorithmic stock price forecasting.

Details DOI

NeurIPS Conference 2025 Conference Paper

FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning

Da Wang
Yi Ma
Ting Guo
Hongyao Tang
Wei Wei
Jiye Liang

Offline reinforcement learning (RL) aims to learn optimal policies from static datasets while enhancing generalization to out-of-distribution (OOD) data. To mitigate overfitting to suboptimal behaviors in offline datasets, existing methods often relax constraints on policy and data or extract informative patterns through data-driven techniques. However, there has been limited exploration into structurally guiding the optimization process toward flatter regions of the solution space that offer better generalization. Motivated by this observation, we present \textit{FANS}, a generalization-oriented structured network framework that promotes flatter and robust policy learning by guiding the optimization trajectory through modular architectural design. FANS comprises four key components: (1) Residual Blocks, which facilitate compact and expressive representations; (2) Gaussian Activation, which promotes smoother gradients; (3) Layer Normalization, which mitigates overfitting; and (4) Ensemble Modeling, which reduces estimation variance. By integrating FANS into a standard actor-critic framework, we highlight that this remarkably simple architecture achieves superior performance across various tasks compared to many existing advanced methods. Moreover, we validate the effectiveness of FANS in mitigating overestimation and promoting generalization, demonstrating the promising potential of architectural design in advancing offline RL.

PDF Details

NeurIPS Conference 2024 Conference Paper

SpeAr: A Spectral Approach for Zero-Shot Node Classification

Ting Guo
Da Wang
Jiye Liang
Kaihan Zhang
Jianchao Zeng

Zero-shot node classification is a vital task in the field of graph data processing, aiming to identify nodes of classes unseen during the training process. Prediction bias is one of the primary challenges in zero-shot node classification, referring to the model's propensity to misclassify nodes of unseen classes as seen classes. However, most methods introduce external knowledge to mitigate the bias, inadequately leveraging the inherent cluster information within the unlabeled nodes. To address this issue, we employ spectral analysis coupled with learnable class prototypes to discover the implicit cluster structures within the graph, providing a more comprehensive understanding of classes. In this paper, we propose a spectral approach for zero-shot node classification (SpeAr). Specifically, we establish an approximate relationship between minimizing the spectral contrastive loss and performing spectral decomposition on the graph, thereby enabling effective node characterization through loss minimization. Subsequently, the class prototypes are iteratively refined based on the learned node representations, initialized with the semantic vectors. Finally, extensive experiments verify the effectiveness of the SpeAr, which can further alleviate the bias problem.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Discriminative Sample Generation for Deep Imbalanced Learning

Ting Guo
Xingquan Zhu
Yang Wang
Fang Chen

In this paper, we propose a discriminative variational autoencoder (DVAE) to assist deep learning from data with imbalanced class distributions. DVAE is designed to alleviate the class imbalance by explicitly learning class boundaries between training samples, and uses learned class boundaries to guide the feature learning and sample generation. To learn class boundaries, DVAE learns a latent two-component mixture distributor, conditioned by the class labels, so the latent features can help differentiate minority class vs. majority class samples. In order to balance the training data for deep learning to emphasize on the minority class, we combine DVAE and generative adversarial networks (GAN) to form a unified model, DVAAN, which generates synthetic instances close to the class boundaries as training data to learn latent features and update the model. Experiments and comparisons confirm that DVAAN significantly alleviates the class imbalance and delivers accurate models for deep learning from imbalanced data.

PDF Details

YNIMG Journal 2019 Journal Article

White matter injury in term neonates with congenital heart diseases: Topology & comparison with preterm newborns

Ting Guo
Vann Chau
Shabnam Peyvandi
Beatrice Latal
Patrick S. McQuillen
Walter Knirsch
Anne Synnes
Maria Feldmann

Background Neonates with congenital heart disease (CHD) are at high risk of punctate white matter injury (WMI) and impaired brain development. We hypothesized that WMI in CHD neonates occurs in a characteristic distribution that shares topology with preterm WMI and that lower birth gestational age (GA) is associated with larger WMI volume. Objective (1) To quantitatively assess the volume and location of WMI in CHD neonates across three centres. (2) To compare the volume and spatial distribution of WMI between term CHD neonates and preterm neonates using lesion mapping. Methods In 216 term born CHD neonates from three prospective cohorts (mean birth GA: 39 weeks), WMI was identified in 86 neonates (UBC: 29; UCSF: 43; UCZ: 14) on pre- and/or post-operative T1 weighted MRI. WMI was manually segmented and volumes were calculated. A standard brain template was generated. Probabilistic WMI maps (total, pre- and post-operative) were developed in this common space. Using these maps, WMI in the term CHD neonates was compared with that in preterm neonates: 58 at early-in-life (mean postmenstrual age at scan 32. 2 weeks); 41 at term-equivalent age (mean postmenstrual age at scan 40. 1 weeks). Results The total WMI volumes of CHD neonates across centres did not differ (p = 0. 068): UBC (median = 84. 6 mm3, IQR = 26–174. 7 mm3); UCSF (median = 104 mm3, IQR = 44–243 mm3); UCZ (median = 121 mm3, IQR = 68–200. 8 mm3). The spatial distribution of WMI in CHD neonates showed strong concordance across centres with predilection for anterior and posterior rather than central lesions. Predominance of anterior lesions was apparent on the post-operative WMI map relative to the pre-operative map. Lower GA at birth predicted an increasing volume of WMI across the full cohort (41. 1 mm3 increase of WMI per week decrease in gestational age; 95% CI 11. 5–70. 8; p = 0. 007), when accounting for centre and heart lesion. While WMI in term CHD and preterm neonates occurs most commonly in the intermediate zone/outer subventricular zone there is a paucity of central lesions in the CHD neonates relative to preterms. Conclusions WMI in term neonates with CHD occurs in a characteristic topology. The spatial distribution of WMI in term neonates with CHD reflects the expected maturation of pre-oligodendrocytes such that the central regions are less vulnerable than in the preterm neonates.

Details DOI

YNICL Journal 2019 Journal Article

White matter injury predicts disrupted functional connectivity and microstructure in very preterm born neonates

Emma G. Duerden
Sheliza Halani
Karin Ng
Ting Guo
Justin Foong
Torin J.A. Glass
Vann Chau
Helen M. Branson

OBJECTIVE: To determine whether the spatial extent and location of early-identified punctate white matter injury (WMI) is associated with regionally-specific disruptions in thalamocortical-connectivity in very-preterm born neonates. METHODS: 37 very-preterm born neonates (median gestational age: 28.1 weeks; interquartile range [IQR]: 27-30) underwent early MRI (median age 32.9 weeks; IQR: 32-35), and WMI was identified in 13 (35%) neonates. Structural T1-weighted, resting-state functional Magnetic Resonance Imaging (rs-fMRI, n = 34) and Diffusion Tensor Imaging (DTI, n = 31) sequences were acquired using 3 T-MRI. A probabilistic map of WMI was developed for the 13 neonates demonstrating brain injury. A neonatal atlas was applied to the WMI maps, rs-fMRI and DTI analyses to extract volumetric, functional and microstructural data from regionally-specific brain areas. Associations of thalamocortical-network strength and alterations in fractional anisotropy (FA, a measure of white-matter microstructure) with WMI volume were assessed in general linear models, adjusting for age at scan and cerebral volumes. RESULTS: WMI volume in the superior (β = -0.007; p = .02) and posterior corona radiata (β = -0.01; p = .01), posterior thalamic radiations (β = -0.01; p = .005) and superior longitudinal fasciculus (β = -0.02; p = .001) was associated with reduced connectivity strength between thalamus and parietal resting-state networks. WMI volume in the left (β = -0.02; p = .02) and right superior corona radiata (β = -0.03; p = .008), left posterior corona radiata (β = -0.03; p = .01), corpus callosum (β = -0.11; p < .0001) and right superior longitudinal fasciculus (β = -0.02; p = .02) was associated with functional connectivity strength between thalamic and sensorimotor networks. Increased WMI volume was also associated with decreased FA values in the corpus callosum (β = -0.004, p = .015). CONCLUSIONS: Regionally-specific alterations in early functional and structural network complexity resulting from WMI may underlie impaired outcomes.

Details DOI

NeurIPS Conference 2016 Conference Paper

Infinite Hidden Semi-Markov Modulated Interaction Point Process

matt zhang
Peng Lin
Ting Guo
Yang Wang
Fang Chen

The correlation between events is ubiquitous and important for temporal events modelling. In many cases, the correlation exists between not only events' emitted observations, but also their arrival times. State space models (e. g. , hidden Markov model) and stochastic interaction point process models (e. g. , Hawkes process) have been studied extensively yet separately for the two types of correlations in the past. In this paper, we propose a Bayesian nonparametric approach that considers both types of correlations via unifying and generalizing hidden semi-Markov model and interaction point process model. The proposed approach can simultaneously model both the observations and arrival times of temporal events, and determine the number of latent states from data. A Metropolis-within-particle-Gibbs sampler with ancestor resampling is developed for efficient posterior inference. The approach is tested on both synthetic and real-world data with promising outcomes.

PDF Details

AAAI Conference 2016 Conference Paper

Interaction Point Processes via Infinite Branching Model

Peng Lin
Bang Zhang
Ting Guo
Yang Wang
Fang Chen

Many natural and social phenomena can be modeled by interaction point processes (IPPs) (Diggle et al. 1994), stochastic point processes considering the interaction between points. In this paper, we propose the inﬁnite branching model (IBM), a Bayesian statistical model that can generalize and extend some popular IPPs, e. g. , Hawkes process (Hawkes 1971; Hawkes and Oakes 1974). It treats IPP as a mixture of basis point processes with the aid of a distance dependent prior over branching structure that describes the relationship between points. The IBM can estimate point event intensity, interaction mechanism and branching structure simultaneously. A generic Metropolis-within-Gibbs sampling method is also developed for model parameter inference. The experiments on synthetic and real-world data demonstrate the superiority of the IBM.

PDF Details

YNICL Journal 2015 Journal Article

Automatic segmentation of the hippocampus for preterm neonates from early-in-life to term-equivalent age

Ting Guo
Julie L. Winterburn
Jon Pipitone
Emma G. Duerden
Min Tae M. Park
Vann Chau
Kenneth J. Poskitt
Ruth E. Grunau

INTRODUCTION: The hippocampus, a medial temporal lobe structure central to learning and memory, is particularly vulnerable in preterm-born neonates. To date, segmentation of the hippocampus for preterm-born neonates has not yet been performed early-in-life (shortly after birth when clinically stable). The present study focuses on the development and validation of an automatic segmentation protocol that is based on the MAGeT-Brain (Multiple Automatically Generated Templates) algorithm to delineate the hippocampi of preterm neonates on their brain MRIs acquired at not only term-equivalent age but also early-in-life. METHODS: First, we present a three-step manual segmentation protocol to delineate the hippocampus for preterm neonates and apply this protocol on 22 early-in-life and 22 term images. These manual segmentations are considered the gold standard in assessing the automatic segmentations. MAGeT-Brain, automatic hippocampal segmentation pipeline, requires only a small number of input atlases and reduces the registration and resampling errors by employing an intermediate template library. We assess the segmentation accuracy of MAGeT-Brain in three validation studies, evaluate the hippocampal growth from early-in-life to term-equivalent age, and study the effect of preterm birth on the hippocampal volume. The first experiment thoroughly validates MAGeT-Brain segmentation in three sets of 10-fold Monte Carlo cross-validation (MCCV) analyses with 187 different groups of input atlases and templates. The second experiment segments the neonatal hippocampi on 168 early-in-life and 154 term images and evaluates the hippocampal growth rate of 125 infants from early-in-life to term-equivalent age. The third experiment analyzes the effect of gestational age (GA) at birth on the average hippocampal volume at early-in-life and term-equivalent age using linear regression. RESULTS: The final segmentations demonstrate that MAGeT-Brain consistently provides accurate segmentations in comparison to manually derived gold standards (mean Dice's Kappa > 0.79 and Euclidean distance <1.3 mm between centroids). Using this method, we demonstrate that the average volume of the hippocampus is significantly different (p < 0.0001) in early-in-life (621.8 mm(3)) and term-equivalent age (958.8 mm(3)). Using these differences, we generalize the hippocampal growth rate to 38.3 ± 11.7 mm(3)/week and 40.5 ± 12.9 mm(3)/week for the left and right hippocampi respectively. Not surprisingly, younger gestational age at birth is associated with smaller volumes of the hippocampi (p = 0.001). CONCLUSIONS: MAGeT-Brain is capable of segmenting hippocampi accurately in preterm neonates, even at early-in-life. Hippocampal asymmetry with a larger right side is demonstrated on early-in-life images, suggesting that this phenomenon has its onset in the 3rd trimester of gestation. Hippocampal volume assessed at the time of early-in-life and term-equivalent age is linearly associated with GA at birth, whereby smaller volumes are associated with earlier birth.

Details DOI

EAAI Journal 2015 Journal Article

Reverse twin plant for efficient diagnosability testing and optimizing

Boyu Li
Ting Guo
Xingquan Zhu
Zhanshan Li

Model-based diagnosis in discrete event systems (DESs) is a major research topic in failure diagnosis, where diagnosability plays an important role in the construction of the diagnosis engine. To improve the solution efficiency for diagnosability, this paper proposes novel techniques to solve the problems of testing and optimizing for diagnosability. We propose a new concept, reverse twin plant, which is generated backwards from the final states of the DESs so there is no need to generate a complete copy of the DES model to determine the diagnosability. Such a design makes our testing algorithm much faster than existing methods. An efficient optimizing algorithm, which makes a non-diagnosable system diagnosable, is also proposed in the paper by expanding the minimal observable space with operation on just a part of the DES model. Examples and theoretical studies demonstrate the performance of the proposed designs.

Details DOI

AAAI Conference 2011 Conference Paper

Large Scale Diagnosis Using Associations between System Outputs and Components

Ting Guo
Zhanshan Li
Ruizhi Guo
Xingquan Zhu

Model-based diagnosis (MBD) uses an abstraction of system to diagnose possible faulty functions of an underlying system. To improve the solution efficiency for multi-fault diagnosis problems, especially for large scale systems, this paper proposes a method to induce reasonable diagnosis solutions, under coarse diagnosis, by using the relationships between system outputs and components. Compared to existing diagnosis methods, the proposed framework only needs to consider associations between outputs and components by using an assumption-based truth maintenance system (ATMS) [de Kleer 1986] to obtain correlation components for every output node. As a result, our method significantly reduces the number of variables required for model diagnosis, which makes it suitable for large scale circuit systems.

PDF Details