Author name cluster

Ying Zeng

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.

6 papers

1 author row

NeurIPS Conference 2025 Conference Paper

CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning

Ronghao Lin
Qiaolin He
Sijie Mai
Ying Zeng
Aolin Xiong
Li Huang
Yap-Peng Tan
Haifeng Hu

Multimodal machine learning, mimicking the human brain’s ability to integrate various modalities has seen rapid growth. Most previous multimodal models are trained on perfectly paired multimodal input to reach optimal performance. In real‑world deployments, however, the presence of modality is highly variable and unpredictable, causing the pre-trained models in suffering significant performance drops and fail to remain robust with dynamic missing modalities circumstances. In this paper, we present a novel Cyclic INformative Learning framework (CyIN) to bridge the gap between complete and incomplete multimodal learning. Specifically, we firstly build an informative latent space by adopting token- and label-level Information Bottleneck (IB) cyclically among various modalities. Capturing task-related features with variational approximation, the informative bottleneck latents are purified for more efficient cross-modal interaction and multimodal fusion. Moreover, to supplement the missing information caused by incomplete multimodal input, we propose cross-modal cyclic translation by reconstruct the missing modalities with the remained ones through forward and reverse propagation process. With the help of the extracted and reconstructed informative latents, CyIN succeeds in jointly optimizing complete and incomplete multimodal learning in one unified model. Extensive experiments on 4 multimodal datasets demonstrate the superior performance of our method in both complete and diverse incomplete scenarios.

PDF Details

YNIMG Journal 2025 Journal Article

Dynamic interplay of hierarchical rank and social contexts in shaping perceived fairness

Yaner Su
Ying Zeng
Andre Aleman
Sander Martens
Pengfei Xu
Yue-Jia Luo
Katharina S. Goerlich

Fairness is a core principle of social norms. Previous studies have observed that individuals' social rank affects their perception of fairness. However, how others' social rank influences fairness norms remains unclear. Here, we conducted two experiments using the Ultimatum Game (UG) to investigate the influence of social rank on perceived fairness in competitive versus cooperative contexts. In both experiments, participants were asked to either accept or reject different offers from proposers of varying social ranks. Experiment 1 showed that participants accepted more offers from superior than inferior proposers and rated them as fairer. Reaction times were longer for sub-fair offers, and for fair offers made by inferior players. Computational modeling further revealed greater sensitivity to unfairness from inferior versus superior proposers. Experiment 2, using the same paradigm combined with electroencephalography (EEG), replicated the behavioral pattern and additionally showed that participants accepted more fair offers and sub-fair offers from superior players than from inferior ones. However, this social rank bias disappeared for unfair offers, suggesting a trade-off between social rank and equality norms. Moreover, computational modeling further revealed that the effect of social rank on fairness sensitivity was modulated by social context. Participants were more sensitive to unfairness from inferior proposers than superior proposers in cooperative contexts, whereas this rank effect was absent in competitive settings. Additionally, participants showed higher decision consistency in the competitive context, as reflected in increased inverse temperature values. EEG results showed larger P1 amplitudes in the cooperative than in the competitive context, and more negative N170 responses to faces of superior versus inferior players. These findings suggest a temporal distinction in early neural processing, with social context encoded prior to social rank. Moreover, the medial frontal negativity (MFN) was modulated by fairness level, with sub-fair offers eliciting the largest amplitude. Importantly, late positive potential (LPP) amplitudes were enhanced for fair relative to sub-fair offers in the superior rank condition, but not in the inferior condition, showing that fairness-related neural activity was modulated by social rank. Together, these findings demonstrate a dynamic interplay between social context and hierarchical rank in shaping both fairness-related behavior and its neural correlates.

Details DOI

AAAI Conference 2021 Conference Paper

Taxonomy Completion via Triplet Matching Network

Jieyu Zhang
Xiangchen Song
Ying Zeng
Jiaze Chen
Jiaming Shen
Yuning Mao
Lei Li

Automatically constructing taxonomy finds many applications in e-commerce and web search. One critical challenge is as data and business scope grow in real applications, new concepts are emerging and needed to be added to the existing taxonomy. Previous approaches focus on the taxonomy expansion, i. e. finding an appropriate hypernym concept from the taxonomy for a new query concept. In this paper, we formulate a new task, “taxonomy completion”, by discovering both the hypernym and hyponym concepts for a query. We propose Triplet Matching Network (TMN1 ), to find the appropriate hhypernym, hyponymi pairs for a given query concept. TMN consists of one primal scorer and multiple auxiliary scorers. These auxiliary scorers capture various fine-grained signals (e. g. , query to hypernym or query to hyponym semantics), and the primal scorer makes a holistic prediction on hquery, hypernym, hyponymi triplet based on the internal feature representations of all auxiliary scorers. Also, an innovative channel-wise gating mechanism that retains task-specific information in concept representations is introduced to further boost model performance. Experiments on four real-world large-scale datasets show that TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.

PDF Details

AAAI Conference 2020 Conference Paper

Importance-Aware Learning for Neural Headline Editing

Qingyang Wu
Lei Li
Hao Zhou
Ying Zeng
Zhou Yu

Many social media news writers are not professionally trained. Therefore, social media platforms have to hire professional editors to adjust amateur headlines to attract more readers. We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers. To train such a neural headline editing model, we collected a dataset which contains articles with original headlines and professionally edited headlines. However, it is expensive to collect a large number of professionally edited headlines. To solve this low-resource problem, we design an encoder-decoder model which leverages large scale pre-trained language models. We further improve the pre-trained model’s quality by introducing a headline generation task as an intermediate task before the headline editing task. Also, we propose Self Importance- Aware (SIA) loss to address the different levels of editing in the dataset by down-weighting the importance of easily classiﬁed tokens and sentences. With the help of Pre-training, Adaptation, and SIA, the model learns to generate headlines in the professional editor’s style. Experimental results show that our method signiﬁcantly improves the quality of headline editing comparing against previous methods.

PDF Details

YNIMG Journal 2018 Journal Article

A voxel-based analysis of neurobiological mechanisms in placebo analgesia in rats

Ying Zeng
Di Hu
Wei Yang
Emi Hayashinaka
Yasuhiro Wada
Yasuyoshi Watanabe
Qunli Zeng
Yilong Cui

Placebo analgesia is the beneficial effect that follows despite a pharmacologically inert treatment. Modern neuroimaging studies in humans have delineated the hierarchical brain regions involved in placebo analgesia. However, because of the lack of proper approaches to perform molecular and cellular manipulations, the detailed molecular processes behind it have not been clarified. To address this issue, we developed an animal model of placebo analgesia in rats and analyzed the placebo analgesia related brain activity using small-animal neuroimaging method. We show here that gabapentin-based Pavlovian conditioning successfully induced placebo analgesia in neuropathic pain model rats and hierarchical brain regions are involved in placebo analgesia in rats, including the prelimbic cortex (PrL) of the medial prefrontal cortex (mPFC), nucleus accumbens (NAc), ventrolateral periaqueductal gray matter (vlPAG), etc. The functional couplings in placebo responders between the mPFC and vlPAG was interrupted by naloxone, an antagonist of μ opioid receptor. Moreover, both local chemical lesion and microinfusion of naloxone in the mPFC suppressed the placebo analgesia. These results suggest that the intrinsic μ opioid system in the mPFC causally contribute to placebo analgesia in rats, and the small-animal neuroimaging approach could provide important insights toward understanding the placebo effect in great detail.

Details DOI

AAAI Conference 2018 Conference Paper

Scale Up Event Extraction Learning via Automatic Training Data Generation

Ying Zeng
Yansong Feng
Rong Ma
Zheng Wang
Rui Yan
Chongde Shi
Dongyan Zhao

The task of event extraction has long been investigated in a supervised learning paradigm, which is bound by the number and the quality of the training instances. Existing training data must be manually generated through a combination of expert domain knowledge and extensive human involvement. However, due to drastic efforts required in annotating text, the resultant datasets are usually small, which severally affects the quality of the learned model, making it hard to generalize. Our work develops an automatic approach for generating training data for event extraction. Our approach allows us to scale up event extraction training instances from thousands to hundreds of thousands, and it does this at a much lower cost than a manual approach. We achieve this by employing distant supervision to automatically create event annotations from unlabelled text using existing structured knowledge bases or tables. We then develop a neural network model with post inference to transfer the knowledge extracted from structured knowledge bases to automatically annotate typed events with corresponding arguments in text. We evaluate our approach by using the knowledge extracted from Freebase to label texts from Wikipedia articles. Experimental results show that our approach can generate a large number of highquality training instances. We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events.

PDF Details