Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Novel class discovery(NCD) aims to cluster the unlabeled data with the help of a labeled set containing different but related classes. The key to solving NCD is the knowledge transfer between labeled and unlabeled sets.Since NCD requires that known classes and unknown classes are related, it is significant to explore class-level relationships between known and unknown for more effective knowledge transfer. However, most existing methods either facilitate knowledge transfer by learning a shared representation space or by modeling coarse-grained or asymmetric relationships between known and unknown, neglecting class-level relationships. To tackle these challenges, we propose a symmetric class-to-class relationship modeling and knowledge transfer method, achieving bidirectional knowledge transfer at class-level. Considering that class-level modeling often overlooks the subtle distinctions between samples, we propose pairwise similarity-based relationship modeling and consistency constraint for instance-level knowledge transfer. Extensive experiments on CIFAR100 and three fine-grained datasets demonstrate that our method achieves significant performance improvements compared to state-of-the-art methods.

Novel class discover(NCD) aims to identify new classes undefined during model training phase with the help of knowledge of known classes. Many methods have been proposed and notably boosted performance of NCD in natural images. However, there has been no work done in discovering new classes based on medical images and disease categories, which is crucial for understanding and diagnosing specific diseases. Moreover, most of the existing methods only utilize information from image modality and use labels as the only supervisory information. In this paper, we propose a multi-modal novel class discovery method based on paired images and text, inspired by the low classification accuracy of chest X-ray images and the relatively higher accuracy of the paired text. Specifically, we first pretrain the image encoder and text encoder with multi-modal contrastive learning on the entire dataset and then we generate pseudo-labels separately on the image branch and text branch. We utilize intra-modal consistency to assess the quality of pseudo-labels and adjust the weights of the pseudo-labels from both branches to generate the ultimate pseudo-labels for training. Experiments on eight subset splits of MIMIC-CXR-JPG dataset show that our method improves the clustering performance of unlabeled classes by about 10% on average compared to state-of-the-art methods. Code is available at: https://github.com/zzzzzzzzjy/MMNCD-main.

In wireless deterministic network (DetNet), it is a great challenge to serve heterogeneous traffic under different delay-bound requirements and wireless channels. This paper investigates the dynamic transmission scheduling policy for wireless DetNet with heterogeneous traffic. To meet the delaybound requirements for diverse traffic types, we propose a queue slicing model, where the queue buffer is divided into multiple slices. In each time slot, the newly arriving packets of different traffic types are allocated to specific queue buffer slices. Based on the queue slicing model, a cross-layer scheduling scheme is proposed, utilizing channel state information (CSI) of the physical layer (PHY) and queue state information of the medium access control (MAC) layer. Our objective is to minimize the delay violation probability under constraints on average transmission power and queue slice length. To solve the problem, we propose a queue slicing based dynamic deterministic scheduling (QS-DDS) algorithm using the Lyapunov drift-plus-penalty optimization method. Numerical results demonstrate that the proposed algorithm provides deterministic transmission for different traffic types. For wireless network with a single traffic type, the proposed algorithm achieves a lower delay violation probability than traditional queuing model based deterministic scheduling policies. Moreover, we validate the effectiveness of Lyapunov optimization method and show a trade-off between the objective function and the average virtual queue backlog.

Pathological images are important for diagnosis and prognosis of oral squamous cell carcinoma (OSCC). However, it is difficult for pathologists to directly apply intuitive pathological image information to predict prognosis. Applying supervised learning (SL) to whole slide images (WSIs) analysis is labor-consuming and time-costing, and semi-supervised learning (SmSL) has provided a new opportunity to revisit classical approaches in digital pathology. In this study, we designed an intelligent SmSL system based on Self-supervised Pretraining (SP) and Adaptive Threshold (AT), named SPAT_SmSL, for the diagnosis and prognosis of OSCC on multi centers. Firstly, we used the SP technique and AT strategy to fully exploit the unlabeled data, both of which were integrated into the SPAT_SmSL algorithm to recognize tumor, stroma, and tumor-infiltrating lymphocytes (TILs) regions. Secondly, pathological variables including TIL-score and depth of invasion (DOI) were digitally quantified based on the results of image recognition. Finally, multivariable cox analysis was performed to identify independent prognostic factors affecting overall survival and establish a comprehensive predictive model for OSCC patients. The new SPAT_SmSL paradigm demonstrates superior performance in WSIs recognition and survival prediction, which potentially serves as a novel tool to build an expert digital pathological platform to meet the demand of intelligent diagnosis and prognosis, as well as facilitating clinicians with complementary information for individualized treatment in the future.

Many questions should be answered by not a single answer but a set of multiple answers. This emerging Multi-Span Reading Comprehension (MSRC) task requires extracting multiple non-contiguous spans from a given context to answer a question. Existing methods extend conventional single-span models to predict the positions of the start and end tokens of answer spans, or predict the beginning-inside-outside tag of each token. Such token-centric paradigms can hardly capture dependencies among span-level answers which are critical to MSRC. In this paper, we propose SpanQualifier, a span-centric scheme where spans, as opposed to tokens, are directly represented and scored to qualify as answers. Explicit span representations enable their interaction which exploits their dependencies to enhance representations. Experiments on three MSRC datasets demonstrate the effectiveness of our span-centric scheme and show that SpanQualifier achieves state-of-the-art results.

Supporting wireless transmission of large-scale control systems is a challenging task due to the scarcity of wireless resources in the industrial internet of things (IIOT). To reduce wireless resource consumption while maintaining control stability, this paper investigates the wireless networked predictive control system, where only part of the control devices is permitted to transmit their state information to the centralized controller in each control cycle. For the rest unscheduled control devices, the centralized controller predicts their state information via the Gaussian process regression method. To evaluate the control performance and the wireless resources consumption, we formulate a joint optimization problem of control device scheduling, power allocation, and bandwidth allocation. The joint predictive control and communication optimization (JPCCO) scheduling algorithm is proposed to minimize both the control cost and communication cost. As for control device scheduling, we proposed a fuzzy logic based scheduling ranking (FL-SR) method, where control devices are ranked in descending order according to the fuzzy output. Numerical results show that the proposed JPCCO scheduling method with FL-SR outperforms the previous scheduling methods without predictive control, enabling a more stable wireless networked control system with less wireless resources.

Zixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, Gong Cheng. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

The rapid development in data collecting devices and computation platforms produces an emerging number of agents, each equipped with a unique data modality over a particular population of subjects. While an agent’s predictive performance may be enhanced by transmitting others’ data to it, this is often unrealistic due to intractable transmission costs and security concerns. In this paper, we propose a method named ASCII for an agent to improve its classification performance through assistance from other agents, without sharing proprietary data and model information. The main idea is to iteratively interchange an ignorance value between 0 and 1 for each collated sample among agents, where the value represents the urgency of further assistance needed. The method is naturally suitable for privacy-aware, transmission-economical, and decentralized learning scenarios. The method is also general as it allows the agents to use arbitrary classifiers such as logistic regression, ensemble tree, and neural network, and they may be heterogeneous among agents. We demonstrate the proposed method with extensive experimental studies.

We consider the distributed learning setting where each agent or learner holds a specific parametric model and a data source. The goal is to integrate information across a set of learners and data sources to enhance the prediction accuracy of a given learner. A natural way to integrate information is to build a joint model across a group of learners that shares common parameters of interest. However, the underlying parameter sharing patterns across a set of learners may not be known a priori. Misspecifying the parameter sharing patterns or the parametric model for each learner often yields a biased estimator that degrades the prediction accuracy. We propose a general method to integrate information across a set of learners that is robust against misspecification of both models and parameter sharing patterns. The main crux of our proposed method is to sequentially incorporate additional learners that can enhance the prediction accuracy of an existing joint model based on user- specified parameter sharing patterns across a set of learners. Theoretically, we show that the proposed method can data-adaptively select a parameter sharing pattern that enhances the predictive performance of a given learner. Extensive numerical studies are conducted to assess the performance of the proposed method.