Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Reconstructing 3D shapes from monocular freehand sketches is challenging due to their fragmented structures, varying line thickness, and discontinuity. These characteristics cause ambiguity, making it difficult for existing methods to extract sufficient geometric feature information to distinguish subtle shape variations and internal details of the object contours depicted in the sketches, resulting in poor overall reconstruction quality. To address these challenges, we introduce the Part-level Semantic Fusion (PSFusion) module, which combines local units of image features with global feature guidance to enhance the representation of complex geometric structures and subtle contour variations. This approach reduces ambiguity in complex edges and local details, improving shape preservation and edge contour accuracy. Additionally, we propose the coarse-to-fine 3D Decoder consisting of one 3D convolutional network as a coarse-grained regressor and one Shuffle-UNet-based fine-grained refiner, to capture feature dependencies across spatial and channel dimensions. Shuffle operations facilitate information exchange among sub-features, enhancing structural differentiation and cross-feature dependency modelling. This significantly improves the handling of subtle textures and complex intersection boundaries. Extensive experiments on three public benchmarks show that our method outperforms baseline approaches, as demonstrated by both quantitative and qualitative results.

Pre-trained language models (PrLMs) demonstrate impressive performance on the sentiment analysis task. However, the large number of trainable parameters brings about heavy computational costs, which become more serious in multi-domain scenarios. In this paper, we propose to extract multi-layer features from the PrLM for efficient training since the training process is independent to its large backbone. Meanwhile, compared with the conventional feature extraction, we leverage prompts to induce PrLM for generating sentiment-aware features which lead to significant improvement on the sentiment analysis. In addition, most previous methods adopted a domain alignment paradigm for multi-domain learning, which becomes cumbersome when the number of domains is large. Therefore, we propose a novel prompt-augmented cross-domain contrastive learning for generalizable performance, which clusters samples with the same label under different prompts or domains. Our method is evaluated on two public multi-domain sentiment analysis benchmarks, which significantly outperforms recent state-of-the-art methods. Extensive ablation studies also verify the effectiveness of each proposed component.

Cancer is inherently a complex disease and cancer somatic driver mutations within the cancer pathway often show mutually exclusive patterns in a group of patients, providing a novel signal to distinguish driver mutations from mass passenger mutations. However, in biological pathways, most mutated genes are low exclusivity and mutual exclusivity-based driver genes identification methods do not identify low exclusivity driver genes well. Furthermore, mutual exclusivity-based methods are largely influenced by the integrity of the biological network, resulting in their ineffectiveness in identifying driver genes. Therefore, in this paper, we propose a driver genes identification method with improved cross-entropy measure (ICE), which measures mutation frequencies of mutated genes in biological pathways while measuring mutual exclusivity through improved cross-entropy, thereby achieving complementary mutual exclusivity and mutation rates. Experimental results show that our method outperforms eight state-of-the-art methods in identifying driver genes, especially in identifying low-exclusivity genes. In addition, our method is more effective when protein networks and biological pathways are error-prone or incomplete.

Multimodal sarcasm detection has received considerable attention due to its unique role in social networks. Existing methods often rely on feature concatenation to fuse different modalities or model the inconsistencies among modalities. However, sarcasm is often embodied in local and momentary nuances in a subtle way, which causes difficulty for sarcasm detection. To effectively incorporate these nuances, this paper presents Context-Aware Self-Attention Fusion (CAAF) to integrate local and momentary multimodal information into specific words. Furthermore, due to the instantaneous nature of sarcasm, the connotative meanings of words post-multimodal integration generally deviate from their denotative meanings. Therefore, Word Weight Calculation (WWC) is presented to compute the weight of specific words based on CAAF’s fusion nuances, illustrating the inconsistency between connotation and denotation. We evaluate our method on the MUStARD dataset, achieving an accuracy of 76.9 and an F1 score of 76.1, which surpasses the current state-of-the-art IWAN model by 1.7 and 1.6 respectively.

In this work, we study a more realistic challenging scenario in multiview clustering (MVC), referred to as incomplete MVC (IMVC) where some instances in certain views are missing. The key to IMVC is how to adequately exploit complementary and consistency information under the incompleteness of data. However, most existing methods address the incompleteness problem at the instance level and they require sufficient information to perform data recovery. In this work, we develop a new approach to facilitate IMVC based on the graph propagation perspective. Specifically, a partial graph is used to describe the similarity of samples for incomplete views, such that the issue of missing instances can be translated into the missing entries of the partial graph. In this way, a common graph can be adaptively learned to self-guide the propagation process by exploiting the consistency information, and the propagated graph of each view is in turn used to refine the common self-guided graph in an iterative manner. Thus, the associated missing entries can be inferred through graph propagation by exploiting the consistency information across all views. On the other hand, existing approaches focus on the consistency structure only, and the complementary information has not been sufficiently exploited due to the data incompleteness issue. By contrast, under the proposed graph propagation framework, an exclusive regularization term can be naturally adopted to exploit the complementary information in our method. Extensive experiments demonstrate the effectiveness of the proposed method in comparison with state-of-the-art methods. The source code of our method is available at the https://github.com/CLiu272/TNNLS-PGP.

Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER, state-of-the-art models struggle to achieve a satisfactory performance. We propose a self-attention based method with combined use of label-adaptive mixup and center loss. By adapting label probabilities in mixup and fitting center loss to the mixup training scheme, our proposed method achieves a superior performance to the state-of-the-art methods.

Cancer is a disease with a complex genome of altered functions.However, most existing driver gene identification approaches rarely consider driver genes may have the same functional properties.To overcome this issue, we propose the gamma distribution test for the driver gene identification based on similarity networks, termed GASN, which identifies driver genes by combining machine learning and distributional statistics methods.Similarity networks are able to learn gene similarities and key features that represent the functional impact of genes.In addition, we classify genes into different cellular compartments and use the gamma distribution test within cellular compartments to identify significant driver genes.The experimental results show that our method outperforms the other 17 comparative methods.

Abstract Corona Virus disease 2019 (COVID‐19) has shattered people's daily lives and is spreading rapidly across the globe. Existing non‐pharmaceutical intervention solutions often require timely and precise selection of small areas of people for containment or even isolation. Although such containment has been successful in stopping or mitigating the spread of COVID‐19 in some countries, it has been criticized as inefficient or ineffective, because of the time‐delayed and sophisticated nature of the statistics on determining cases. To address these concerns, we propose a GSA‐ELM model based on a gravitational search algorithm to forecast the global number of active cases of COVID‐19. The model employs the gravitational search algorithm, which utilises the gravitational law between two particles to guide the motion of each particle to optimise the search for the global optimal solution, and utilises an extreme learning machine to address the effects of nonlinearity in the number of active cases. Extensive experiments are conducted on the statistical COVID‐19 dataset from Johns Hopkins University, the MAPE of the authors’ model is 7.79%, which corroborates the superiority of the model to state‐of‐the‐art methods.

Abstract One-hot labels are commonly employed as ground truth in Emotion Recognition in Conversations (ERC). However, this approach may not fully encompass all the emotions conveyed in a single utterance, leading to suboptimal performance. Regrettably, current ERC datasets lack comprehensive emotionally distributed labels. To address this issue, we propose the Emotion Label Refinement (EmoLR) method, which utilizes context- and speaker-sensitive information to infer mixed emotional labels. EmoLR comprises an Emotion Predictor (EP) module and a Label Refinement (LR) module. The EP module recognizes emotions and provides context/speaker states for the LR module. Subsequently, the LR module calculates the similarity between these states and ground-truth labels, generating a refined label distribution (RLD). The RLD captures a more comprehensive range of emotions than the original one-hot labels. These refined labels are then used for model training in place of the one-hot labels. Experimental results on three public conversational datasets demonstrate that our EmoLR achieves state-of-the-art performance.

Emotion recognition in conversations (ERC) has wide applications in medical care, human-computer interaction, and other fields. Unlike the general task of emotion analysis, humans usually rely on context and commonsense knowledge to convey emotions in conversations. Only when the model can connect and fully utilize a large-scale commonsense knowledge base, it can better understand latent contents in conversations. Unfortunately, there is no available knowledge selection mechanism to address such knowledge needs and to make sure the system is not flooded with irrelevant commonsense knowledge. Therefore, we propose an AutoML strategy based on emotion congruent effect to select suitable knowledge and models, called AutoML-Emo. Global exploration and local exploitation-based selection mechanisms (G&LESM) are used for automatic knowledge selection. The transformer-based architecture search (TAS) is applied to model selection, the selected transformer-based model is employed to incorporate knowledge and capture context information in conversations. The experimental results show that AutoML-Emo can effectively enhance external knowledge in different sizes and domain datasets. Moreover, the selected transformer-based model derived from TAS is superior to the most advanced models.

Emotion recognition in conversations (ERC) needs to detect the emotion of each utterance in conversations. However, it is difficult for machines to recognize the emotion of utterances like humans, partly because of the lack of commonsense knowledge. Despite existing efforts gradually incorporate knowledge in ERC, they can not adaptively adjust knowledge according to different utterances and their context. In this article, we propose a knowledge selection framework SKSEC (SelectKnowledge in light ofSentimentEmotion andContext). In the SKSEC framework, first, external knowledge is eliminated by three Knowledge Elimination (KE) modules. More concretely, In word-level KE, the concept knowledge different from the sentiment corresponding to the word in utterances is randomly eliminated. In utterance- or context-level KE, If the similarity between the knowledge representation and the emotion label representation of the current utterance or its context is less than the preset threshold, the knowledge will be eliminated. Then we refine the weight of knowledge using two Graph ATtention (GAT) mechanisms. Specifically, In Sentics GAT, we employ a dimensional emotion model to measure words in utterances and their corresponding knowledge and adjust the weight of knowledge according to their emotional similarity. In Semantics GAT, the weight of knowledge is adjusted according to the semantic similarity between context and incorporated knowledge. Finally, we feed the selected knowledge to the most advanced models to evaluate the quality of knowledge. The experimental results show that the SKSEC framework can effectively improve the performance of the model by eliminating and refining external knowledge in different size and domain datasets.

Incomplete multi-view clustering (IMVC) is challenging, as it requires adequately exploring complementary and consistency information under the incompleteness of data. Most existing approaches attempt to overcome the incompleteness at instance-level. In this work, we develop a new approach to facilitate IMVC from a new perspective. Specifically, we transfer the issue of missing instances to a similarity graph completion problem for incomplete views, and propose a self-supervised multi-view graph completion algorithm to infer the associated missing entries. Further, by incorporating constrained feature learning, the inferred graph can be naturally leveraged in representation learning. We theoretically show that our feature learning process performs an Auto-Regressive filter function by encoding the learned similarity graph, which could yield discriminative representation for a clustering task. Extensive experiments demonstrate the effectiveness of the proposed method in comparison with state-of-the-art methods.

Recently, fine-tuning the pre-trained language model (PrLM) on labeled sentiment datasets demonstrates impressive performance. However, collecting labeled sentiment dataset is time-consuming, and fine-tuning the whole PrLM brings about much computation cost. To this end, we focus on multi-source unsupervised sentiment adaptation problem with the pre-trained features, which is more practical and challenging. We first design a dynamic feature network to fully exploit the extracted pre-trained features for efficient domain adaptation. Meanwhile, with the difference of the traditional source-target domain alignment methods, we propose a novel asymmetric mutual learning strategy, which can robustly estimate the pseudo-labels of the target domain with the knowledge from all the other source models. Experiments on multiple sentiment benchmarks show that our method outperforms the recent state-of-the-art approaches, and we also conduct extensive ablation studies to verify the effectiveness of each the proposed module.

Identifying cancer subtypes by integration of multi-omic data is beneficial to improve the understanding of disease progression, and provides more precise treatment for patients. Cancer subtypes identification is usually accomplished by clustering patients with unsupervised learning approaches. Thus, most existing integrative cancer subtyping methods are performed in an entirely unsupervised way. An integrative cancer subtyping approach can be improved to discover clinically more relevant cancer subtypes when considering the clinical survival response variables. In this study, we propose a Survival Supervised Graph Clustering (S2GC)for cancer subtyping by taking into consideration survival information. Specifically, we use a graph to represent similarity of patients, and develop a multi-omic survival analysis embedding with patient-to-patient similarity graph learning for cancer subtype identification. The multi-view (omic)survival analysis model and graph of patients are jointly learned in a unified way. The learned optimal graph can be unitized to cluster cancer subtypes directly. In the proposed model, the survival analysis model and adaptive graph learning could positively reinforce each other. Consequently, the survival time can be considered as supervised information to improve the quality of the similarity graph and explore clinically more relevant subgroups of patients. Experiments on several representative multi-omic cancer datasets demonstrate that the proposed method achieves better results than a number of state-of-the-art methods. The results also suggest that our method is able to identify biologically meaningful subgroups for different cancer types. (Our Matlab source code is available online at github: https://github.com/CLiu272/S2GC).

Recently, multitask learning has been successfully applied to survival analysis problems. A critical challenge in real-world survival analysis tasks is that not all instances and tasks are equally learnable. A survival analysis model can be improved when considering the complexities of instances and tasks during the model training. To this end, we propose an asymmetric graph-guided multitask learning approach with self-paced learning for survival analysis applications. The proposed model is able to improve the learning performance by identifying the complex structure among tasks and considering the complexities of training instances and tasks during the model training. Especially, by incorporating the self-paced learning strategy and asymmetric graph-guided regularization, the proposed model is able to learn the model in a progressive way from "easy" to "hard" loss function items. In addition, together with the self-paced learning function, the asymmetric graph-guided regularization allows the related knowledge transfer from one task to another in an asymmetric way. Consequently, the knowledge acquired from those earlier learned tasks can help to solve complex tasks effectively. The experimental results on both synthetic and real-world TCGA data suggest that the proposed method is indeed useful for improving survival analysis and achieves higher prediction accuracies than the previous state-of-the-art methods.

Abstract The target of Emotion modeling is to establish an system that can perceive, recognize, and express emotions with concurrency which humanity have by proper mathematical models. A big challenge in Emotion modeling is to establish the complex personal system of an intelligent agent or machine in a quasi‐physical and quasi‐sociological way, so that it rationally responds to emotions and behaviors by different internal and external stimuli with concurrency. For this purpose, an emotion classification model is presented for the audio‐visual external stimuli based on an improved long short‐term memory network. Then, based on Gross's emotional regulation theory, a hidden Markov model is constructed to imitate the process framework of human emotional cognition and personalized emotional regulation and expression, so as to realize the machine's intuitive and reasonable response to stimuli with concurrency. In this article, a framework of machine personalized artificial emotion simulation is preliminarily constructed, which provides a new model for human–computer interaction, in order to provide a reference solution for machine emotion understanding and expression.

Multimodality sentiment analysis in the social Internet of Things is a developing field, which is basic to empathetic mechanisms, affective computing, and artificial intelligence. Current works in this domain do not explicitly consider the influence of contextual information fusion based on correlation coefficient and memory network with branch structure for sentiment analysis. Unlike present works, this article presents a hierarchical self-attention fusion (H-SATF) model for capturing contextual information better among utterances, a contextual self-attention temporal convolutional network (CSAT-TCN) for sentiment recognition in the social Internet of Things, and a multibranch memory (MBM) network that stores self-speaker and interspeaker sentimental states into global memories. For MOSI data sets, the hybrid H-SATF-CSAT-TCN-MBM model outperforms the state-of-the-art networks and shows 0.31%-9.93% improvement.

As network supporting devices and sensors in the Internet of Things are leaping forward, countless real‐world data will be generated for human intelligent applications. Speech sensor networks, an important part of the Internet of Things, have numerous application needs. Indeed, the sensor data can further help intelligent applications to provide higher quality services, whereas this data may involve considerable noise data. Accordingly, speech signal processing method should be urgently implemented to acquire low‐noise and effective speech data. Blind source separation and enhancement technique refer to one of the representative methods. However, in the unsupervised complex environment, in the only presence of a single‐channel signal, many technical challenges are imposed on achieving single‐channel and multiperson mixed speech separation. For this reason, this study develops an unsupervised speech separation method CNMF+JADE, i.e., a hybrid method combined with Convolutional Non‐Negative Matrix Factorization and Joint Approximative Diagonalization of Eigenmatrix. Moreover, an adaptive wavelet transform‐based speech enhancement technique is proposed, capable of adaptively and effectively enhancing the separated speech signal. The proposed method is aimed at yielding a general and efficient speech processing algorithm for the data acquired by speech sensors. As revealed from the experimental results, in the TIMIT speech sources, the proposed method can effectively extract the target speaker from the mixed speech with a tiny training sample. The algorithm is highly general and robust, capable of technically supporting the processing of speech signal acquired by most speech sensors.

In this paper, we introduce a novel 3D shape reconstruction method from a single‐view sketch image based on a deep neural network. The proposed pipeline is mainly composed of three modules. The first module is sketch component segmentation based on multimodal DNN fusion and is used to segment a given sketch into a series of basic units and build a transformation template by the knots between them. The second module is a nonlinear transformation network for multifarious sketch generation with the obtained transformation template. It creates the transformation representation of a sketch by extracting the shape features of an input sketch and transformation template samples. The third module is deep 3D shape reconstruction using multifarious sketches, which takes the obtained sketches as input to reconstruct 3D shapes with a generative model. It fuses and optimizes features of multiple views and thus is more likely to generate high‐quality 3D shapes. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on a public 3D reconstruction dataset. The results demonstrate that our model can achieve better reconstruction performance than peer methods. Specifically, compared to the state‐of‐the‐art method, the proposed model achieves a performance gain in terms of the five evaluation metrics by an average of 25.5% on the man‐made model dataset and 23.4% on the character object dataset using synthetic sketches and by an average of 31.8% and 29.5% on the two datasets, respectively, using human drawing sketches.

The existing sequential recommendation methods focus on modeling the temporal relationships of user behaviors and are good at using additional item information to improve performance. However, these methods rarely consider the influences of users' sequential subjective sentiments on their behaviors---and sometimes the temporal changes in human sentiment patterns plays a decisive role in users' final preferences. To investigate the influence of temporal sentiments on user preferences, we propose generating preferences by guiding user behavior through sequential sentiments. Specifically, we design a dual-channel fusion mechanism. The main channel consists of sentiment-guided attention to match and guide sequential user behavior, and the secondary channel consists of sparse sentiment attention to assist in preference generation. In the experiments, we demonstrate the effectiveness of these two sentiment modeling mechanisms through ablation studies. Our approach outperforms current state-of-the-art sequential recommendation methods that incorporate sentiment factors.

In this paper, we present a novel and effective technique for short-term traffic flow forecasting. Our main contribution is an extension of Kalman filter, such that it becomes to be able to identify the noise and then filter out it; we hence named the present technique as noise-identified Kalman filter. Our epistemological perspective is that the classic Kalman filter filters out not only the noise but also useful signals. We hence develop the Kalman filter for de-noising while preserving the useful signals by devising a cost function. By conducting extensive experiments on four benchmark data sets, the proposed technique is firmly verified to be effective for short-term traffic flow forecasting, outperforming not only the classic Kalman filter but also other frequently-used parametric and non-parametric techniques.

At Intensive Care Unit (ICU), acute hypotensive episode (AHE) can cause serious consequences. It can make the organs broken, or even the patient dead. Generally AHE is predicted by the doctor clinically. In order to forecast the AHE automatically, this paper proposes an algorithm based on the genetic programming (GP) and random forest (RF). The algorithm obtains features of the signal through the Intrinsic Mode Function (IMF) signal produced by applying empirical mode decomposition (EMD) to the arterial blood pressure (MAP) signal. Then the feature sets and the data sets are grouped to evolve decision functions via GP. Finally, a random forest is formed and the classification result is obtained by voting. The achieved accuracy of the proposed method is 77.55%, the sensitivity is 80.55% and specificity is 75.14% after the five-fold cross-validation.

In this paper, the performance of a sequential Differential Evolution (DE) enhanced by neighborhood search (SDENS) is reported on the set of benchmark functions provided for the CEC2010 Special Session on Large Scale Global Optimization. The original DENS was proposed in our previous work, which differs from existing works which are utilizing the neighborhood search in DE, such as DE with neighborhood search (NSDE) and self-adaptive DE with neighborhood search (SaNSDE). In SDENS, we focus on searching the neighbors of individuals, while the latter two algorithms (NSDE and SaNSDE) work on the adaption of the control parameters F and CR. The proposed algorithm consists of two following main steps. First, for each individual, we create two trial individuals by local and global neighborhood search strategies. Second, we select the fittest one among the current individual and the two created trial individuals as a new current individual. Additionally, sequential DE (DE with one-array) is used as a parent algorithm to accelerate the convergence speed in large scale search spaces. The simulation results for twenty benchmark functions with dimensionality of one thousand are reported.

There exist many difficulties when investment portfolio problems based on Markowitz model are solved by using some traditional methods, such as Newton method, conjugate gradient method, etc. One of the difficulties is that Markowitz model has rigorous constraint conditions. Evolutionary computation is a parallel global optimization algorithm with high efficiency and it has been widely used in portfolio investment field. A heuristic subspace searching algorithm is put forward in this paper for solving investment portfolio optimization problems based on Markowitz model. The experimental results indicate that this algorithm has an improved efficiency compared with traditional evolutionary computation.

Reuse (or reusability) plays an important role in the software engineering. The software reuse technique, considered as an effective approach to improve the productivity, can reduce the cost in software design and development. This paper introduces the concept of reuse in the software into the chromosome and presents an evolutionary modeling algorithm based on the overlapped reuse. Furthermore, a new gene reading & computing machine is constructed for calculating the fitness of chromosome which has the characteristic of reusability. As a new kind of modeling algorithm, this is a new research way for evolutionary modeling.

A new evolutionary algorithm based on quantum statistical mechanics (QSEA) is raised in this paper. In the algorithm, the whole evolutionary system is treated as a quantum statistical system, where quantum coding is adopted to express chromosomes, and superposition of quantum bits is used to simulate the linear superposition state of the system. Quantum system entropy and statistical energy have been defined by analogy with corresponding concepts in quantum statistical mechanics. And the competition between quantum statistical energy and entropy of the system is used to simulate the conflict between dasiaselection pressurepsila and dasiadiversity of populationpsila, which helps the algorithm to keep a delicate balance between these two issues, and obtain optimal solution rapidly. Numerical experiments show that this new algorithm has high efficiency and strong ability to get global optimal solution.