Knowledge graph completion (KGC) aims to alleviate the inherent incompleteness of knowledge graphs (KGs), a crucial task for numerous applications such as recommendation systems and drug repurposing. The success of knowledge graph embedding (KGE) models provokes the question about the explainability: ``\textit{Which the patterns of the input KG are most determinant to the prediction}?'' Particularly, path-based explainers prevail in existing methods because of their strong capability for human understanding. In this paper, based on the observation that a fact is usually determined by the synergy of multiple reasoning chains, we propose a novel explainable framework, dubbed KGExplainer, to explore synergistic pathways. KGExplainer is a model-agnostic approach that employs a perturbation-based greedy search algorithm to identify the most crucial synergistic paths as explanations within the local structure of target predictions. To evaluate the quality of these explanations, KGExplainer distills an evaluator from the target KGE model, allowing for the examination of their fidelity. We experimentally demonstrate that the distilled evaluator has comparable predictive performance to the target KGE. Experimental results on benchmark datasets demonstrate the effectiveness of KGExplainer, achieving a human evaluation accuracy of 83.3\% and showing promising improvements in explainability. Code is available at \url{https://github.com/xiaomingaaa/KGExplainer}

Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling strategies. However, they generally overlook domain-invariant pathological patterns and underutilize the rich contextual knowledge of foundation models, relying solely on visual information, which is insufficient for distinguishing subtle pathological variations. Therefore, we propose integrating fine-grained pathological descriptions to complement prototypes with additional context, thereby resolving ambiguities in borderline cases. Specifically, we propose a Hierarchical Anchor Prototype Modulation (HAPM) framework to facilitate DR grading. First, we introduce a variance spectrum-driven anchor prototype library that preserves domain-invariant pathological patterns. We further employ a hierarchical differential prompt gating mechanism, dynamically selecting discriminative semantic prompts from both LVLM and LLM sources to address semantic confusion between adjacent DR grades. Finally, we utilize a two-stage prototype modulation strategy that progressively integrates clinical knowledge into visual prototypes through a Pathological Semantic Injector (PSI) and a Discriminative Prototype Enhancer (DPE). Extensive experiments across eight public datasets demonstrate that our approach achieves pathology-guided prototype evolution while outperforming state-of-the-art methods. The code is available at https://github.com/zhcz328/HAPM.

Understanding how the brain responds to external stimuli and decoding this process has been a significant challenge in neuroscience. While previous studies typically concentrated on brain-to-image and brain-to-language reconstruction, our work strives to reconstruct gestures associated with speech stimuli perceived by brain. Unfortunately, the lack of paired {brain, speech, gesture} data hinders the deployment of deep learning models for this purpose. In this paper, we introduce a novel approach, fMRI2GES, that allows training of fMRI-to-gesture reconstruction networks on unpaired data using Dual Brain Decoding Alignment. This method relies on two key components: (i) observed texts that elicit brain responses, and (ii) textual descriptions associated with the gestures. Then, instead of training models in a completely supervised manner to find a mapping relationship among the three modalities, we harness an fMRIto- text model, a text-to-gesture model with paired data and an fMRI-to-gesture model with unpaired data, establishing dual fMRI-to-gesture reconstruction patterns. Afterward, we explicitly align two outputs and train our model in a self-supervision way. We show that our proposed method can reconstruct expressive gestures directly from fMRI recordings. We also investigate fMRI signals from different ROIs in the cortex and how they affect generation results. Overall, we provide new insights into decoding co-speech gestures, thereby advancing our understanding of neuroscience and cognitive science.

Video colorization poses challenging tasks, necessitating structural stability, continuity, and details control in the colors produced. In this paper, based on a pretrained text-to-image model, we introduce the Gated Color Guidance module (GCG ), enabling the model to adaptively perform color propagation or generation according to the structural differences between reference and grayscale frames. Based on this multifunctionality, we propose a novel two-stage coloring strategy. In the first stage, under reference-mask condition, the model autonomously and jointly colors input keyframes in a one-to-many color domain mapping, while temporal coherence constraints are emphasized by modifying the attention mechanism. In the second stage, under reference-guided condition, the model effectively captures the colors of matching structures in the reference, and we further introduce Sliding Reference Grid strategy (SRG) to merge and extract the color features from multiple frames, providing more stable coloring for the grayscale frames. Through this pipeline, we can achieve high-quality and stable video coloring while maintaining the accuracy of detailed colors. Additionally, the two-stage strategy is flexible and detachable, allowing users to adjust the number of selected reference frames to balance coloring quality and efficiency. Extensive experiments demonstrate that our method significantly outperforms previous state-of-the-art models in both qualitative comparison and quantitative measurement.

Molecular interaction prediction plays a crucial role in forecasting unknown interactions between molecules, such as drug-target interaction (DTI) and drug-drug interaction (DDI), which are essential in the field of drug discovery and therapeutics. Although previous prediction methods have yielded promising results by leveraging the rich semantics and topological structure of biomedical knowledge graphs (KGs), they have primarily focused on enhancing predictive performance without addressing the presence of inevitable noise and inconsistent semantics. This limitation has hindered the advancement of KG-based prediction methods. To address this limitation, we propose BioKDN (BiomedicalKnowledge GraphDenoisingNetwork) for robust molecular interaction prediction. BioKDN refines the reliable structure of local subgraphs by denoising noisy links in a learnable manner, providing a general module for extracting task-relevant interactions. To enhance the reliability of the refined structure, BioKDN maintains consistent and robust semantics by smoothing relations around the target interaction. By maximizing the mutual information between reliable structure and smoothed relations, BioKDN emphasizes informative semantics to enable precise predictions. Experimental results on real-world datasets show that BioKDN surpasses state-of-the-art models in DTI and DDI prediction tasks, confirming the effectiveness and robustness of BioKDN in denoising unreliable interactions within contaminated KGs.

Exemplar-based anime line art colorization of the same character has been a challenging problem in digital art production because of the sparse representation of line images and the significantly different anime appearance between line and color images. Therefore, it is a fundamental problem to find semantic correspondence between two kinds of images. In this paper, we propose a correspondence learning Transformer network for exemplar-based line art colorization, called ArtFormer, which utilizes a Transformer-based architecture to learn both spatial and visual relationships between line art and color images. ArtFormer mainly consists of two parts: correspondence learning and high-quality image generation. In particular, the correspondence learning module is composed of several Transformer blocks, each of which formulates the deep line image features and color images features as queries and keys, and learns the dense correspondence between two image domains. Then, the network synthesizes high-quality images with a newly proposed Spatial Attention Adaptive Normalization (SAAN) that uses warped deep exemplar features to modulate the shallow features for better adaptive normalization parameters generation. Both qualitative and quantitative experiments show that our method achieves the best performance on exemplar-based line art colorization compared with state-of-the-art methods and other baselines.

With the rapid development of stereoscopic vision applications, stereo image processing techniques have attracted increasing attention in both academic and industrial communities. In this paper, we study the fundamental stereo image super-resolution (SR) problem, which aims to recover high-resolution stereo images from low-resolution (LR) stereo images. Since disparities between stereo images vary significantly, convolutional network-based stereo image SR methods show a limitation in capturing long-range dependencies. To address this problem, this paper proposes to leverage the capability of self-attention in Transformers to efficiently capture reliable stereo correspondence and incorporate cross-view information for stereo image SR. Our model, named Steformer, consists of three parts: cross attentive feature extraction, cross-to-intra information integration and high-quality image reconstruction. In particular, the cross attentive feature extraction module employs residual cross Steformer blocks (RCSB) for long-range cross-view information extraction. Then, the cross-to-intra information integration module exploits cross-view and intra-view information using cross-to-intra attention mechanism (C2IAM). Finally, residual Steformer blocks (RSB) are designed for feature pre-processing in high-quality image reconstruction. Extensive experiments show that Steformer achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations, while the total number of parameters can be reduced by up to 40.71%.

State-of-the-art unsupervised image-to-image translation (I2I) methods have made great progress on transferring images from a source domain X to a target domain Y. However, training these unsupervised I2I models on imbalanced target domain (e.g., Y with limited samples) usually causes mode collapse, which has not been well solved in current literature. In this work, we propose a new Cross-domain Adaptive Co-learning paradigm, CACOLIT, to alleviate the imbalanced unsupervised I2I training problem. Concretely, CACOLIT first constructs a teacher translation model by introducing an auxiliary domain along with source domain as well as two complementary student translation models formulating an I2I closed loop. Then, the two student models are simultaneously learned by transferring correspondence knowledge from teacher model in an interactive way. With extensive experiments on both human face style transfer and animal face translation tasks, we demonstrate that our adaptive co-learning model effectively transfers correspondence knowledge from teacher model to student models and generates more diverse and realistic images than existing I2I methods both qualitatively and quantitatively.

Audience providing proper reaction during a conversation can bring positive impact to speaker, which is significant to digital human and social agent areas. Given information sent by speaker, responsive listener head synthesis task aims to generate corresponding listener behaviours such as nodding, thinking and smiling. A common method is to build listener responsive pattern by analyzing acoustic and facial feature of speaker. However, it is hard to understand what speaker means, purely based on acoustic and facial feature since numerous message is buried in language. Traditional method may lead to similar results ignoring the diversity of input. Therefore, in this paper we presents a new Semantic-aware Responsive Listener Head Synthesis (SaRLHS) approach by considering semantic information lied in language patterns in addition to acoustic and facial feature. Besides, we implement a post-face enhancement process to increase the visual effects. Moreover, we won the People's Selection Awards and the second place on Grand Challenges of ACM 2022 conference.

Reservoir classification is an essential step for the exploration and production process in the oil and gas industry. An appropriate automatic reservoir classification will not only reduce the manual workloads of experts, but also help petroleum companies to make optimal decisions efficiently, which in turn will dramatically reduce the costs. Existing methods mainly focused on generating reservoir classification in a single geological block but failed to work well on a new oilfield block. Indeed, how to transfer the subsurface characteristics and make accurate reservoir classification across the geological oilfields is a very important but challenging problem. To that end, in this paper, we present a focused study on the cross-oilfield reservoir classification task. Specifically, we first propose a Multi-scale Sensor Extraction (MSE) to extract the multi-scale feature representations of geological characteristics from multivariate well logs. Furthermore, we design an encoder-decoder module, Specific Feature Learning (SFL), to take advantage of specific information of both oilfields. Then, we develop a Knowledge-Attentive Transfer (KAT) module to learn the feature-invariant representation and transfer the geological knowledge from a source oilfield to a target oilfield. Finally, we evaluate our approaches by conducting extensive experiments with real-world industrial datasets. The experimental results clearly demonstrate the effectiveness of our proposed approaches to transfer the geological knowledge and generate the cross-oilfield reservoir classifications.

Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where the learning experiences are ignored and the obtained model cannot be adapted to a new coming domain. In this work, we take on unsupervised domain translation problems from a meta-learning perspective. We propose a model called Meta-Translation GAN (MT-GAN) to find good initialization of translation models. In the meta-training procedure, MT-GAN is explicitly trained with a primary translation task and a synthesized dual translation task. A cycle-consistency meta-optimization objective is designed to ensure the generalization ability. We demonstrate effectiveness of our model on ten diverse two-domain translation tasks and multiple face identity translation tasks. We show that our proposed approach significantly outperforms the existing domain translation methods when each domain contains no more than ten training samples.

Visual Emotion Recognition has attracted more and more research attention in recent years. Existing approaches mainly depend on facial expression or analyze the whole image between positive and negative. Actually, people can recognize multiple emotions from one image based on global and 10-cal information. In this paper, we propose a Context-Aware Generation-Based Net (CAGBN), a novel architecture that makes full use of global and local information of the image by considering both the whole image and details of the target person. Inspired by psychological studies that when viewing a person in his situation, we tend to give judgments gradually rather than assign all labels at the same time, CAGBN transforms the multi-label classification problem into a sequence generation task for better recognition. Extensive experimental results on the emotion recognition dataset demonstrate the superiority and rationality of CAGBN.

Ensemble pruning, selecting a subset of individual learners from an original ensemble, alleviates the deficiencies of ensemble learning on the cost of time and space. Accuracy and diversity serve as two crucial factors, while they usually conflict with each other. To balance both of them, we formalize the ensemble pruning problem as an objection maximization problem based on information entropy. Then we propose an ensemble pruning method, including a centralized version and a distributed version, in which the latter is to speed up the former. Finally, we extract a general distributed framework for ensemble pruning, which can be widely suitable for most of the existing ensemble pruning methods and achieve less time-consuming without much accuracy degradation. Experimental results validate the efficiency of our framework and methods, particularly concerning a remarkable improvement of the execution speed, accompanied by gratifying accuracy performance.

Demand forecasting factory production is of particular importance for retailers of perishable goods, as they are produced daily with a fixed production lead time. Over- or underestimating demand can result in loss of profits due to stock-outs or overstock. However, demand forecasting and production planning for perishable goods represent a significant challenge due to factors such as high volatility, significant variation, the dynamics of store-level product demand, and the need for L day ahead forecasting that allows enough time for production planning. By collaborating with a leading perishable product retailer, we have analyzed (1) detailed internal supply chain data, including sales transaction records and day-end inventories, along with (2) environmental factors, including temperature, weather conditions and wind speed. With the aim of minimizing loss of profit caused by inaccurate forecasting, we propose the following three-stage hierarchical demand forecasting model that leverages the combined data for perishable goods production planning: 1. Identification of store-level demand patterns, 2. store clustering for aggregated production, and 3. a recurrent dynamic network based on a nonlinear autoregressive network with exogenous inputs (NARX) for L-day ahead demand forecasting. Finally, we validate the proposed approach by comparing the loss of profits using this model with other baselines along with the industry standard model used in the perishable goods industry. Our proposed model successfully reduces lost profits to 3.30% of total sales, representing a reduction of 1.71% when compared with the industry standard production system.

Image translation across different domains has attracted much attention in both machine learning and computer vision communities. Taking the translation from a source domain to a target domain as an example, existing algorithms mainly rely on two kinds of loss for training: One is the discrimination loss, which is used to differentiate images generated by the models and natural images; the other is the reconstruction loss, which measures the difference between an original image and the reconstructed version. In this work, we introduce a new kind of loss, multi-path consistency loss, which evaluates the differences between direct translation from source domain to target domain and indirect translation from source domain to an auxiliary domain to target domain, to regularize training. For multi-domain translation (at least, three) which focuses on building translation models between any two domains, at each training iteration, we randomly select three domains, set them respectively as the source, auxiliary and target domains, build the multi-path consistency loss and optimize the network. For two-domain translation, we need to introduce an additional auxiliary domain and construct the multi-path consistency loss. We conduct various experiments to demonstrate the effectiveness of our proposed methods, including face-to-face translation, paint-to-photo translation, and de-raining/de-noising translation.

Neural machine translation (NMT) heavily relies on parallel bilingual corpora for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection and help the training procedure of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the reverse translation model (target-to-source translation model) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. Then we propose two different methods to leverage the law of total probability, including marginal distribution regularization and likelihood maximization of monolingual corpora. Experiment results on English-French and German-English tasks demonstrate that our methods achieve significant improvement over several strong baselines.

Neural machine translation (NMT) heavily relies on parallel bilingual data for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection to learn from and regularize the training of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. That is, we transfer the knowledge contained in the dual model to boost the training of the primal model (source-to-target translation), and we call such an approach dual transfer learning. Experiment results on English-French and German-English tasks demonstrate that dual transfer learning achieves significant improvement over several strong baselines and obtains new state-of-the-art results.

Keyphrases have been widely used in large document collections for providing a concise summary of document content. While significant efforts have been made on the task of automatic keyphrase extraction, existing methods have challenges in training a robust supervised model when there are insufficient labeled data in the resource-poor domains. To this end, in this paper, we propose a novel Topic-based Adversarial Neural Network (TANN) method, which aims at exploiting the unlabeled data in the target domain and the data in the resource-rich source domain. Specifically, we first explicitly incorporate the global topic information into the document representation using a topic correlation layer. Then, domain-invariant features are learned to allow the efficient transfer from the source domain to the target by utilizing adversarial training on the topic-based representation. Meanwhile, to balance the adversarial training and preserve the domain-private features in the target domain, we reconstruct the target data from both forward and backward directions. Finally, based on the learned features, keyphrase are extracted using a tagging method. Experiments on two realworld cross-domain scenarios demonstrate that our method can significantly improve the performance of keyphrase extraction on unlabeled or insufficiently labeled target domain.

Supply chain management aims at delivering goods in the shortest time at the lowest possible price while ensuring the best possible quality and is now vital to the success of the online retail business. Executing effective warehouse site selection has been one of the key challenges in the development of a successful supply chain system. While some effective strategies for warehouse site selection have been identified by the domain experts based on their experiences, the emergence of new ways of collecting fine-grained supply chain data has enabled a new paradigm for warehouse site selection. Indeed, in this paper, we provide a data-smart approach for addressing the connected capacitated warehouse location problem (CCWL), which searches for the minimum total transportation cost of the warehouse network including supplier-warehouses shipping cost, warehouse-customer delivering cost and the cost of warehouse-warehouse inter-transportation. Specifically, we first design a sales distribution prediction model and evaluate the importance of customer logistic service utilities on online market sales demand for online retailers. Then, we propose the E&M algorithm to optimize warehouse locations continuously with much less computation cost. Moreover, the computation cost is further reduced through delivery demand based Hierarchical Clustering which reduces the problem size by grouping delivering cities with close locations. Finally, we validate the proposed method on real-world e-Commerce supply chain data and the selection effect of new warehouses is evaluated in terms of sales improvement with faster delivery and more effective inventory management.

Matrix Factorization (MF) is among the most widely used techniques for collaborative filtering based recommendation. Along this line, a critical demand is to incrementally refine the MF models when new ratings come in an online scenario. However, most of existing incremental MF algorithms are limited by specific MF models or strict use restrictions. In this paper, we propose a general incremental MF framework by designing a linear transformation of user and item latent vectors over time. This framework shows a relatively high accuracy with a computation and space efficient training process in an online scenario. Meanwhile, we explain the framework with a low-rank approximation perspective, and give an upper bound on the training error when this framework is used for incremental learning in some special cases. Finally, extensive experimental results on two real-world datasets clearly validate the effectiveness, efficiency and storage performance of the proposed framework.

An e-commerce website provides a platform for merchants to sell products to customers. While most existing research focuses on providing customers with personalized product suggestions by recommender systems, in this paper, we consider the role of merchants and introduce a parallel problem, i.e., how to select the most valuable customers for a merchant? Accurately answering this question can not only help merchants to gain more profits, but also benefit the ecosystem of e-commence platforms. To deal with this problem, we propose a general approach by taking into consideration the interest and profit of each customer to the merchant, i.e., select the customers who are not only interested in the merchant to ensure the visit of the merchant, but also capable of making good profits. Specifically, we first generate candidate customers for a given merchant by using traditional recommendation techniques. Then we select a set of the valuable customers from candidate customers, which has the balanced maximization between the interest and the profit metrics. Given the NP-hardness of the balanced maximization formulation, we further introduce efficient techniques to solve this maximization problem by exploiting the inherent submodularity property. Finally, extensive experimental results on a real-world dataset demonstrate the effectiveness of our proposed approach.