RESUMEN
Online education brings more possibilities for personalized learning, in which identifying the cognitive state of learners is conducive to better providing learning services. Cognitive diagnosis is an effective measurement to assess the cognitive state of students through response data of answering the problems(e.g., right or wrong). Generally, the cognitive diagnosis framework includes the mastery of skills required by a specified problem and the aggregation of skills. The current multi-skill aggregation methods are mainly divided into conjunctive and compensatory methods and generally considered that each skill has the same effect on the correct response. However, in practical learning situations, there may be more complex interactions between skills, in which each skill has different weight impacting the final result. To this end, this paper proposes a generalized multi-skill aggregation method based on the Sugeno integral (SI-GAM) and introduces fuzzy measures to characterize the complex interactions between skills. We also provide a new idea for modeling multi-strategy problems. The cognitive diagnosis process is implemented by a more general and interpretable aggregation method. Finally, the feasibility and effectiveness of the model are verified on synthetic and real-world datasets.
RESUMEN
Generating molecules with desired properties is an important task in chemistry and pharmacy. An efficient method may have a positive impact on finding drugs to treat diseases like COVID-19. Data mining and artificial intelligence may be good ways to find an efficient method. Recently, both the generative models based on deep learning and the work based on genetic algorithms have made some progress in generating molecules and optimizing the molecule's properties. However, existing methods need to be improved in efficiency and performance. To solve these problems, we propose a method named the Chemical Genetic Algorithm for Large Molecular Space (CALM). Specifically, CALM employs a scalable and efficient molecular representation called molecular matrix. Then, we design corresponding crossover, mutation, and mask operators inspired by domain knowledge and previous studies. We apply our genetic algorithm to several tasks related to molecular property optimization and constraint molecular optimization. The results of these tasks show that our approach outperforms the other state-of-the-art deep learning and genetic algorithm methods, where the z tests performed on the results of several experiments show that our method is more than 99% likely to be significant. At the same time, based on the experimental results, we point out the insufficiency in the experimental evaluation standard which affects the fair evaluation of previous work. Supplementary Information: The online version contains supplementary material available at 10.1007/s11390-021-0970-3.
RESUMEN
Absolute phase unwrapping in the phase-shifting profilometry (PSP) is significant for dynamic 3-D measurements over a large depth range. Among traditional phase unwrapping methods, spatial phase unwrapping can only retrieve a relative phase map, and temporal phase unwrapping requires auxiliary projection sequences. We propose a shading-based absolute phase unwrapping (SAPU) framework for in situ 3-D measurements without additional projection patterns. First, the wrapped phase map is calculated from three captured images. Then, the continuous relative phase map is obtained using the phase histogram check (PHC), from which the absolute phase map candidates are derived with different fringe orders. Finally, the correct absolute phase map candidate can be determined without additional patterns or spatial references by applying the shading matching check (SMC). The experimental results demonstrate the validity of the proposed method.
RESUMEN
Pixel-by-pixel phase unwrapping (PPU) has been employed to rapidly achieve three-dimensional (3-D) shape measurement without additional projection patterns. However, the maximum measurement depth range that traditional PPU can handle is within 2π in phase domain; thus PPU fails to measure the dynamic object surface when the object moves in a large depth range. In this paper, we propose a novel adaptive pixel-by-pixel phase unwrapping (APPU), which extends PPU to an unlimited depth range. First, with PPU, temporary phase maps of objects are obtained referring to the absolute phase map of a background plane. Second, we quantify the difference between the image edges of the temporary phase maps and the practical depth edges of dynamic objects. Moreover, according to the degree of the edge difference, the temporary phase maps are categorized into two classes: failed phase maps and relative phase maps. Third, by combining a mobile reference phase map and the edge difference quantization technique, the failed phase maps are correspondently converted into relative phase maps. Finally, the relative phase maps are innovatively transformed into the absolute phase maps using a new shadow-informed depth estimation method (SDEM). The proposed approach is suitable for high-speed 3-D shape measurement without depth limitations or additional projection patterns.
RESUMEN
In a typical digital fringe projection (DFP) system, the shadows in the fringe images cause errors in the phase map. We propose a novel discriminative repair approach to remove the shadow-induced error in the phase map. The proposed approach first classifies the shadow area in the phase map obtained by the DFP into two categories: valid shadow area and invalid shadow area. Then the valid shadow area is repaired by a proposed neighboring information fusion phase estimation (NIFPE) method, which fuses the phase gradient into the result of kernel density estimation (KDE) through the Kalman filter (KF) algorithm. The invalid shadow area is repaired by a proposed background phase matching (BPM) method. The experimental results demonstrate that the shadow-induced error in the phase map can be removed, which verifies the effectiveness of the proposed approach.
RESUMEN
Arbitrary two-dimensional (2-D) motion introduces coordinate errors and phase errors to three-dimensional (3-D) shape measurement of objects in phase-shifting profilometry (PSP). This paper presents a new robust 3-D reconstruction method for arbitrary 2-D moving objects by introducing an adaptive reference phase map and the motion estimation based on fence image. First, a composite fence image is used to track object motion. Second, to obtain the transformation matrixes and remove the coordinate errors among object images, the angle extraction technique and the 1-D hybrid phase correlation method (1-D HPCM) are integrated to automatically estimate the sub-pixel motion of objects. Third, the phase errors are compensated to obtain the rough absolute phase map of objects by combining the transformation matrixes with the reference phase map. Finally, the absolute phase map is refined to reconstruct the 3-D surfaces of moving objects with adaptive reference phase map. The proposed computational framework can accurately and automatically realize 3-D shape measurement of arbitrary objects with 2-D movement. The results of experiment verify the effectiveness of our computational framework.
RESUMEN
Factorization machines (FMs) are widely used in recommender systems due to their adaptability and ability to learn from sparse data. However, for the ubiquitous non-interactive features in sparse data, existing FMs can only estimate the parameters corresponding to these features via the inner product of their embeddings. Undeniably, they cannot learn the direct interactions of these features, which limits the model's expressive power. To this end, we first present MixFM, inspired by Mixup, to generate auxiliary training data to boost FMs. Unlike existing augmentation strategies that require labor costs and expertise to collect additional information such as position and fields, these augmented data are only by the convex combination of the raw ones without any professional knowledge support. More importantly, if non-interactive features exist in parent samples to be mixed respectively, MixFM will establish their direct interactions. Second, considering that MixFM may generate redundant or even detrimental instances, we further put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM). Guided by the customized saliency, SMFM can generate more informative neighbor data. Through theoretical analysis, we prove that the proposed methods minimize the upper bound of the generalization error, which positively enhances FMs. Finally, extensive experiments on seven datasets confirm that our approaches are superior to baselines. Notably, the results also show that "poisoning" mixed data benefits the FM variants.
RESUMEN
Mobility data has attracted the researchers for the past few years because of its rich context and spatiotemporal nature, where this information can be used for potential applications like early warning system, route prediction, traffic management, advertisement, social networking, and community finding. All the mentioned applications are based on mobility profile building and user trend analysis, where mobility profile building is done through significant places extraction, user's actual movement prediction, and context awareness. However, significant places extraction and user's actual movement prediction for mobility profile building are a trivial task. In this paper, we present the user similarity mining-based methodology through user mobility profile building by using the semantic tagging information provided by user and basic GSM network architecture properties based on unsupervised clustering approach. As the mobility information is in low-level raw form, our proposed methodology successfully converts it to a high-level meaningful information by using the cell-Id location information rather than previously used location capturing methods like GPS, Infrared, and Wifi for profile mining and user similarity mining.
Asunto(s)
Algoritmos , Inteligencia Artificial , Redes de Comunicación de Computadores , Minería de Datos/métodos , Sistemas de Información Geográfica , Procesamiento de Señales Asistido por Computador , Tecnología InalámbricaRESUMEN
Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks, such as natural language inference (NLI) and paraphrase identification (PI). Much recent progress has been made in this area, especially attention-based methods and pretrained language model-based methods. However, most of these methods focus on all the important parts in sentences in a static way and only emphasize how important the words are to the query, inhibiting the ability of the attention mechanism. In order to overcome this problem and boost the performance of the attention mechanism, we propose a novel dynamic reread (DRr) attention, which can pay close attention to one small region of sentences at each step and reread the important parts for better sentence representations. Based on this attention variation, we develop a novel DRr network (DRr-Net) for sentence semantic matching. Moreover, selecting one small region in DRr attention seems insufficient for sentence semantics, and employing pretrained language models as input encoders will introduce incomplete and fragile representation problems. To this end, we extend DRr-Net to locally aware dynamic reread attention net (LadRa-Net), in which local structure of sentences is employed to alleviate the shortcoming of byte-pair encoding (BPE) in pretrained language models and boost the performance of DRr attention. Extensive experiments on two popular sentence semantic matching tasks demonstrate that DRr-Net can significantly improve the performance of sentence semantic matching. Meanwhile, LadRa-Net is able to achieve better performance by considering the local structures of sentences. In addition, it is exceedingly interesting that some discoveries in our experiments are consistent with some findings of psychological research.
RESUMEN
Designing molecules with desirable physiochemical properties and functionalities is a long-standing challenge in chemistry, material science, and drug discovery. Recently, machine learning-based generative models have emerged as promising approaches for de novo molecule design. However, further refinement of methodology is highly desired as most existing methods lack unified modeling of 2D topology and 3D geometry information and fail to effectively learn the structure-property relationship for molecule design. Here we present MolCode, a roto-translation equivariant generative framework for molecular graph-structure Co-design. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Extensive experimental results show that MolCode outperforms previous methods on a series of challenging tasks including de novo molecule design, targeted molecule discovery, and structure-based drug design. Particularly, MolCode not only consistently generates valid (99.95% validity) and diverse (98.75% uniqueness) molecular graphs/structures with desirable properties, but also generates drug-like molecules with high affinity to target proteins (61.8% high affinity ratio), which demonstrates MolCode's potential applications in material design and drug discovery. Our extensive investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design, and provide new insights into machine learning-based molecule representation and generation.
RESUMEN
Saturation information in hazy images is conducive to effective haze removal, However, existing saturation-based dehazing methods just focus on the saturation value of each pixel itself, while the higher-level distribution characteristic between pixels regarding saturation remains to be harnessed. In this paper, we observe that the pixels, which share the same surface reflectance coefficient in the local patches of haze-free images, exhibit a linear relationship between their saturation component and the reciprocal of their brightness component in the corresponding hazy images normalized by atmospheric light. Furthermore, the intercept of the line described by this linear relationship on the saturation axis is exactly the saturation value of these pixels in the haze-free images. Using this characteristic of saturation, termed saturation line prior (SLP), the transmission estimation is translated into the construction of saturation lines. Accordingly, a new dehazing framework using SLP is proposed, which employs the intrinsic relevance between pixels to achieve a reliable saturation line construction for transmission estimation. This approach can recover the fine details and attain realistic colors from hazy scenes, resulting in a remarkable visibility improvement. Extensive experiments in real-world and synthetic hazy images show that the proposed method performs favorably against state-of-the-art dehazing methods. Code is available on https://github.com/LPengYang/Saturation-Line-Prior.
RESUMEN
Recent studies have shown that recommender systems are vulnerable, and it is easy for attackers to inject well-designed malicious profiles into the system, resulting in biased recommendations. We cannot deprive these data's injection right and deny their existence's rationality, making it imperative to study recommendation robustness. Despite impressive emerging work, threat assessment of the bi-level poisoning problem and the imperceptibility of poisoning users remain key challenges to be solved. To this end, we propose Infmix, an efficient poisoning attack strategy. Specifically, Infmix consists of an influence-based threat estimator and a user generator, Usermix. First, the influence-based estimator can efficiently evaluate the user's harm to the recommender system without retraining, which is challenging for existing attacks. Second, Usermix, a distribution-agnostic generator, can generate unnoticeable fake data even with a few known users. Under the guidance of the threat estimator, Infmix can select the users with large attacking impacts from the quasi-real candidates generated by Usermix. Extensive experiments demonstrate Infmix's superiority by attacking six recommendation systems with four real datasets. Additionally, we propose a novel defense strategy, adversarial poisoning training (APT). It mimics the poisoning process by injecting fake users (ERM users) committed to minimizing empirical risk to build a robust system. Similar to Infmix, we also utilize the influence function to solve the bi-level optimization challenge of generating ERM users. Although the idea of "fighting fire with fire" in APT seems counterintuitive, we prove its effectiveness in improving recommendation robustness through theoretical analysis and empirical experiments.
RESUMEN
Entity summarization is a novel and efficient way to understand real-world facts and solve the increasing information overload problem in large-scale knowledge graphs (KG). Existing studies mainly rely on ranking independent entity descriptions as a list under a certain scoring standard such as importance. However, they often ignore the relatedness and even semantic overlap between individual descriptions. This may seriously interfere with the contribution judgment of descriptions for entity summarization. Actually, the entity summary is a whole to comprehensively integrate the main aspects of entity descriptions, which could be naturally treated as a set. Unfortunately, the exploration of these set characteristics for entity summarization is still an open issue with great challenges. To that end, we draw inspiration from a set completion perspective and propose an entity summarization method with complementarity and salience (ESCS) to deeply exploit description complementarity and salience in order to form a summary set for the target entity. Specifically, we first generate entity description representations with textual features in the description embedding module. For the purpose of learning complementary relationships within the entire summary set, we devise a bi-directional long short-term memory structure to capture global complementarity for each summary in the summary complementarity learning module. Meanwhile, in order to estimate the salience of individual descriptions, we calculate similarities between semantic embeddings of the target entity and its property-value pairs in the description salience learning module. Next, with a joint learning stage, we can optimize ESCS from a set completion perspective. Finally, a summary generation strategy is designed to infer the entire summary set step-by-step for the target entity. Extensive experiments on a public benchmark have clearly demonstrated the effectiveness of ESCS and revealed the potential of set completion in entity summarization task.
Asunto(s)
Benchmarking , Redes Neurales de la Computación , Conocimiento , Aprendizaje , Memoria a Largo PlazoRESUMEN
The efficiency of communication across workers is a significant factor that affects the performance of federated learning. Though periodic communication strategy is applied to reduce communication rounds in training, the communication cost is still high when the training data distributions are not independently and identically distributed (non-IID) which is common in federated learning. Recently, some works introduce variance reduction to eliminate the effect caused by non-IID data among workers. Nevertheless the provable optimal communication complexity O(log(ST)) and convergence rate O(1/(ST)) cannot be achieved simultaneously, where S denotes the number of sampled workers in each round and T is the number of iterations. To deal with this dilemma, we propose an optimization algorithm SQUARFA that adopts stagewise training framework coupling with variance reduction and uses a quick-start phase in each loop. Theoretical results show that SQUARFA achieves both optimal convergence rate and communication complexity for both strongly convex objectives and non-convex objectives under PL condition, thus fills the gap mentioned above. Then, a variant of SQUARFA yields the optimal theoretical results for general non-convex objectives. We further extend the technique in SQUARFA to the large batch setting and achieve optimal communication complexity. Experimental results demonstrate the superiority of the proposed algorithms.
Asunto(s)
Algoritmos , Aprendizaje , Humanos , ComunicaciónRESUMEN
Recently, learning-based multi-exposure fusion (MEF) methods have made significant improvements. However, these methods mainly focus on static scenes and are prone to generate ghosting artifacts when tackling a more common scenario, i.e., the input images include motion, due to the lack of a benchmark dataset and solution for dynamic scenes. In this paper, we fill this gap by creating an MEF dataset of dynamic scenes, which contains multi-exposure image sequences and their corresponding high-quality reference images. To construct such a dataset, we propose a 'static-for-dynamic' strategy to obtain multi-exposure sequences with motions and their corresponding reference images. To the best of our knowledge, this is the first MEF dataset of dynamic scenes. Correspondingly, we propose a deep dynamic MEF (DDMEF) framework to reconstruct a ghost-free high-quality image from only two differently exposed images of a dynamic scene. DDMEF is achieved through two steps: pre-enhancement-based alignment and privilege-information-guided fusion. The former pre-enhances the input images before alignment, which helps to address the misalignments caused by the significant exposure difference. The latter introduces a privilege distillation scheme with an information attention transfer loss, which effectively improves the deghosting ability of the fusion network. Extensive qualitative and quantitative experimental results show that the proposed method outperforms state-of-the-art dynamic MEF methods. The source code and dataset are released at https://github.com/Tx000/Deep_dynamicMEF.
RESUMEN
Automatically solving math word problems (MWPs) is a challenging task for artificial intelligence (AI) and machine learning (ML) research, which aims to answer the problem with a mathematical expression. Many existing solutions simply model the MWP as a sequence of words, which is far from precise solving. To this end, we turn to how humans solve MWPs. Humans read the problem part-by-part and capture dependencies between words for a thorough understanding and infer the expression precisely in a goal-driven manner with knowledge. Moreover, humans can associate different MWPs to help solve the target with related experience. In this article, we present a focused study on an MWP solver by imitating such procedure. Specifically, we first propose a novel hierarchical math solver (HMS) to exploit semantics in one MWP. First, to imitate human reading habits, we propose a novel encoder to learn the semantics guided by dependencies between words following a hierarchical "word-clause-problem" paradigm. Next, we develop a goal-driven tree-based decoder with knowledge application to generate the expression. One step further, to imitate human associating different MWPs for related experience in problem-solving, we extend HMS to the Relation-enHanced Math Solver (RHMS) to utilize the relation between MWPs. First, to capture the structural similarity relation, we develop a meta-structure tool to measure the similarity based on the logical structure of MWPs and construct a graph to associate related MWPs. Then, based on the graph, we learn an improved solver to exploit related experience for higher accuracy and robustness. Finally, we conduct extensive experiments on two large datasets, which demonstrates the effectiveness of the two proposed methods and the superiority of RHMS.
RESUMEN
Excessive proliferation, invasion, metastasis, and immune resistance in pancreatic cancer (PC) makes it one of the most lethal malignant tumors. Recently, DDX60 was found to be involved in the development of various tumors and in immunotherapy. Therefore, we aimed to investigate whether DDX60 is a new factor involved in PC immunotherapy. The DDX60 mRNA was screened using transcriptome sequencing (RNA-seq). The Cox and survival analysis of DDX60 was performed using the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases. In addition, clinical and immune infiltration data in the databases were analyzed and plotted using the R language. Clinical samples and in vitro experiments were used to determine the molecular evolution of DDX60 during PC progression. We found that DDX60 was upregulated in PC tissues (P value = 0.0083) and was associated with poor prognosis and short survival time of patients with PC. Results of Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and gene set variation analyses showed that viral defense, tumor, and immune-related pathways were significantly enriched in samples with high DDX60 expression. The Pearson correlation test demonstrated that DDX60 expression correlated strongly with immune checkpoint and immune system-related metagene clusters. Our results indicated that DDX60 promoted cell proliferation, migration, and invasion and was related to poor prognosis and immune resistance. Therefore, DDX60 may be a promising novel target for PC immunotherapy.
RESUMEN
Recent studies have shown that amphoteric regulatory protein (AREG), a member of the epidermal growth factor (EGF) family, is expressed in many cancers and is an independent prognostic indicator for patients with pancreatic cancer, but whether AREG is regulated at the epigenetic level to promote the development of pancreatic cancer (PC) has not been elucidated. Our results support the notion that AREG is overexpressed in pancreatic cancer tissues and cell lines. Functionally, the deletion of AREG impedes pancreatic cancer (PC) cell proliferation, migration, and invasion. In addition, we identified and validated that methyltransferase-like 3 (METTL3) induced the m6A modification on AREG and facilitated the stability of AREG mRNA after sequencing. Additionally, we obtained experimental evidence that miR-33a-3p targets and inhibits METTL3 from taking action, as predicted by using the miRDB and RNAinter. Remediation experiments showed that miR-33a-3p inhibits PC progression through METTL3. In summary, this research reveals that miR-33a-3p inhibits m6A-induced stabilization of AREG by targeting METTL3, which plays a key role in the aggressive progression of PC. AREG could be a potential target for PC treatment.
Asunto(s)
Anfirregulina , Metiltransferasas , MicroARNs , Neoplasias Pancreáticas , Humanos , Anfirregulina/metabolismo , Factor de Crecimiento Epidérmico , Metiltransferasas/genética , MicroARNs/genética , Neoplasias Pancreáticas/genética , Neoplasias Pancreáticas/metabolismo , Neoplasias Pancreáticas/patología , Transición Epitelial-Mesenquimal , Neoplasias PancreáticasRESUMEN
Text classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially pretrained language models (PLMs). Usually, these methods concentrate on input sentences and corresponding semantic embedding generation. However, for another essential component: labels, most existing works either treat them as meaningless one-hot vectors or use vanilla embedding methods to learn label representations along with model training, underestimating the semantic information and guidance that these labels reveal. To alleviate this problem and better exploit label information, in this article, we employ self-supervised learning (SSL) in model learning process and design a novel self-supervised relation of relation (R 2 ) classification task for label utilization from a one-hot manner perspective. Then, we propose a novel () for text classification, in which text classification and R 2 classification are treated as optimization targets. Meanwhile, triplet loss is employed to enhance the analysis of differences and connections among labels. Moreover, considering that one-hot usage is still short of exploiting label information, we incorporate external knowledge from WordNet to obtain multiaspect descriptions for label semantic learning and extend to a novel () from a label embedding perspective. One step further, since these fine-grained descriptions may introduce unexpected noise, we develop a mutual interaction module to select appropriate parts from input sentences and labels simultaneously based on contrastive learning (CL) for noise mitigation. Extensive experiments on different text classification tasks reveal that can effectively improve the classification performance and can make better use of label information and further improve the performance. As a byproduct, we have released the codes to facilitate other research.
RESUMEN
In the drug discovery and development setting, the ability to accurately predict the human pharmacokinetics (PK) of a candidate compound from preclinical data is critical for informing the effective design of the first-in-human trial. PK prediction is especially challenging for monoclonal antibodies exhibiting nonlinear PK attributed to target-mediated drug disposition (TMDD). Here, we present a model-based method for predicting the PK of PF-03446962, an IgG2 antibody directed against human ALK1 (activin receptor-like kinase 1) receptor. Systems parameters as determined experimentally or obtained from the literature, such as binding affinity (k(on) and k(off)), internalization of the drug-target complex (k(int)), target degradation rate (k(deg)), and target abundance (R(0)), were directly integrated into the modeling and prediction. NONMEM 7 was used to model monkey PK data and simulate human PK profiles based on the construct of a TMDD model using a population-based approach. As validated by actual patient data from a phase I study, the human PK of PF-03446962 were predicted within 1- to 2-fold of observations. Whereas traditional approaches fail, this approach successfully predicted the human PK of a monoclonal antibody exhibiting nonlinearity because of TMDD.