Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach has received tremendous attention due to its powerful feature learning capability and robustness. Although several studies have incorporated this technique for text classification, some limitations remain. First, many text datasets are imbalanced, and the learning mechanism of supervised contrastive learning is sensitive to data imbalance, which may harm the model's performance. Moreover, these models leverage separate classification branches with cross entropy and supervised contrastive learning branches without explicit mutual guidance. To this end, we propose a novel model named SharpReCL for imbalanced text classification tasks. First, we obtain the prototype vector of each class in the balanced classification branch to act as a representation of each class. Then, by further explicitly leveraging the prototype vectors, we construct a proper and sufficient target sample set with the same size for each class to perform the supervised contrastive learning procedure. The empirical results show the effectiveness of our model, which even outperforms popular large language models across several datasets. Our code is available here.

Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning models have exhibited superior performance across diverse applications. Despite their successes, several limitations still exist. First, existing models in the meta-training phase predominantly focus on instance-level features within tasks, neglecting crucial set-level features essential for distinguishing between different categories. Second, these models often utilize query sets directly on classifiers trained with support sets containing only a few labeled examples, overlooking potential distribution shifts between these sets and leading to suboptimal performance. Finally, previous models typically require necessitate abundant labeled data from base classes to extract transferable knowledge, which is typically infeasible in real-world scenarios. To address these issues, we propose a novel model named STAR, which leverages Set funcTions and optimAl tRansport for enhancing unsupervised graph few-shot learning. Specifically, STAR utilizes expressive set functions to obtain set-level features in an unsupervised manner and employs optimal transport principles to align the distributions of support and query sets, thereby mitigating distribution shift effects. Theoretical analysis demonstrates that STAR can capture more task-relevant information and enhance generalization capabilities. Empirically, extensive experiments across multiple datasets validate the effectiveness of STAR. Our code can be found here.

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it. %the wide web. for downstream task analysis. Current leading graph models require a large number of labeled samples for training, which unavoidably leads to overfitting in few-shot scenarios. Recent research has sought to alleviate this issue by simultaneously leveraging graph learning and meta-learning paradigms. However, these graph meta-learning models assume the availability of numerous meta-training tasks to learn transferable meta-knowledge. Such assumption may not be feasible in the real world due to the difficulty of constructing tasks and the substantial costs involved. Therefore, we propose a SiMple yet effectIve approach for graph few-shot Learning with fEwer tasks, named SMILE. We introduce a dual-level mixup strategy, encompassing both within-task and across-task mixup, to simultaneously enrich the available nodes and tasks in meta-learning. Moreover, we explicitly leverage the prior information provided by the node degrees in the graph to encode expressive node representations. Theoretically, we demonstrate that SMILE can enhance the model generalization ability. Empirically, SMILE consistently outperforms other competitive models by a large margin across all evaluated datasets with in-domain and cross-domain settings. Our anonymous code can be found https://github.com/KEAML-JLU/SMILE.

Graphs, as a fundamental data structure, have proven efficacy in modeling complex relationships between objects and are therefore found in wide web applications. Graph classification is an essential task in graph data analysis, which can effectively assist in extracting information and mining content from the web. Recently, few-shot graph classification, a more realistic and challenging task, has garnered great research interest. Existing few-shot graph classification models are all supervised, assuming abundant labeled data in base classes for meta-training. However, sufficient annotation is often challenging to obtain in practice due to high costs or demand for expertise. Moreover, they commonly adopt complicated meta-learning algorithms via episodic training to transfer prior knowledge from base classes. To break free from these constraints, in this paper, we propose a simple yet effective approach named SMART for unsupervised few-shot graph classification without using any labeled data. SMART employs transfer learning philosophy instead of the previously prevailing meta-learning paradigm, avoiding the need for sophisticated meta-learning algorithms. Additionally, we adopt a novel mixup strategy to augment the original graph data and leverage unsupervised pretraining on these data to obtain the expressive graph encoder. We also utilize the prompt tuning technique to alleviate the overfitting and low fine-tuning efficiency caused by the limited support samples of novel classes. Extensive experimental results demonstrate the superiority of our proposed approach, significantly surpassing even leading supervised few-shot graph classification models. Our code is available here.

Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited labeled nodes within the specific task, without explicitly utilizing numerous unlabeled nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS \(++\) . Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-training to extract valuable information from unlabeled nodes. Additionally, we adopt S \({}^{2}\) (scaling and shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS \(++\) . Our code is available here .

A common solution to the semantic heterogeneity problem is to perform knowledge graph (KG) extension exploiting the information encoded in one or more candidate KGs, where the alignment between the reference KG and candidate KGs is considered the critical procedure. However, existing KG alignment methods mainly rely on entity type (etype) label matching as a prerequisite, which is poorly performing in practice or not applicable in some cases. In this paper, we design a machine learning-based framework for KG extension, including an alternative novel property-based alignment approach that allows aligning etypes on the basis of the properties used to define them. The main intuition is that it is properties that intentionally define the etype, and this definition is independent of the specific label used to name an etype, and of the specific hierarchical schema of KGs. Compared with the state-of-the-art, the experimental results show the validity of the KG alignment approach and the superiority of the proposed KG extension framework, both quantitatively and qualitatively.

WeNet is a multidisciplinary project aimed at introducing a platform capable of enhancing socially aware, diverseconscious, richer, and deeper social interactions. This study presents the integration and validation of a tutoring application, named SOS Tutoring UC, based on social interactions on the WeNet platform. The validation has encompassed both the system and the diversity-conscious matching algorithm. The experience reveals several relevant challenges for integrating vertical applications on the WeNet platform and underscores the pivotal role played by understanding diversity-conscious matching algorithms in the integration process.

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose a deep feature-based text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. Our code is available at https://github.com/KEAML-JLU/DeepTextClustering.

The cold-start problem is a major factor that limits the effectiveness of recommendation systems. Having too few available interaction records brings a series of challenges when predicting user preferences. At present, there are two main kinds of strategies for solving this problem from different perspectives. One is cross-domain recommendation (CDR), which introduces additional information by domain knowledge propagation with transfer learning. However, CDR methods follow traditional training processes in machine learning and cannot solve this typical few-shot problem from the perspective of optimization. The other type of methods that has recently emerged is based on meta-learning. Most of these approaches focus only on generating a meta-model to perform better on new tasks and ignore improvements based on cross-domain information. Therefore, it is necessary to design a novel approach to solve this problem with both domain knowledge and meta-optimization. To achieve this goal, a novel cross-domain meta-learner for cold-start recommendation (MetaCDR) is proposed. In MetaCDR, we design a domain knowledge meta-transfer module to connect different domain networks. In addition, we introduce a pretraining strategy to ensure its efficiency. The experimental results show that MetaCDR performs significantly better than state-of-the-art models in a variety of scenarios.

User cold-start is a major challenge in building personalized recommender systems. Due to the lack of sufficient interactions, it is difficult to effectively model new users. One of the main solutions is to obtain an initial model through meta-learning (mainly gradient-based methods) and adapt it to new users with a few steps of gradient descent. Although these methods have achieved remarkable performance, they are still far from being usable in real-world applications due to their high-demand data processing, heavy computational burden, and inability to perform effective user-incremental update. In this paper, we propose a d eployable and c ontinuable m eta-learning-based r ecommendation (DCMR) approach, which can achieve fast user-incremental updating with task replay and first-order gradient descent. Specifically, we introduce a dual-constrained task sampler, distillation-based loss functions, and an adaptive controller in this framework to balance the trade-off between stability and plasticity in updating. In summary, DCMR can be updated while serving new users; in other words, it learns continuously and rapidly from a sequential user stream and is able to make recommendations at any time. The extensive experiments conducted on three benchmark datasets illustrate the superiority of our model.

Attributed networks, as a manifestation of data in non-Euclidean domains, have a wide range of applications in the real world, such as molecular property prediction, social network analysis and anomaly detection. Node classification, as a fundamental research problem in attributed networks, has attracted increasing attention among research communities. However, most existing models cannot be directly applied to the data with limited labeled instances (\textiti.e., the few-shot scenario). Few-shot node classification on attributed networks is gradually becoming a research hotspot. Although several methods aim to integrate meta-learning with graph neural networks to address this problem, some limitations remain. First, they all assume node representation learning using graph neural networks in homophilic graphs. %Hence, suboptimal performance is obtained when these models are applied to heterophilic graphs. Second, existing models based on meta-learning entirely depend on instance-based statistics. %which in few-shot settings are unavoidably degraded by data noise or outliers. Third, most previous models treat all sampled tasks equally and fail to adapt their uniqueness. %which has a significant impact on the overall performance of the model. To solve the above three limitations, we propose a novel graph Meta -learning framework called G raph learning based on P rototype and S caling & shifting transformation (Meta-GPS ). More specifically, we introduce an efficient method for learning expressive node representations even on heterophilic graphs and propose utilizing a prototype-based approach to initialize parameters in meta-learning. Moreover, we also leverage S$^2$ (scaling & shifting) transformation to learn effective transferable knowledge from diverse tasks. Extensive experimental results on six real-world datasets demonstrate the superiority of our proposed framework, which outperforms other state-of-the-art baselines by up to 13% absolute improvement in terms of related metrics.

User cold-start recommendation is a serious problem that limits the performance of recommender systems (RSs). Recent studies have focused on treating this issue as a few-shot problem and seeking solutions with model-agnostic meta-learning (MAML). Such methods regard making recommendations for one user as a task and adapt to new users with a few steps of gradient updates on the meta-model. However, none of those methods consider the limitation of user representation learning imposed by the special task setting of MAML-based RSs. And they learn a common meta-model for all users while ignoring the implicit grouping distribution induced by the correlation differences among users. In response to the above problems, we propose a pretrained network modulation and task adaptation approach (PNMTA) for user cold-start recommendation. In the pretraining stage, a pretrained model is obtained with non-meta-learning methods to achieve better user representation and generalization, which can also transfer the learned knowledge to the meta-learning stage for modulation. During the meta-learning stage, an encoder modulator is utilized to realize the memorization and correction of prior parameters for the meta-learning task, and a predictor modulator is introduced to condition the model initialization on the task identity for adaptation steps. In addition, PNMTA can also make use of the existing non-cold-start users for pretraining. Comprehensive experiments on two benchmark datasets demonstrate that our model can achieve significant and consistent improvements against other state-of-the-art methods.

Abstract We introduce and study knowledge drift (KD), a special form of concept drift that occurs in hierarchical classification. Under KD the vocabulary of concepts, their individual distributions, and the is-a relations between them can all change over time. The main challenge is that, since the ground-truth concept hierarchy is unobserved, it is hard to tell apart different forms of KD. For instance, the introduction of a new is-a relation between two concepts might be confused with changes to those individual concepts, but it is far from equivalent. Failure to identify the right kind of KD compromises the concept hierarchy used by the classifier, leading to systematic prediction errors. Our key observation is that in human-in-the-loop applications like smart personal assistants the user knows what kind of drift occurred recently, if any. Motivated by this observation, we introduce trckd, a novel approach that combines two automated stages—drift detection and adaptation—with a new interactive disambiguation stage in which the user is asked to refine the machine’s understanding of recently detected KD. In addition, trckd implements a simple but effective knowledge-aware adaptation strategy. Our simulations show that, when the structure of the concept hierarchy drifts, a handful of queries to the user are often enough to substantially improve prediction performance on both synthetic and realistic data.

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose adeepfeature-basedtextclustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms and the state-of-the-art pretrained language model, i.e., BERT, on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results.

This paper presents the Mongolian Wordnet (MOW), and a general methodology of how to construct it from various sources e.g.lexical resources and expert translations.As of today, the MOW contains 23,665 synsets, 26,875 words, 2,979 glosses, and 213 examples.The manual evaluation of the resource 1 estimated its quality at 96.4%.

WordNet represents polysemous terms by capturing the different meanings of these terms at the lexical level, but without giving emphasis on the polysemy types such terms belong to.The state of the art polysemy approaches identify several polysemy types in WordNet but they do not explain how to classify and organize them.In this paper, we present a novel approach for classifying the polysemy types which exploits taxonomic principles which in turn, allow us to discover a set of polysemy structural patterns.

Computer-enabled social services like tagging or sharing are ubiquitous in current web applications that are aimed to a group of users. These services do not only add value and new functionalities to their applications but also create a network of users and services that interconnect them to a wider on-line ecosystem. Currently these social networks mainly use the vast amount of user-created content, and activity logs to apply to provide recommendations and more complex services. This paper presents the Social Core a social network engine that implements semantic-based functionalities like semantic annotations, semantic search semantic-enhanced access control and user privacy protection. The Social Core was integrated as part of the SmartCampus mobile platform, which was tested by around one hundred students, and it is currently being further developed as part of European FP7 project SmartSociety.

The digital content of users is commonly organised in local directories representing entities from the real world (e.g., people, locations, organisations, and events). Different representations can show different "versions", using different names to refer to the same real world entity (e.g., George Lombardi, Lombardi G., Dr. Lombardi). Although the data in these directories are related and can even complement each other, there are no formal links connecting them and allowing users to share and search across them. In this work we propose a Distributed Directory System, applied to A Healthcare Use Case for Rural Areas that allows peers: (i) to maintain full control over their data; and (ii) to find different versions of an entity based on any name that is used in the network to refer to it. We evaluate the approach in networks of different sizes using PlanetLab and we show promising results in terms of scalability.

The world is extremely diverse and its diversity is obvious in the cultural differences and the large number of spoken languages being used all over the world. In this sense, we need to collect and organize a huge amount of knowledge obtained from multiple resources differing from one another in many aspects. A possible approach for doing that is to think of designing effective tools for construction and maintenance of linguistic resources based on well-defined knowledge representation methodologies capable of dealing with diversity and the continuous evolvement of human knowledge. In this paper, we present a linguistic resource management platform which allows for knowledge organization in a language-independent manner and provides the appropriate mapping from a language independent concept to one or more language specific lexicalization. The paper explains the knowledge representation methodology used in constructing the platform together with the iterative process followed in designing and implementing the first version of the platform, named UKC-1 and the updated refined version, named UKC-2.

This paper is based upon an approach for automatic detection of personal events in on-line personal photo collections and proposes a powerful exploitation of these events: We compose social events out of personal events and then automatically reveal interpersonal ties. Trying to tame the stream of big data in social networks we solely rely on image meta-data of time and space. We validate our assumptions in the wild using 1.8 million public images of more than 4100 users. The proposed approach has three main steps: (i) personal event detection using individual, unsorted photo collections, in which we make use of the spatio-temporal context embedded in digital photos to detect event boundaries within the collection; (ii) social event detection for which we use a tailored similarity measurement between personal events of different users; and (iii) an analysis of event co-participation to propagate social connections. Experiments validate that the fully automated approach is able to accurately detect 78.76% of social events and reconstruct the interpersonal ties of a user with a verified true positive rate of 45%. This rate is probably much higher: Since most interpersonal ties are undefined in the universe of social networks, our experimental ground-truth of course remains fragmentary.

We are addressing the problem of organizing and indexing one's personal media. Recent approaches of media indexing use events as media aggregators, but do not fully consider the context in which the media asset has been produced and do not take the personal perspective of the user into account. To this end, we propose a new paradigm for the automated indexing of social media based on the the notion of personal events. We reveal both personal habits of a user by analyzing the patterns of capturing images in space and time, while we also improve the understanding of photos over the years by learning the user's personal behavior. Our fully automatic and computationally inexpensive approach outperforms the state of the art in event-based media indexing. Moreover, we aim to push two main ideas to the problem: (1) We automatically assign the events to routine locations and non-routine locations. This gives the basic nature of events. (2) We hierarchically arrange events at non-routine locations until a routine location is reached again and the round trip is complete. This highly coincides with the given ground-truth at large scale experiments on Picasaweb. We provide experimental validation on a data-set crawled from Picasaweb which consists of about 42,000 photos taken by 5 users in a time period of 37 years, outperforming the state-of-the-art significantly.

By functional reasoning we mean the ability of integrating shape, function, and plans in reasoning. the shape of many man-made objects, such as tools, is expressly designed to provide precise functionalities. Moreover, humans know how to use the same objects for different functions. In vision and reasoning we make use of complex information which is not exclusively based on geometric and spatial knowledge, but also on functional elements. They seem to play a role in object recognition and representation. This article is an insight in functional reasoning from the computational point of view. It introduces its concepts and its apparent ubiquity in human behavior. Some relevant computational literature is reported and discussed. the rest of the article is an outline of the FUR project, an attempt to develop a computational model for functional reasoning. the development state of the project is presented along with the implementation of a first prototype. Some experimental results are finally given.