Recent advancements in test-time adaptation (TTA) offer promising solutions for mitigating performance degradation caused by distribution shifts. However, they may fall short in practical deployment of GNNs during test time, due to the significant reliance on impractical retraining or modifications to online GNN models. To address such challenges, in this work, we propose a novel method, i.e., Test-Time Graph REBirth, dubbed TT-GREB, to effectively generalize the well-trained GNN models to the test-time graphs under distribution shifts by directly manipulating the test graph data. Concretely, we develop an overall framework designed by two principles for obtaining newly reborn test graphs, corresponding to two sub-modules: (1) prototype extractor for re-extracting the environment-invariant features of the test-time graph; and (2) environment refiner for re-fining the environment-varying features to explore the potential shifts. Furthermore, we propose a dual test-time graph contrastive learning objective with an effective iterative optimization strategy to obtain optimal prototype components and environmental components of the test graph. Extensive experiments on real-world graphs under diverse test-time distribution shifts verify the effectiveness of our proposed method, showcasing its superior ability to manipulate test-time graphs for better GNN generalization ability.

Information Retrieval (IR) constitutes a vital facet of Open Domain Question Answering (ODQA) systems, focusing on the exploration of pertinent information within extensive collections of passages, such as Wikipedia, to facilitate subsequent reader processing. Historically, IR relied on textual overlaps for relevant context retrieval, employing methods like BM25 and TF-IDF, which, however, lacked natural language understanding. The advent of deep learning ushered in a new era, leading to the introduction of Dense Passage Retrievers (DPR), shows superiority over traditional sparse retrievers. These dense retrievers leverage Pre-Trained Language Models (PLMs) to initialize context encoders, enabling the extraction of natural language representations. They utilize the distance between latent vectors of contexts as a metric for assessing similarity. However, DPR methods are heavily reliant on large volumes of meticulously labeled data, such as Natural Questions. The process of data labeling is both costly and time-intensive. In this article, we propose a novel data augmentation methodology Self Data Augmentation (SDA) that employs DPR models to automatically annotate unanswered questions. Specifically, we initiate the process by retrieving relevant pseudo passages for these unlabeled questions. We subsequently introduce three distinct passage selection methods to annotate these pseudo passages. Ultimately, we amalgamate the pseudo-labeled passages with the unanswered questions to create augmented data. Our experimental evaluations conducted on two extensive datasets (Natural Questions and TriviaQA), alongside a relatively small dataset (WebQuestions), utilizing three diverse base models, illustrate the significant enhancement achieved through the incorporation of freshly augmented data. Moreover, our proposed data augmentation method exhibits remarkable flexibility, which is readily adaptable to various dense retrievers. Additionally, we have conducted a comprehensive human study on the augmented data, which further supports our conclusions.

The surge in merchant fraud poses a significant threat to market order and consumer security. Effective security monitoring for merchants is crucial in safeguarding the digital life ecosystem and users' financial well-being. Detecting daily fraudulent payment transactions, a challenging task for current methods, requires efficient transformation of transactions into embeddings, especially in representing merchants based on their behavioral transactions. To address this, we propose the Grouping Sampling-based Sequence Generation (GSSG) method to generate meaningful sequences, enabling interactions among correlated transactions. We introduce Hierarchical Embedding Learning (HEL) and Hierarchical Masking pre-training (HMP) for the effective representation of hierarchical structures within flat transaction sequences. Pretrained on WeChat Pay data, our model, PTP, demonstrates superior performance in downstream fraud transaction detection, especially in few-shot learning scenarios, showcasing great potential in payment transaction scenarios.

Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world applications. To date, automated heterophilic graph learning with NAS is still a research blank to be filled in. Due to the complexity and variety of heterophilic graphs, the critical challenge of heterophilic graph NAS mainly lies in developing the heterophily-specific search space and strategy. Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities. Specifically, Auto-HeG incorporates heterophily into all stages of automatic heterophilic graph learning, including search space design, supernet training, and architecture selection. Through the diverse message-passing scheme with joint micro-level and macro-level designs, we first build a comprehensive heterophilic GNN search space, enabling Auto-HeG to integrate complex and various heterophily of graphs. With a progressive supernet training strategy, we dynamically shrink the initial search space according to layer-wise variation of heterophily, resulting in a compact and efficient supernet. Taking a heterophily-aware distance criterion as the guidance, we conduct heterophilic architecture selection in the leave-one-out pattern, so that specialized and expressive heterophilic GNN architectures can be derived. Extensive experiments illustrate the superiority of Auto-HeG in developing excellent heterophilic GNNs to human-designed models and graph NAS models.

Structured sequences are a popular data representation, used to model complex data such as traffic networks. A key machine learning task for structured sequences is node classification, that is predicting the class labels of unlabeled nodes. Though many node classification models were proposed, they assume a closed world setting, that all class labels appear in the training data. But in the real-world, the presence of never-before-seen class labels in testing data can considerably degrade a classifier’s accuracy. A promising solution to this issue is to build classifiers for an open-world setting, where samples with unknown class labels are continuously observed such that training and testing data may have different class label spaces. Several approaches have been proposed for open-world learning problems in computer vision and natural language processing, but they cannot be applied directly to structured sequences due to the complexity of their non-Euclidean properties and their dynamic nature. This paper addresses this important research gap by proposing a novel Open-world Structured Sequence node Classification (OSSC) model, to learn from structured sequences in an open-world setting. OSSC captures the structural and temporal information via a GCN-based dynamic variational framework. A latent distribution sequence is learned for each node using both stochastic states and deterministic states, to capture the evolution of node attributes and topology, followed by a sampling process to generate node representations. An open-world classification loss is further adopted to ensure that node representations are sensitive to unknown classes. And a combination of Openmax and Softmax is utilized to recognize nodes from unknown classes and to classify others to one of the known classes. Experiments on real-world datasets show that the proposed OSSC method is capable of learning accurate open-world node classifiers from structured sequence data.

Hashing technology has been widely used in image retrieval due to its computational and storage efficiency. Recently, deep unsupervised hashing methods have attracted increasing attention due to the high cost of human annotations in the real world and the superiority of deep learning technology. However, most deep unsupervised hashing methods usually pre-compute a similarity matrix to model the pairwise relationship in the pre-trained feature space. Then this similarity matrix would be used to guide hash learning, in which most of the data pairs are treated equivalently. The above process is confronted with the following defects:1) The pre-computed similarity matrix is inalterable and disconnected from the hash learning process, which cannot explore the underlying semantic information. 2) The informative data pairs may be buried by the large number of less-informative data pairs. To solve the aforementioned problems, we propose a Deep Self-Adaptive Hashing(DSAH) model to adaptively capture the semantic information with two special designs: Adaptive Neighbor Discovery(AND) and Pairwise Information Content(PIC). Firstly, we adopt the AND to initially construct a neighborhood-based similarity matrix, and then refine this initial similarity matrix with a novel update strategy to further investigate the semantic structure behind the learned representation. Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning. Extensive experiments on several datasets demonstrate that the above two technologies facilitate the deep hashing model to achieve superior performance.

Identifying influencers on social media, such as Twitter, has played a central role in many applications, including online marketing and political campaigns. Compared with social media celebrities, domain-specific influencers are less expensive to hire and more engaged in spreading messages such as new treatment or timely prevention for HIV. However, most of the existing topic modeling based approaches fail to identify influencers who are dedicated to the rare yet important topics such as HIV and suicide. To alleviate this limitation, we investigate an on-Demand Influencer Discovery (DID) framework that is able to identify influencers on any subject depicted by a few user-specified keywords, regardless of its popularity on social media. The DID model employs an iterative learning process that integrates the language attention network as a subject filter and the influence convolution network built on user interactions. Comprehensive evaluations on Twitter datasets show that the DID model can reliably identify influencers even on rare subjects such as HIV and suicide, outperforming existing topic-specific influencer detection models.

Social recommendation explores social information to improve the quality of a recommender system. It can be further divided into explicit and implicit social network recommendation. The former assumes the existence of explicit social connections between users in addition to the rating data. The latter one assumes the availability of only the ratings but not the social connections between users since the explicit social information data may not necessarily be available and usually are binary decision values (e.g., whether two people are friends), while the strength of their relationships is missing. Most of the works in this field use only rating data to infer the latent social networks. They ignore the dynamic nature of users that the preferences of users drift over time distinctly. To this end, we propose a new Implicit Dynamic Social Recommendation (IDSR) model, which infers latent social network from cascade data. It can sufficiently mine the information contained in time by mining the cascade data and identify the dynamic changes in the users in time by using the latest updated social network to make recommendations. Experiments and comparisons on three real-world datasets show that the proposed model outperforms the state-of-the-art solutions in both explicit and implicit scenarios.

In this paper, we study a new problem of continuous learning from doubly-streaming data where both data volume and feature space increase over time. We refer to the doubly-streaming data as trapezoidal data streams and the corresponding learning problem as online learning from trapezoidal data streams. The problem is challenging because both data volume and data dimension increase over time, and existing online learning[1],[2], online feature selection[3], and streaming feature selection algorithms[4],[5]are inapplicable. We propose a new Online Learning with Streaming Features algorithm (OL$_{SF}$for short) and its two variants, which combine online learning[1],[2]and streaming feature selection[4],[5]to enable learning from trapezoidal data streams with infinite training instances and features. When a new training instance carrying new features arrives, a classifier updates the existing features by following the passive-aggressive update rule[2]and updates the new features by following the structural risk minimization principle. Feature sparsity is then introduced by using the projected truncation technique. We derive performance bounds of the OL$_{SF}$algorithm and its variants. We also conduct experiments on real-world data sets to show the performance of the proposed algorithms.

We study a new problem of learning from doubly-streaming data where both data volume and feature space increase over time. We refer to the problem as mining trapezoidal data streams. The problem is challenging because both data volume and feature space are increasing, to which existing online learning, online feature selection and streaming feature selection algorithms are inapplicable. We propose a new Sparse Trapezoidal Streaming Data mining algorithm (STSD) and its two variants which combine online learning and online feature selection to enable learning trapezoidal data streams with infinite training instances and features. Specifically, when new training instances carrying new features arrive, the classifier updates the existing features by following the passive-aggressive update rule used in online learning and updates the new features with the structural risk minimization principle. Feature sparsity is also introduced using the projected truncation techniques. Extensive experiments on the demonstrated UCI data sets show the performance of the proposed algorithms.