Recent advancements in proactive dialogues have garnered significant attention, particularly for more complex objectives (e.g. emotion support and persuasion). Unlike traditional task-oriented dialogues, proactive dialogues demand advanced policy planning and adaptability, requiring rich scenarios and comprehensive policy repositories to develop such systems. However, existing approaches tend to rely on Large Language Models (LLMs) for user simulation and online learning, leading to biases that diverge from realistic scenarios and result in suboptimal efficiency. Moreover, these methods depend on manually defined, context-independent, coarse-grained policies, which not only incur high expert costs but also raise concerns regarding their completeness. In our work, we highlight the potential for automatically discovering policies directly from raw, real-world dialogue records. To this end, we introduce a novel dialogue policy planning framework, LDPP. It fully automates the process from mining policies in dialogue records to learning policy planning. Specifically, we employ a variant of the Variational Autoencoder to discover fine-grained policies represented as latent vectors. After automatically annotating the data with these latent policy labels, we propose an Offline Hierarchical Reinforcement Learning (RL) algorithm in the latent space to develop effective policy planning capabilities. Our experiments demonstrate that LDPP outperforms existing methods on two proactive scenarios, even surpassing ChatGPT with only a 1.8-billion-parameter LLM.

Small objects, due to their limited pixel size, are highly susceptible to background noise, leading to the loss of critical details during feature extraction. Some existing Transformer-based detectors rely on encoders to capture global contextual information for small object detection in complex environments. However, due to interference from intricate backgrounds, attention-based encoders often learn redundant or irrelevant features, which degrade detection performance. To overcome this challenge, we introduce SODMAMBA-DETR, which incorporates a SODMAMBA encoder equipped with a selective learning mechanism to effectively focus on critical information. By integrating a Multi-scale Feature Fusion Neck and a MFFAW module, our framework efficiently captures local details and fuses features across multiple scales. Experimental results on VisDrone and AI-TOD datasets demonstrate that our framework significantly outperforms existing Transformer and CNN-based detectors, particularly in complex scenarios.

Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box nature hinders their applications due to fairness, explainability, and compliance consideration. Rule-based systems are considered reliable in these sensitive scenarios. However, building a rule system is labor-intensive. Experts need to find informative statistics from user behavior sequences, design rules based on statistics and assign weights to each rule. In this paper, we bridge the gap between effective but black-box models and transparent rule models. We propose a two-stage framework, CauseRuDi, that distills the knowledge of black-box teacher models into rule-based student models. We design a Monte Carlo tree search-based statistics generation method that maximizes the correlation or dependence between the generated statistics and the teacher model's outputs. We formulate a sequential move game and a simultaneous move coalitional game to generate multiple statistics. Then statistics are composed into logical rules with our proposed neural logical networks by mimicking the outputs of teacher models. We evaluate CauseRuDi on three real-world public datasets and an industrial dataset to demonstrate its effectiveness.

Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph modeling methods have achieved satisfactory results, they still suffer from three key limitations, hindering their scalability and further applicability. i) Indiscriminate updating. For incoming edges, existing methods would indiscriminately deal with them, which may lead to more time consumption and unexpected noisy information. ii) Ineffective node-wise long-term modeling. They heavily rely on recurrent neural networks (RNNs) as a backbone, which has been demonstrated to be incapable of fully capturing node-wise long-term dependencies in event sequences. iii) Neglect of re-occurrence patterns. Dynamic graphs involve the repeated occurrence of neighbors that indicates their importance, which is disappointedly neglected by existing methods.

Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain diverse and intricate noise. Noise can significantly degrade the quality of representation generation, impeding the effectiveness of TGNs in downstream tasks. Though structure learning is widely applied to mitigate noise in static graphs, its adaptation to dynamic graph settings poses two significant challenges. i) Noise dynamics. Existing structure learning methods are ill-equipped to address the temporal aspect of noise, hampering their effectiveness in such dynamic and ever-changing noise patterns. ii) More severe noise. Noise may be introduced along with multiple interactions between two nodes, leading to the re-pollution of these nodes and consequently causing more severe noise compared to static graphs.

Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic node embeddings that vary over time, researchers have proposed a series of temporal graph neural networks for TIGs. However, due to the entangled temporal and structural dependencies, existing methods have to process the sequence of events chronologically and consecutively to ensure node representations are up-to-date. This prevents existing models from parallelization and reduces their flexibility in industrial applications. To tackle the above challenge, in this paper, we propose TIGER, a TIG embedding model that can restart at any timestamp. We introduce a restarter module that generates surrogate representations acting as the warm initialization of node representations. By restarting from multiple timestamps simultaneously, we divide the sequence into multiple chunks and naturally enable the parallelization of the model. Moreover, in contrast to previous models that utilize a single memory unit, we introduce a dual memory module to better exploit neighborhood information and alleviate the staleness problem. Extensive experiments on four public datasets and one industrial dataset are conducted, and the results verify both the effectiveness and the efficiency of our work.

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to financial inclusion. It brings non-trivial social benefits of diminishing financial inequality. However, the technical challenges in individual financial risk evaluation exacerbated by the unforeseen user characteristic distribution and limited credit history of new users, as well as the inexperience of newly-entered companies in handling complex data and obtaining accurate labels, impede further promotion of financial inclusion. To tackle these challenges, this paper develops a novel transfer learning algorithm (i.e., TransBoost) that combines the merits of tree-based models and kernel methods. The TransBoost is designed with a parallel tree structure and efficient weights updating mechanism with theoretical guarantee, which enables it to excel in tackling real-world data with high dimensional features and sparsity in O(n) time complexity. We conduct extensive experiments on two public datasets and a unique largescale dataset from Tencent Mobile Payment. The results show that the TransBoost outperforms other state-of-the- art benchmark transfer learning algorithms in terms of prediction accuracy with superior efficiency, demonstrate stronger robustness to data sparsity, and provide meaningful model interpretation. Besides, given a financial risk level, the TransBoost enables financial service providers to serve the largest number of users including those who would otherwise be excluded by other algorithms. That is, the TransBoost improves financial inclusion.

Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with sophisticated designs have achieved promising results, the black-box nature hinders their applications due to fairness, explainability, and compliance consideration. Rule-based systems are considered reliable in these sensitive scenarios. However, building a rule system is labor-intensive. Experts need to find informative statistics from user behavior sequences, design rules based on statistics and assign weights to each rule. In this paper, we bridge the gap between effective but black-box models and transparent rule models. We propose a two-stage method, RuDi, that distills the knowledge of black-box teacher models into rule-based student models. We design a Monte Carlo tree search-based statistics generation method that can provide a set of informative statistics in the first stage. Then statistics are composed into logical rules with our proposed neural logical networks by mimicking the outputs of teacher models. We evaluate RuDi on three real-world public datasets and an industrial dataset to demonstrate its effectiveness.

Community detection refers to the task of discovering closely related subgraphs to understand the networks. However, traditional community detection algorithms fail to pinpoint a particular kind of community. This limits its applicability in real-world networks, e.g., distinguishing fraud groups from normal ones in transaction networks. Recently, semi-supervised community detection emerges as a solution. It aims to seek other similar communities in the network with few labeled communities as training data. Existing works can be regarded as seed-based: locate seed nodes and then develop communities around seeds. However, these methods are quite sensitive to the quality of selected seeds since communities generated around a mis-detected seed may be irrelevant. Besides, they have individual issues, e.g., inflexibility and high computational overhead. To address these issues, we propose CLARE, which consists of two key components, Community Locator and Community Rewriter. Our idea is that we can locate potential communities and then refine them. Therefore, the community locator is proposed for quickly locating potential communities by seeking subgraphs that are similar to training ones in the network. To further adjust these located communities, we devise the community rewriter. Enhanced by deep reinforcement learning, it suggests intelligent decisions, such as adding or dropping nodes, to refine community structures flexibly. Extensive experiments verify both the effectiveness and efficiency of our work compared with prior state-of-the-art approaches on multiple real-world datasets.

Fraudulent cash-out is an increasingly serious problem in China, which costs financial facilities billions of dollars. Unlike most of the well-studied credit card fraud, where only one party illicitly seeks financial gain, fraudulent cash-out involves both parties of the transaction. When prior information, such as credit score and reputation score, about the majority of consumers and shops is available, the phenomenon can be readily analyzed by using the Markov random field models. In this paper, we investigate the detection of fraudulent cash-out under the circumstance where no prior information but only the labels of a small set of consumers and shops are available. The novelty of this work is building a semi-supervised learning algorithm that automatically tunes the prior and parameters in Markov random field while inferring labels for every node in the graph. We evaluate our algorithm with data from JD Finance.