Graph few-shot learning is of great importance among various graph learning tasks. Under thefew-shot scenario, models areoftenrequired toconduct classification givenlimited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i.e., the graph that the meta-task is sampled from) to learn node representations.

The support nodes are either positive or negative. For the transformation function, we stack multiple computation blocks as shown in Figure 1. The stacking mechanism helps the function capture comprehensive relationships between nodes such that the performance is boosted. In each computation block, there are mainly two modules. The detailed architecture of the self-attention module is illustrated in Figure 1.

Additionally, we introduce an embedding transformation function that remedies the deficiency of the straightforward use of meta-learning.

Multi-agent pathfinding (MAPF) traditionally focuses on collision avoidance, but many real-world applications require active coordination between agents to improve team performance. This paper introduces Team Coordination on Graphs with Risky Edges (TCGRE), where agents collaborate to reduce traversal costs on high-risk edges via support from teammates. We reformulate TCGRE as a 3D matching problem-mapping robot pairs, support pairs, and time steps-and rigorously prove its NP-hardness via reduction from Minimum 3D Matching. To address this complexity, (in the conference version) we proposed efficient decomposition methods, reducing the problem to tractable subproblems: Joint-State Graph (JSG): Encodes coordination as a single-agent shortest-path problem. Coordination-Exhaustive Search (CES): Optimizes support assignments via exhaustive pairing. Receding-Horizon Optimistic Cooperative A* (RHOCA*): Balances optimality and scalability via horizon-limited planning. Further in this extension, we introduce a dynamic graph construction method (Dynamic-HJSG), leveraging agent homogeneity to prune redundant states and reduce computational overhead by constructing the joint-state graph dynamically. Theoretical analysis shows Dynamic-HJSG preserves optimality while lowering complexity from exponential to polynomial in key cases. Empirical results validate scalability for large teams and graphs, with HJSG outperforming baselines greatly in runtime in different sizes and types of graphs. This work bridges combinatorial optimization and multi-agent planning, offering a principled framework for collaborative pathfinding with provable guarantees, and the key idea of the solution can be widely extended to many other collaborative optimization problems, such as MAPF.

Under the few-shot scenario, models are often required to conduct classification given limited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i.e., the graph that the meta-task is sampled from) to learn node

The support nodes are either positive or negative. For the transformation function, we stack multiple computation blocks as shown in Figure 1. The stacking mechanism helps the function capture comprehensive relationships between nodes such that the performance is boosted. In each computation block, there are mainly two modules. The detailed architecture of the self-attention module is illustrated in Figure 1.

Corporate fraud detection aims to automatically recognize companies that conduct wrongful activities such as fraudulent financial statements or illegal insider trading. Previous learning-based methods fail to e ffectively integrate rich interactions in the company network. To close this gap, we collect 18-year financial records in China to form three graph datasets with fraud labels. We analyze the characteristics of the financial graphs, highlighting two pronounced issues: (1) information overload: the dominance of (noisy) non-company nodes over company nodes hinders the message-passing process in Graph Convolution Networks (GCN); and (2) hidden fraud: there exists a large percentage of possible undetected violations in the collected data. The hidden fraud problem will introduce noisy labels in the training dataset and compromise fraud detection results. The proposed model adopts a two-stage learning method to enhance robustness against hidden frauds. Introduction Corporate fraud refers to illegal schemes by listed companies in the stock market, aiming at financial gains through di ff erent means such as fraudulent financial statements and illegal insider trading. This kind of fraud bears systematic risks, which can potentially lead to financial crises at the macro level [1]. Unfortunately, the rapid growth of young capital markets has given rise to an increasing number of fraudulent cases in recent years, putting pressure on regulators and auditors. Since the traditional human supervision solution is no longer effi cient, it is desirable to build an autonomous system to assist regulators in this essential task. These machine-learning models are built to classify annual financial statements as fraudulent or not, based on expert-chosen feature sets. Unfortunately, the rich interactions in the company network have not been e ffec-tively integrated for corporate fraud detection. Financial experts, on the other hand, have recognized the influence of "Directors / Supervisors / Executives (DSE)" and "Related Party Transactions (RPT)" on corporate fraud (see Figure 1). DSE refers to the members of the director board of the company. Being the decision-making body in a company, the director board is certainly the agent behind most corporate frauds [6]. Connection via DSE also helps companies lower the coordination cost for illegal activities, thus significantly increasing the likelihood of committing fraud [7]. RPT refers to deals or arrangements between two companies that are joined by a previous business association or share common interests. RPTs, particularly those that go unchecked, carry the risk of financial fraud by various means such as illegal profit transmission [8, 9].

Team Coordination on Graphs with Risky Edges (TCGRE) is a recently emerged problem, in which a robot team collectively reduces graph traversal cost through support from one robot to another when the latter traverses a risky edge. Resembling the traditional Multi-Agent Path Finding (MAPF) problem, both classical and learning-based methods have been proposed to solve TCGRE, however, they lacked either computation efficiency or optimality assurance. In this paper, we reformulate TCGRE as a constrained optimization and perform rigorous mathematical analysis. Our theoretical analysis shows the NP-hardness of TCGRE by reduction from the Maximum 3D Matching problem and that efficient decomposition is a key to tackle this combinatorial optimization problem. Further more, we design three classes of algorithms to solve TCGRE, i.e., Joint State Graph (JSG) based, coordination based, and receding-horizon sub-team based solutions. Each of these proposed algorithms enjoy different provable optimality and efficiency characteristics that are demonstrated in our extensive experiments.