Towards Multi-view Graph Anomaly Detection with Similarity-Guided Contrastive Clustering

Anomaly detection on graphs plays an important role in many real-world applications. Usually, these data are composed of multiple types (e.g., user information and transaction records for financial data), thus exhibiting view heterogeneity. Therefore, it can be challenging to leverage such multi-view information and learn the graph's contextual information to identify rare anomalies. To tackle this problem, many deep learning-based methods utilize contrastive learning loss as a regularization term to learn good representations. However, many existing contrastive-based methods show that traditional contrastive learning losses fail to consider the semantic information (e.g., class membership information). In addition, we theoretically show that clustering-based contrastive learning also easily leads to a sub-optimal solution. To address these issues, in this paper, we proposed an autoencoder-based clustering framework regularized by a similarity-guided contrastive loss to detect anomalous nodes. Specifically, we build a similarity map to help the model learn robust representations without imposing a hard margin constraint between the positive and negative pairs. Theoretically, we show that the proposed similarity-guided loss is a variant of contrastive learning loss, and how it alleviates the issue of unreliable pseudo-labels with the connection to graph spectral clustering. Experimental results on several datasets demonstrate the effectiveness and efficiency of our proposed framework.

Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games

Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in stochastic games in the non-asymptotic regime. In particular, we establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general-sum stochastic games (SGs) - weakly acyclic SGs, which includes the common cooperative MARL setting with an identical reward to all agents (a Markov team problem) as a special case. We focus on the practical while challenging setting of fully decentralized MARL, where neither the rewards nor the actions of other agents can be observed by each agent. In fact, each agent is completely oblivious to the presence of other decision makers. Both the tabular and the linear function approximation cases have been considered. In the tabular setting, we analyze the sample complexity for the decentralized Q-learning algorithm to converge to a Markov perfect equilibrium (Nash equilibrium). With linear function approximation, the results are for convergence to a linear approximated equilibrium - a new notion of equilibrium that we propose - which describes that each agent's policy is a best reply (to other agents) within a linear space. Numerical experiments are also provided for both settings to demonstrate the results.