Multi-domain aspect-based sentiment analysis (ABSA) seeks to capture fine-grained sentiment across diverse domains. While existing research narrowly focuses on single-domain applications constrained by methodological limitations and data scarcity, the reality is that sentiment naturally traverses multiple domains. Although large language models (LLMs) offer a promising solution for ABSA, it is difficult to integrate effectively with established techniques, including graph-based models and linguistics, because modifying their internal architecture is not easy. To alleviate this problem, we propose a novel framework, Feature-aware In-context Learning for Multi-domain ABSA (FaiMA). The core insight of FaiMA is to utilize in-context learning (ICL) as a feature-aware mechanism that facilitates adaptive learning in multi-domain ABSA tasks. Specifically, we employ a multi-head graph attention network as a text encoder optimized by heuristic rules for linguistic, domain, and sentiment features. Through contrastive learning, we optimize sentence representations by focusing on these diverse features. Additionally, we construct an efficient indexing mechanism, allowing FaiMA to stably retrieve highly relevant examples across multiple dimensions for any given input. To evaluate the efficacy of FaiMA, we build the first multi-domain ABSA benchmark dataset. Extensive experimental results demonstrate that FaiMA achieves significant performance improvements in multiple domains compared to baselines, increasing F1 by 2.07% on average. Source code and data sets are anonymously available at https://github.com/SupritYoung/FaiMA.

Efficient exploration is important for reinforcement learners to achieve high rewards. In multi-agent systems, coordinated exploration and behaviour is critical for agents to jointly achieve optimal outcomes. In this paper, we introduce a new general framework for improving coordination and performance of multi-agent reinforcement learners (MARL). Our framework, named Learnable Intrinsic-Reward Generation Selection algorithm (LIGS) introduces an adaptive learner, Generator that observes the agents and learns to construct intrinsic rewards online that coordinate the agents' joint exploration and joint behaviour. Using a novel combination of MARL and switching controls, LIGS determines the best states to learn to add intrinsic rewards which leads to a highly efficient learning process. LIGS can subdivide complex tasks making them easier to solve and enables systems of MARL agents to quickly solve environments with sparse rewards. LIGS can seamlessly adopt existing MARL algorithms and, our theory shows that it ensures convergence to policies that deliver higher system performance. We demonstrate its superior performance in challenging tasks in Foraging and StarCraft II.

Our approach uses unsupervised machine learning techniques to generate new formulas by mimicking the structural properties of a given input formula Phi. We proceed in two phases: first, we construct the Literal-Incidence Graph (LIG) of Phi. This is used by a Generative Adversarial Network (GAN) to generate new LIGs that exhibit graph-theoretic properties similar to those of the LIG of Phi. In the second phase, we extract a formula whose LIG would correspond to the generated graph. We show that generating such a formula is equivalent to finding a minimal clique edge cover of the given graph, which we tackle efficiently using a greedy hill-climbing algorithm. We verify experimentally that our approach generates formulas that closely resemble a given real-world SAT instance, as measured by a range of different metrics.

The aim of measuring inconsistency is to obtain an evaluation of the imperfections in a set of formulas, and this evaluation may then be used to help decide on some course of action (such as rejecting some of the formulas, resolving the inconsistency, seeking better sources of information, etc). A number of proposals have been made to define measures of inconsistency. Each has its rationale. But to date, it is not clear how to delineate the space of options for measures, nor is it clear how we can classify measures systematically. To address these problems, we introduce a general framework for comparing syntactic measures of inconsistency. It is based on the notion of an inconsistency graph for each knowledgebase (a bipartite graph with a set of vertices representing formulas in the knowledgebase, a set of vertices representing minimal inconsistent subsets of the knowledgebase, and edges representing that a formula belongs to a minimal inconsistent subset). We then show that various measures can be computed using the inconsistency graph. Then we introduce abstractions of the inconsistency graph and use them to construct a hierarchy of syntactic inconsistency measures. Furthermore, we extend the inconsistency graph concept with a labeling that extends the hierarchy to include some other types of inconsistency measures.

In this paper, we present Satgen, the first implicit generative model of real-world Boolean Satisfiability (SAT) formulas. Our approach uses unsupervised machine learning techniques to generate new formulas by mimicking the structural properties of a given input formula Phi. We proceed in two phases: first, we construct the Literal-Incidence Graph (LIG) of Phi. This is used by a Generative Adversarial Network (GAN) to generate new LIGs that exhibit graph-theoretic properties similar to those of the LIG of Phi. In the second phase, we extract a formula whose LIG would correspond to the generated graph. We show that generating such a formula is equivalent to finding a minimal clique edge cover of the given graph, which we tackle efficiently using a greedy hill-climbing algorithm. We verify experimentally that our approach generates formulas that closely resemble a given real-world SAT instance, as measured by a range of different metrics.