Machine learning and deep learning have demonstrated remarkable success across a wide range of time series tasks. However, their lack of transparency limits explainability and trust. To address this challenge, numerous explanation methods have been proposed in recent years, each of them providing distinct perspectives on how to interpret time series models through signals, patterns, structures, or semantics. This survey synthesizes these perspectives into a unified cognitive hierarchy that bridges methodological diversity with human understanding. Existing approaches are classified into four levels: signal-space, pattern-space, structural, and semantic, reflecting a progressive shift from low-level signal attribution to high-level semantic reasoning. Building on this taxonomy, we conduct comprehensive literature review, revealing cross-level connections, emerging trends, and critical gaps in current research. Our analysis underscores the growing importance of semantic explanations, particularly those facilitated by large language models (LLMs), as a promising direction for achieving human-centered and readable explainability. In addition, we compile and categorize data benchmarks used for explaining diverse time series tasks and provide an accompanying open repository to support continued research in this field.

Graph Neural Networks (GNNs) are essential for processing graph-structured data and have wide applications in critical domains. The increasing use of GNNs in high-stakes scenarios requires robust explainability to ensure trust and transparency in decision-making. A common approach to explaining GNNs is to identify subgraphs, a.k.a. explanations, that significantly influence model predictions. However, this task is challenging due to the distribution shifts from the original training graphs to the explanation subgraphs, a factor that is largely overlooked in the existing research. These shifts arise because GNNs are trained on original graphs, while explanation subgraphs often differ in properties such as the number of nodes or structural patterns. As a result, GNNs may struggle to generalize to explanation subgraphs with a different distribution from its training data. In this paper, we systematically investigate the Out-Of-Distribution (OOD) problem through theoretical analysis and empirical studies. To address this challenge, we first develop a theoretical framework that formalizes the notion of explanation subgraphs through sufficiency and minimality criteria, ensuring both prediction preservation and structural compactness. Our analysis reveals a fundamental distributional disparity between explanation subgraphs and original graphs, leading to a novel concept of proxy graphs proposed in this work. Proxy graphs maintain the essential explanatory information while conforming to the original data distribution through a combination of parametric and non-parametric optimization approaches. Empirical evaluations on diverse datasets show that our method improves the quality and reliability of GNN explanations, advancing the field of GNN explainability.

Large language models acquire substantial factual and procedural knowledge when trained on large datasets. A growing body of work is concerned with understanding, modifying, and auditing this knowledge. Many of these works explore the localization of knowledge: whether a fact, skill, or competence associated with a task is localized in a small set of parameters within the model or distributed across them. There is a mixed perspective regarding the state of the art. Some studies identify compact representational or causal localization of facts, including mid-layer feed-forward modules and knowledge neurons, while others show that restricting the parameter updates allows one to change factual associations. Causal tracing scores can fail to accurately locate the best edit site, and superposition can make individual neurons polysemantic, so localization does not have to align with any isolated units. We believe that part of this disagreement is definitional. The question ``Is knowledge localized?'' conflates three distinct properties. Representational localization is whether knowledge can be retrieved from a restricted number of representational units; causal localization is whether interventions on a restricted set of units will affect the behavior; and editable localization is whether a restricted region of the model's native parameters can be changed to affect the knowledge. In this survey, we aim to disambiguate the existing works based on the kind of evidence they actually present and show that the evidence available is uneven in its distribution across the three pairwise relations. We also provide a measurement checklist for describing a localization claim in terms of the notion, units, representation system, and measurement procedure, along with a research program toward a cohesive, representation-inclusive account of the localization of knowledge.