Large language models (LLMs) have recently advanced knowledge graph question answering (KGQA), but current methods tend to rely on LLM-induced type systems with inconsistent granularity, or perform multi-hop reasoning without explicit target-type constraints.We introduce OntGQA, a type-constrained KGQA framework that reasons over a relation-centric ontology graph, where each relation is labeled with its head and tail entity types to provide a stable schema backbone.Built on this graph, OntGQA adopts a planner-judge architecture with generative backoff: a type planner proposes plausible head-tail type pairs, a judge verifies retrieved candidates and their paths, and a generator is invoked only when all candidates are rejected.By constraining both endpoints of reasoning in type space, Ont-GQA achieves state-of-the-art performance and produces ontology-grounded reasoning chains, with substantial Hit@1 gains (87.7%→91.5% on WebQSP and 67.6%→74.6% on CWQ).

While large language models (LLMs) have shown remarkable capabilities in natural language processing, they struggle with complex, multi-step reasoning tasks involving knowledge graphs (KGs). Existing approaches that integrate LLMs and KGs either underutilize the reasoning abilities of LLMs or suffer from prohibitive computational costs due to tight coupling. To address these limitations, we propose a novel collaborative framework named EffiQA that can strike a balance between performance and efficiency via an iterative paradigm. EffiQA consists of three stages: global planning, efficient KG exploration, and self-reflection. Specifically, EffiQA leverages the commonsense capability of LLMs to explore potential reasoning pathways through global planning. Then, it offloads semantic pruning to a small plug-in model for efficient KG exploration. Finally, the exploration results are fed to LLMs for self-reflection to further improve global planning and efficient KG exploration. Empirical evidence on multiple KBQA benchmarks shows EffiQA’s effectiveness, achieving an optimal balance between reasoning accuracy and computational costs. We hope the proposed new framework will pave the way for efficient, knowledge-intensive querying by redefining the integration of LLMs and KGs, fostering future research on knowledge-based question answering.

The task of entity alignment (EA) seeks to identify corresponding entities across different knowledge graphs (KGs). However, in large-scale KG alignment tasks, the complexity of the problem renders traditional entity structure representation methods, designed for small-scale KGs, ineffective. Partition-based approaches address this challenge by breaking large KGs into smaller subgraphs, but this inevitably results in a loss of structural information. Although existing methods have sought to mitigate this issue, they have largely overlooked the interplay between partitioning and entity structure representation learning. To address this, we propose a Self-Partitioning Entity Alignment (SPEA) pipeline for large-scale EA, in which partitioning and entity structure representation learning are mutually optimized. Within this framework, we introduce the Inter-Subgraph Neighbor Interaction (ISNI) for enhanced entity structure representation, the Bidirectional Margin-based Confidence (BMC) for pseudo-pairing, the Seed-oriented Cross Graph Partitioner (SCGP) for dynamic repartitioning, and the Historical Confidence Ensembling (HCE) strategy for consistent training. Extensive experiments demonstrate that SPEA significantly outperforms existing methods for large-scale EA tasks.

Recently, it has been shown that for offline deep reinforcement learning (DRL), pre-training Decision Transformer with a large language corpus can improve downstream performance (Reid et al., 2022). A natural question to ask is whether this performance gain can only be achieved with language pre-training, or can be achieved with simpler pre-training schemes which do not involve language. In this paper, we first show that language is not essential for improved performance, and indeed pre-training with synthetic IID data for a small number of updates can match the performance gains from pre-training with a large language corpus; moreover, pre-training with data generated by a one-step Markov chain can further improve the performance. Inspired by these experimental results, we then consider pre-training Conservative Q-Learning (CQL), a popular offline DRL algorithm, which is Q-learning-based and typically employs a Multi-Layer Perceptron (MLP) backbone. Surprisingly, pre-training with simple synthetic data for a small number of updates can also improve CQL, providing consistent performance improvement on D4RL Gym locomotion datasets. The results of this paper not only illustrate the importance of pre-training for offline DRL but also show that the pre-training data can be synthetic and generated with remarkably simple mechanisms.

Temporal Knowledge Graph Completion (TKGC) aims to predict missing parts of quadruples, which is crucial for real-life knowledge graphs. Compared with methods that only use graph neural networks, the emergence of pre-trained model has introduced a trend of simultaneously leveraging text and graph structure information. However, most current methods based on pre-trained models struggle to effectively utilize both text and multi-hop graph structure information concurrently, resulting in insufficient association mining of relations. To address the challenge, we propose a novel model: Temporal Closing Path for Pre-trained Language Model-based TKGC (TCP-PLM). We obtain the temporal closing relation path of the target relation through sampling, and use the relation path as a bridge to simultaneously utilize text and multi-hop graph structure information. Moreover, the relation path serves as a tool for mining associations between relations. At the same time, due to the design of entity-independent relation paths, our model can also handle the inductive setting. Our experiments on three benchmarks, along with extensive analysis, demonstrate that our model not only achieves substantial performance enhancements across four metrics compared to other models but also adeptly handles inductive settings.

Nowadays, protecting user privacy on the Internet is paramount, especially with the increasing use of the Tor network to anonymize online activities. However, Tor is vulnerable to website fingerprinting (WF), where patterns in encrypted traffic are analyzed to infer visited websites. It can be utilized to monitor and investigate illegal activities on the dark web. Existing website fingerprinting techniques typically assume single-tab browsing, which is unrealistic as users often open multiple tabs consecutively or within a short period due to Tor’s slow loading speeds and typical user habits. Moreover, current multi-tab approaches face challenges in classification speed, which is crucial for high-throughput networks. FingerMamba, our proposed model, addresses these gaps by efficiently extracting local information and establishing long-range dependencies using a Mamba-based structured state-space model. It significantly enhances the accuracy and speed of multi-tab website fingerprinting. Extensive experiments on the largest real-world multi-tab dataset demonstrate that FingerMamba effectively improves classification accuracy in both closed-world and open-world settings. Furthermore, with maintaining similar accuracy performance, FingerMamba can increase inference speed by up to four times compared to the existing methods. To our knowledge, FingerMamba is the first model to tailor the Mamba architecture for website fingerprinting.

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other applications, exhibits Neural Regression Collapse (NRC), a new form of neural collapse: (NRC1) The last-layer feature vectors collapse to the subspace spanned by the $n$ principal components of the feature vectors, where $n$ is the dimension of the targets (for univariate regression, $n=1$); (NRC2) The last-layer feature vectors also collapse to the subspace spanned by the last-layer weight vectors; (NRC3) The Gram matrix for the weight vectors converges to a specific functional form that depends on the covariance matrix of the targets. After empirically establishing the prevalence of (NRC1)-(NRC3) for a variety of datasets and network architectures, we provide an explanation of these phenomena by modeling the regression task in the context of the Unconstrained Feature Model (UFM), in which the last layer feature vectors are treated as free variables when minimizing the loss function. We show that when the regularization parameters in the UFM model are strictly positive, then (NRC1)-(NRC3) also emerge as solutions in the UFM optimization problem. We also show that if the regularization parameters are equal to zero, then there is no collapse. To our knowledge, this is the first empirical and theoretical study of neural collapse in the context of regression. This extension is significant not only because it broadens the applicability of neural collapse to a new category of problems but also because it suggests that the phenomena of neural collapse could be a universal behavior in deep learning.