This paper presents two complementary enhancements to the Very Fast Decision Tree algorithm for data stream mining. The first contribution introduces the fractional Hoeffding bound, a relaxed splitting criterion where the original threshold is scaled by a factor . Experimental evidence shows that for this modification, the resulting trees not only grow faster but also achieve higher accuracy compared to the original Very Fast Decision tree. The second contribution proposes a novel data structure, called extended statistics, which extends the traditional sufficient statistics used in the Very Fast Decision Tree by maintaining additional information about attribute co-occurrences. This allows child nodes to inherit richer knowledge from their parent, leading to deeper trees with accelerated convergence to the target accuracy. Numerical experiments on synthetic data streams demonstrate that the combination of fractional bounds and multi-index statistics yields significant accuracy gains, particularly in the early phases of learning. The extended statistics improvement, however, comes at the cost of increased memory and computational requirements, emphasizing the trade-off between predictive performance and resource usage.

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing this issue. Nevertheless, traditional capsule networks often underperform due to their shallow structures, and deeper variants lack hierarchical architectures, thereby compromising interpretability. This paper introduces a novel capsule network, ParseCaps, which utilizes the sparse axial attention routing and parse convolutional capsule layer to form a parse-tree-like structure, enhancing both depth and interpretability. Firstly, sparse axial attention routing optimizes connections between child and parent capsules, as well as emphasizes the weight distribution across instantiation parameters of parent capsules. Secondly, the parse convolutional capsule layer generates capsule predictions aligning with the parse tree. Finally, based on the loss design that is effective whether concept ground truth exists or not, ParseCaps advances interpretability by associating each dimension of the global capsule with a comprehensible concept, thereby facilitating clinician trust and understanding of the model's classification results. Experimental results on three medical datasets show that ParseCaps not only outperforms other capsule network variants in classification accuracy and robustness, but also provides interpretable explanations, regardless of the availability of concept labels.

Despite the advancements made in Vision Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledgeintensive.Indiscriminately adopting Retrieval Augmented Generation (RAG) techniques is an effective yet expensive way to enable models to answer queries beyond their knowledge scopes.To mitigate the dependence on retrieval and simultaneously maintain, or even improve, the performance benefits provided by retrieval, we propose a method to detect the knowledge boundary of VLLMs, allowing for more efficient use of techniques like RAG.Specifically, we propose a method with two variants that finetune a VLLM on an automatically constructed dataset for boundary identification.Experimental results on various types of Visual Question Answering datasets show that our method successfully depicts a VLLM's knowledge boundary, based on which we are able to reduce indiscriminate retrieval while maintaining or improving the performance.In addition, we show that the knowledge boundary identified by our method for one VLLM can be used as a surrogate boundary for other VLLMs.Code will be released at https://github.com/Chord-Che n-30/VLLM-KnowledgeBoundary

Redundancy is a persistent challenge in Capsule Networks (CapsNet), leading to high computational costs and parameter counts. Although previous studies have introduced pruning after the initial capsule layer, dynamic routing's fully connected nature and non-orthogonal weight matrices reintroduce redundancy in deeper layers. Besides, dynamic routing requires iterating to converge, further increasing computational demands. In this paper, we propose an Orthogonal Capsule Network (OrthCaps) to reduce redundancy, improve routing performance and decrease parameter counts. Firstly, an efficient pruned capsule layer is introduced to discard redundant capsules. Secondly, dynamic routing is replaced with orthogonal sparse attention routing, eliminating the need for iterations and fully connected structures. Lastly, weight matrices during routing are orthogonalized to sustain low capsule similarity, which is the first approach to use Householder orthogonal decomposition to enforce orthogonality in CapsNet. Our experiments on baseline datasets affirm the efficiency and robustness of OrthCaps in classification tasks, in which ablation studies validate the criticality of each component. OrthCaps-Shallow outperforms other Capsule Network benchmarks on four datasets, utilizing only 110k parameters - a mere 1.25% of a standard Capsule Network's total. To the best of our knowledge,$it$achieves the smallest parameter count among existing Capsule Networks. Similarly, OrthCaps-Deep demonstrates competitive performance across four datasets, utilizing only 1.2% of the parameters required by its counterparts.