Relative Validity Indices (RVIs) such as the Silhouette Width Criterion, Calinski-Harabasz and Davie's Bouldin indices are the most popular tools for evaluating and optimising applications of clustering. Their ability to rank collections of candidate partitions has been used to guide the selection of the number of clusters, and to compare partitions from different clustering algorithms. Beyond these more conventional tasks, many examples can be found in the literature where RVIs have been used to compare and select other aspects of clustering approaches such as data normalisation procedures, data representation methods, and distance measures. The authors are not aware of any studies that have attempted to establish the suitability of RVIs for such comparisons. Moreover, given the impact of these aspects on pairwise similarities, it is not even immediately obvious how RVIs should be implemented when comparing these aspects. In this study, we conducted experiments with seven common RVIs on over 2.7 million clustering partitions for both synthetic and real-world datasets, encompassing feature-vector and time-series data. Our findings suggest that RVIs are not well-suited to these unconventional tasks, and that conclusions drawn from such applications may be misleading. It is recommended that normalisation procedures, representation methods, and distance measures instead be selected using external validation on high quality labelled datasets or carefully designed outcome-oriented objective criteria, both of which should be informed by relevant domain knowledge and clustering aims.
相關內容
Principal Component Analysis (PCA) aims to find subspaces spanned by the so-called principal components that best represent the variance in the dataset. The deflation method is a popular meta-algorithm that sequentially finds individual principal components, starting from the most important ones and working towards the less important ones. However, as deflation proceeds, numerical errors from the imprecise estimation of principal components propagate due to its sequential nature. This paper mathematically characterizes the error propagation of the inexact Hotelling's deflation method. We consider two scenarios: $i)$ when the sub-routine for finding the leading eigenvector is abstract and can represent various algorithms; and $ii)$ when power iteration is used as the sub-routine. In the latter case, the additional directional information from power iteration allows us to obtain a tighter error bound than the sub-routine agnostic case. For both scenarios, we explicitly characterize how the errors progress and affect subsequent principal component estimations.
Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However, these methods either exhibit poor overall performance or struggle to strike a balance between generalization and locality. We propose MOMoE, a model editing adapter utilizing a Mixture of Experts (MoE) architecture with a knowledge anchor routing strategy. MOMoE updates knowledge using a bypass MoE structure, keeping the original parameters unchanged to preserve the general ability of LLMs. And, the knowledge anchor routing ensures that inputs requiring similar knowledge are routed to the same expert, thereby enhancing the generalization of the updated knowledge. Experimental results show the superiority of our approach over both batch editing and sequential batch editing tasks, exhibiting exceptional overall performance alongside outstanding balance between generalization and locality. Our code will be available.
Residential fixed broadband internet access in the United States (US) has long been distributed inequitably, drawing significant attention from researchers and policymakers. This paper evaluates the efficacy of the Connect America Fund (CAF), a key policy intervention aimed at addressing disparities in US internet access. CAF subsidizes the creation of new regulated broadband monopolies in underserved areas, aiming to provide comparable internet access, in terms of price and speed, to that available in urban regions. Oversight of CAF largely relies on data self-reported by internet service providers (ISPs), which is often questionable. We use the broadband-plan querying tool (BQT) to curate a novel dataset that complements ISP-reported information with ISP-advertised broadband plan details (download speed and monthly cost) on publicly accessible websites. Specifically, we query advertised broadband plans for 687k residential addresses across 15 states, certified as served by ISPs to regulators. Our analysis reveals significant discrepancies between ISP-reported data and actual broadband availability. We find that the serviceability rate-defined as the fraction of addresses ISPs actively serve out of the total queried, weighted by the number of CAF addresses in a census block group-is only 55%, dropping to as low as 18% in some states. Additionally, the compliance rate-defined as the weighted fraction of addresses where ISPs actively serve and advertise download speeds above the FCC's 10 Mbps threshold-is only 33%. We also observe that in a subset of census blocks, CAF-funded addresses receive higher broadband speeds than their monopoly-served neighbors. These results indicate that while a few users have benefited from this multi-billion dollar program, it has largely failed to achieve its intended goal, leaving many targeted rural communities with inadequate or no broadband connectivity.
Given a set of customers, the Flying Sidekick Traveling Salesman Problem (FSTSP) consists of using one truck and one drone to perform deliveries to them. The drone is limited to delivering to one customer at a time, after which it returns to the truck, from where it can be launched again. The goal is to minimize the time required to service all customers and return both vehicles to the depot. In the literature, we can find heuristics for this problem that follow the order-first split-second approach: find a Hamiltonian cycle h with all customers, and then remove some customers to be handled by the drone while deciding from where the drone will be launched and where it will be retrieved. Indeed, they optimally solve the h-FSTSP, which is a variation that consists of solving the FSTSP while respecting a given initial cycle h. We present the Lazy Drone Property, which guarantees that only some combinations of nodes for launch and retrieval of the drone need to be considered by algorithms for the h-FSTSP. We also present an algorithm that uses the property, and we show experimental results which corroborate its effectiveness in decreasing the running time of such algorithms. Our algorithm was shown to be more than 84 times faster than the previously best-known ones over the literature benchmark. Moreover, on average, it considered a number of launch and retrieval pairs that is linear on the number of customers, indicating that the algorithm's performance should be sustainable for larger instances.
We present the Linear Complexity Sequence Model (LCSM), a comprehensive solution that unites various sequence modeling techniques with linear complexity, including linear attention, state space model, long convolution, and linear RNN, within a single framework. The goal is to enhance comprehension of these models by analyzing the impact of each component from a cohesive and streamlined viewpoint. Specifically, we segment the modeling processes of these models into three distinct stages: Expand, Oscillation, and Shrink (EOS), with each model having its own specific settings. The Expand stage involves projecting the input signal onto a high-dimensional memory state. This is followed by recursive operations performed on the memory state in the Oscillation stage. Finally, the memory state is projected back to a low-dimensional space in the Shrink stage. We perform comprehensive experiments to analyze the impact of different stage settings on language modeling and retrieval tasks. Our results show that data-driven methods are crucial for the effectiveness of the three stages in language modeling, whereas hand-crafted methods yield better performance in retrieval tasks.
Despite being a heavily researched topic, Adversarial Training (AT) is rarely, if ever, deployed in practical AI systems for two primary reasons: (i) the gained robustness is frequently accompanied by a drop in generalization and (ii) generating adversarial examples (AEs) is computationally prohibitively expensive. To address these limitations, we propose SMAAT, a new AT algorithm that leverages the manifold conjecture, stating that off-manifold AEs lead to better robustness while on-manifold AEs result in better generalization. Specifically, SMAAT aims at generating a higher proportion of off-manifold AEs by perturbing the intermediate deepnet layer with the lowest intrinsic dimension. This systematically results in better scalability compared to classical AT as it reduces the PGD chains length required for generating the AEs. Additionally, our study provides, to the best of our knowledge, the first explanation for the difference in the generalization and robustness trends between vision and language models, ie., AT results in a drop in generalization in vision models whereas, in encoder-based language models, generalization either improves or remains unchanged. We show that vision transformers and decoder-based models tend to have low intrinsic dimensionality in the earlier layers of the network (more off-manifold AEs), while encoder-based models have low intrinsic dimensionality in the later layers. We demonstrate the efficacy of SMAAT; on several tasks, including robustifying (i) sentiment classifiers, (ii) safety filters in decoder-based models, and (iii) retrievers in RAG setups. SMAAT requires only 25-33% of the GPU time compared to standard AT, while significantly improving robustness across all applications and maintaining comparable generalization.
With the widespread proliferation of AI systems, trust in AI is an important and timely topic to navigate. Researchers so far have largely employed a myopic view of this relationship. In particular, a limited number of relevant trustors (e.g., end-users) and trustees (i.e., AI systems) have been considered, and empirical explorations have remained in laboratory settings, potentially overlooking factors that impact human-AI relationships in the real world. In this paper, we argue for broadening the scope of studies addressing `trust in AI' by accounting for the complex and dynamic supply chains that AI systems result from. AI supply chains entail various technical artifacts that diverse individuals, organizations, and stakeholders interact with, in a variety of ways. We present insights from an in-situ, empirical study of LLM supply chains. Our work reveals additional types of trustors and trustees and new factors impacting their trust relationships. These relationships were found to be central to the development and adoption of LLMs, but they can also be the terrain for uncalibrated trust and reliance on untrustworthy LLMs. Based on these findings, we discuss the implications for research on `trust in AI'. We highlight new research opportunities and challenges concerning the appropriate study of inter-actor relationships across the supply chain and the development of calibrated trust and meaningful reliance behaviors. We also question the meaning of building trust in the LLM supply chain.
Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and social concerns. However, this information is typically presented as unstructured text in accompanying documentation, hampering their automated analysis and processing. In this work, we explore using large language models (LLM) and a set of prompting strategies to automatically extract these dimensions from documents and enrich the dataset description with them. Our approach could aid data publishers and practitioners in creating machine-readable documentation to improve the discoverability of their datasets, assess their compliance with current AI regulations, and improve the overall quality of ML models trained on them. In this paper, we evaluate the approach on 12 scientific dataset papers published in two scientific journals (Nature's Scientific Data and Elsevier's Data in Brief) using two different LLMs (GPT3.5 and Flan-UL2). Results show good accuracy with our prompt extraction strategies. Concrete results vary depending on the dimensions, but overall, GPT3.5 shows slightly better accuracy (81,21%) than FLAN-UL2 (69,13%) although it is more prone to hallucinations. We have released an open-source tool implementing our approach and a replication package, including the experiments' code and results, in an open-source repository.
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS). These models, trained on massive amounts of data using self-supervised learning, have demonstrated remarkable success in learning universal representations and have the potential to enhance various aspects of recommendation systems by some effective transfer techniques such as fine-tuning and prompt tuning, and so on. The crucial aspect of harnessing the power of language models in enhancing recommendation quality is the utilization of their high-quality representations of textual features and their extensive coverage of external knowledge to establish correlations between items and users. To provide a comprehensive understanding of the existing LLM-based recommendation systems, this survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec), with the latter being systematically sorted out for the first time. Furthermore, we systematically review and analyze existing LLM-based recommendation systems within each paradigm, providing insights into their methodologies, techniques, and performance. Additionally, we identify key challenges and several valuable findings to provide researchers and practitioners with inspiration.
Deep Convolutional Neural Networks (CNNs) are a special type of Neural Networks, which have shown state-of-the-art results on various competitive benchmarks. The powerful learning ability of deep CNN is largely achieved with the use of multiple non-linear feature extraction stages that can automatically learn hierarchical representation from the data. Availability of a large amount of data and improvements in the hardware processing units have accelerated the research in CNNs and recently very interesting deep CNN architectures are reported. The recent race in deep CNN architectures for achieving high performance on the challenging benchmarks has shown that the innovative architectural ideas, as well as parameter optimization, can improve the CNN performance on various vision-related tasks. In this regard, different ideas in the CNN design have been explored such as use of different activation and loss functions, parameter optimization, regularization, and restructuring of processing units. However, the major improvement in representational capacity is achieved by the restructuring of the processing units. Especially, the idea of using a block as a structural unit instead of a layer is gaining substantial appreciation. This survey thus focuses on the intrinsic taxonomy present in the recently reported CNN architectures and consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature map exploitation, channel boosting and attention. Additionally, it covers the elementary understanding of the CNN components and sheds light on the current challenges and applications of CNNs.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191