The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess their fit as a head or tail of a candidate link to be added. In Knowledge Graphs on a larger scale, this task rapidly becomes prohibitively heavy. Previous approaches mitigate this problem by using random sampling of entities to assess the quality of links predicted or suggested by a method. However, we show that this approach has serious limitations since the ranking metrics produced do not properly reflect true outcomes. In this paper, we present a thorough analysis of these effects along with the following findings. First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method. We show that this can be attributed to the effect of easy versus hard negatives. Second, we propose a framework that uses relational recommenders to guide the selection of candidates for evaluation. We provide both theoretical and empirical justification of our methodology, and find that simple and fast methods work extremely well, matching advanced neural approaches. Even when a large portion of the true candidates for a property are missed, the estimation of the ranking metrics on a downstream model barely deteriorates. With our proposed framework, we can reduce the time and computation needed similar to random sampling strategies while vastly improving the estimation; on ogbl-wikikg2, we show that accurate estimations of the full ranking can be obtained in 20 seconds instead of 30 minutes. We conclude that considerable computational effort can be saved by effective preprocessing and sampling methods and still reliably predict performance accurately of the true performance for the entire ranking procedure. We make our code available to the community11Accessible at https://github.com/Filco306/are-we-wasting-time.

This paper presents a rapid 3D printing framework that enhances the efficiency of commercially available layered manufacturing-based 3D printers. Unlike traditional methods that simplify printing regions to a single point or rely on predefined entry and exit points, our approach utilizes an improved Traveling Salesman Problem (TSP) algorithm to autonomously generate an optimized, cyclic printing path, while automatically assigning entry and exit points for each region. This minimizes non-printing paths and improves efficiency. Additionally, we propose a principal axis calculation method for irregular shapes, aligning better with geometric orientation. This optimization enhances infill uniformity and surface smoothness. Simulations and experimental results demonstrate that the proposed framework improves printing efficiency while maintaining print quality, with promising applicability to large-scale and complex 3D printing models.

We introduce a novel low-power imaging system capable of multispectral ultraviolet (UV) imaging with the ability to distinguish between different UV wavelengths. This advancement is achieved by enhancing a three-layer vertically stacked photodiode (3T APS) complementary metal-oxide-semiconductor (CMOS) image sensor with specially manufactured and tuned perovskite nanocrystals (PNCs), effectively extending the sensor’s multi-channel quantum efficiency across the UVB and UVA range. Our imaging system includes all necessary peripherals and circuits. Experimental results demonstrate that the PNC-enhanced sensor can precisely differentiate 11 distinct UV wavelengths between 300 nm and 400 nm, a level of detail unachievable with the unmodified sensor. This technology offers substantial potential for industrial and clinical applications, including the in-vitro detection of multiple biomarkers with subtly different UV fluorescence emission spectra.

We present the design, fabrication, and optical validation of a single-chip multispectral imaging sensor spanning 400 nm to 1050 nm. The sensor integrates vertically stacked photodiodes with pixelated spectral filters to capture 12 spectral bands—three in the visible spectrum and nine in the near-infrared (NIR) spectrum. This enables simultaneous visualization of both tumor-targeted and lymph node-mapping probes using the same NIR excitation source. The system’s performance was validated through optical experiments, demonstrating accurate spectral differentiation between indocyanine green (ICG) and the folate-targeted probe Cytalux. This multispectral imaging approach addresses the limitations of current imaging systems, which are restricted to single-probe visualization, offering a powerful tool for enhancing cancer surgery outcomes.

We present a single-chip imaging sensor capable of simultaneous ultraviolet (UV), visible (VIS), and near-infrared (NIR) imaging. The system integrates a checkerboard-patterned multispectral pixelated filter array with a three-layer stacked photodiode architecture, achieving six distinct spectral bands. Each photodiode layer is optimized for specific wavelengths, leveraging the wavelength-dependent absorption properties of silicon. With a power consumption of 250 mW and nearly 100% transmission in both UV and NIR spectra, the platform is optimized for intraoperative use without disrupting the surgical workflow. Clinical data from 33 patients with breast cancer demonstrated a positive predictive value of 100% for detecting primary tumors based on UV autofluorescence. These results highlight the platform’s potential for enhancing cancer detection in real-time surgical settings.

Automated feature generation can greatly enhance the performance of machine learning models in many tabular and time-series prediction problems. The current state-of-the-art method, OpenFE, follows the “expand-and-reduce” framework, which generates a candidate feature set and subsequently extracts the most effective features from this set. Nevertheless, with the increase in the number of features and the length of time series, feature generation algorithms based on expand-and-reduce often produce an overwhelmingly large pool of candidate features, rendering the identification of effective features quite time-consuming and more prone to overfitting. To resolve this issue, we propose OpenFE++, which leverages the feature interactions from both the feature and temporal dimensions to construct a substantially reduced candidate feature set, thereby enhancing efficiency and effectiveness in feature generation. In the feature dimension, OpenFE++ utilizes locally interacted features to generate meaningful candidate features without exhaustively enumerating all possibilities. In the temporal dimension, it evaluates the lagged effects among different features and generates temporally meaningful features via the representative lagged periods, eliminating the need for enumeration in sequence length. Thus, OpenFE++ can efficiently generate effective, generalizable and interpretable features to boost the forecasting performance of machine learning models. We conduct extensive experiments on fourteen widely used benchmark datasets (ten benchmarks for tabular tasks and four benchmarks for time-series tasks) to demonstrate that OpenFE++ outperforms other baseline models in both efficiency and effectiveness.

We proposed a technique of coincidence detection of cascade photons (CDCP) to enhance preclinical SPECT imaging of therapeutic radionuclides emitting cascade photons, such as Lu-177, Ac-225, Ra-223, and In-111. We have carried out experimental studies to evaluate the proposed CDCP-SPECT imaging of low-activity radionuclides using a prototype coincidence detection system constructed with large-volume cadmium zinc telluride (CZT) imaging spectrometers and a pinhole collimator. With In-111 in experimental studies, the CDCP technique allows us to improve the signal-to-contamination in the projection (Projection-SCR) by ~53 times and reduce ~98% of the normalized contamination. Compared to traditional scatter correction, which achieves a Projection-SCR of 1.00, our CDCP method boosts it to 15.91, showing enhanced efficacy in reducing down-scattered contamination, especially at lower activities. The reconstructed images of a line source demonstrated the dramatic enhancement of the image quality with CDCP-SPECT compared to conventional and triple-energy-window-corrected SPECT data acquisition. We also introduced artificial energy blurring and Monte Carlo simulation to quantify the impact of detector performance, especially its energy resolution and timing resolution, on the enhancement through the CDCP technique. We have further demonstrated the benefits of the CDCP technique with simulation studies, which shows the potential of improving the signal-to-contamination ratio by 300 times with Ac-225, which emits cascade photons with a decay constant of ~0.1 ns. These results have demonstrated the potential of CDCP-enhanced SPECT for imaging a super-low level of therapeutic radionuclides in small animals.

Cellular coverage quality estimation has been a critical task for self-organized networks. In real-world scenarios, deep-learning-powered coverage quality estimation methods cannot scale up to large areas due to little ground truth can be provided during network design & optimization. In addition, they fall short in producing expressive embeddings to adequately capture the variations of the cells’ configurations. To deal with this challenge, we formulate the task in a graph representation and so that we can apply state-of-the-art graph neural networks, that show exemplary performance. We propose a novel training framework that can both produce quality cell configuration embeddings for estimating multiple KPIs, while we show it is capable of generalising to large (area-wide) scenarios given very few labeled cells. We show that our framework yields comparable accuracy with models that have been trained using massively labeled samples.

Accurate routing network status estimation is a key component in Software Defined Networking. However, existing deep-learning-based methods for modeling network routing are not able to extrapolate towards unseen feature distributions. Nor are they able to handle scaled and drifted network attributes in test sets that include open-world inputs. To deal with these challenges, we propose a novel approach for modeling network routing, using Graph Neural Networks. Our method can also be used for network-latency estimation. Supported by a domain-knowledge-assisted graph formulation, our model shares a stable performance across different network sizes and configurations of routing networks, while at the same time being able to extrapolate towards unseen sizes, configurations, and user behavior. We show that our model outperforms most conventional deep-learning-based models, in terms of prediction accuracy, computational resources, inference speed, as well as ability to generalize towards open-world input.

Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns. However, since financial datasets have very low signal-to-noise ratio and are non-stationary, complex models are often very prone to overfitting and suffer from instability issues. Moreover, as various machine learning and data mining tools become more widely used in quantitative trading, many trading firms have been producing an increasing number of features (aka factors). Therefore, how to automatically select effective features becomes an imminent problem. To address these issues, we propose DoubleEnsemble, an ensemble framework leveraging learning trajectory based sample reweighting and shuffling based feature selection. Specifically, we identify the key samples based on the training dynamics on each sample and elicit key features based on the ablation impact of each feature via shuffling. Our model is applicable to a wide range of base models, capable of extracting complex patterns, while mitigating the overfitting and instability issues for financial market prediction. We conduct extensive experiments, including price prediction for cryptocurrencies and stock trading, using both DNN and gradient boosting decision tree as base models. Our experiment results demonstrate that DoubleEnsemble achieves a superior performance compared with several baseline methods.

We study the problem of utilizing human intelligence to categorize a large number of objects. In this problem, given a category hierarchy and a set of objects, we can ask humans to check whether an object belongs to a category, and our goal is to find the most cost-effective strategy to locate the appropriate category in the hierarchy for each object, such that the cost (i.e., the number of questions to ask humans) is minimized. There are many important applications of this problem, including image classification and product categorization. We develop an online framework, in which category distribution is gradually learned and thus an effective order of questions are adaptively determined. We prove that even if the true category distribution is known in advance, the problem is computationally intractable. We develop an approximation algorithm, and prove that it achieves an approximation factor of 2. We also show that there is a fully polynomial time approximation scheme for the problem. Furthermore, we propose an online strategy which achieves nearly the same performance guarantee as the offline optimal strategy, even if there is no knowledge about category distribution beforehand. Experiments on a real crowdsourcing platform demonstrate the effectiveness of our method.

It is a long standing open problem whether Yao-Yao graphs YY_{k} are all spanners [Li et al. 2002]. Bauer and Damian [Bauer and Damian, 2012] showed that all YY_{6k} for k >= 6 are spanners. Li and Zhan [Li and Zhan, 2016] generalized their result and proved that all even Yao-Yao graphs YY_{2k} are spanners (for k >= 42). However, their technique cannot be extended to odd Yao-Yao graphs, and whether they are spanners are still elusive. In this paper, we show that, surprisingly, for any integer k >= 1, there exist odd Yao-Yao graph YY_{2k+1} instances, which are not spanners.

With the continuous progress of radio technology it is becoming evident that the cellular network will support advanced cellular Vehicle-to-Everything (C-V2X) services, which require connectivity that can provide low latency, high data throughput, high reliability and broad coverage. Before these services are fully deployed in reality, and due to ethical and safety reasons, we turn to simulation to study the support of the cellular network for such services. Therefore, in this paper, we propose a realistic simulation framework for urban C-V2X usecases. The framework consists of an urban mobility simulator, which can accurately model urban traffic, and a network simulator capable for simulating at least the LTE radio equipment and the network protocol stacks in the urban area where the C-V2X service will be offered. We validate the simulation framework by performing a feasibility assessment of a vehicle teleoperation usecase in one urban area of the city of Stockholm.