Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions. In this paper, we introduce the concepts of relation path coverage and relation path confidence to filter out unreliable paths prior to model training to elevate the model performance. Moreover, we propose Knowledge Reasoning Sentence Transformer (KRST) to predict inductive relations in KGs. KRST is designed to encode the extracted reliable paths in KGs, allowing us to properly cluster paths and provide multi-aspect explanations. We conduct extensive experiments on three real-world datasets. The experimental results show that compared to SOTA models, KRST achieves the best performance in most transductive and inductive test cases (4 of 6), and in 11 of 12 few-shot test cases.

Deep regression networks are widely used to tackle the problem of predicting a continuous value for a given input. Task-specialized approaches for training regression networks have shown significant improvement over generic approaches, such as direct regression. More recently, a generic approach based on regression by binary classification using binary-encoded labels has shown significant improvement over direct regression. The space of label encodings for regression is large. Lacking heretofore have been automated approaches to find a good label encoding for a given application. This paper introduces Regularized Label Encoding Learning (RLEL) for end-to-end training of an entire network and its label encoding. RLEL provides a generic approach for tackling regression. Underlying RLEL is our observation that the search space of label encodings can be constrained and efficiently explored by using a continuous search space of real-valued label encodings combined with a regularization function designed to encourage encodings with certain properties. These properties balance the probability of classification error in individual bits against error correction capability. Label encodings found by RLEL result in lower or comparable errors to manually designed label encodings. Applying RLEL results in 10.9% and 12.4% improvement in Mean Absolute Error (MAE) over direct regression and multiclass classification, respectively. Our evaluation demonstrates that RLEL can be combined with off-the-shelf feature extractors and is suitable across different architectures, datasets, and tasks. Code is available at https://github.com/ubc-aamodt-group/RLEL_regression.

Deep neural networks are used for a wide range of regression problems. However, there exists a significant gap in accuracy between specialized approaches and generic direct regression in which a network is trained by minimizing the squared or absolute error of output labels. Prior work has shown that solving a regression problem with a set of binary classifiers can improve accuracy by utilizing well-studied binary classification algorithms. We introduce binary-encoded labels (BEL), which generalizes the application of binary classification to regression by providing a framework for considering arbitrary multi-bit values when encoding target values. We identify desirable properties of suitable encoding and decoding functions used for the conversion between real-valued and binary-encoded labels based on theoretical and empirical study. These properties highlight a tradeoff between classification error probability and error-correction capabilities of label encodings. BEL can be combined with off-the-shelf task-specific feature extractors and trained end-to-end. We propose a series of sample encoding, decoding, and training loss functions for BEL and demonstrate they result in lower error than direct regression and specialized approaches while being suitable for a diverse set of regression problems, network architectures, and evaluation metrics. BEL achieves state-of-the-art accuracies for several regression benchmarks. Code is available at https://github.com/ubc-aamodt-group/BEL_regression.

Given the current momentum and progress, ADS can be expected to continue to advance as variety of ADS products are going to become commercially available in the space of a decade (Chan, 2017). It is envisioned that automated driving technology will lead to a paradigm shift in transportation systems in terms of user experience, mode choices and business models. Nowadays, a greater number of industrialists are increasing their investments in self-driving cars technologies and, more generally, in the automotive sector. ADS research and an increasing number of industrial implementations have been catalyzed by the accumulated knowledge in vehicle dynamics in the wake of breakthroughs in computer vision caused by the advent of deep learning (Krizhevsky, Sutskever, and Hinton, 2012; Bojarski, Yeres, Choromanaska, Choromanski, Firner, Jackel, and Muller, 2017; Kocić, Jovičić, and Drndarević, 2019; Li, Yang, Qu, Cao, and Li, 2021a) and the availability of new sensor modalities such as lidar (Schwarz, 2010). Deep Learning (DL) has been widely used for the implementation of ADSs.

SURFING the web and making free internet phone calls on your Wi-Fi laptop, listening to your iPod on the way home, it often seems that, technologically speaking, we are enjoying a golden age. Human inventiveness is so finely honed, and the globalised technology industries so productive, that there appears to be an invention to cater for every modern whim. But according to a new analysis, this view couldn't be more wrong: far from being in technological nirvana, we are fast approaching a new dark age. That, at least, is the conclusion of Jonathan Huebner, a physicist working at the Pentagon's Naval Air Warfare Center in China Lake, California. He says the rate of technological innovation reached a peak a century ago and has been declining ever since. And like the lookout on the Titanic who spotted the fateful iceberg, Huebner sees the end of innovation looming dead ahead.

Trends in Intelligent Information Knowledge Based Computer Systems. The 18th International FLAIRS Conference seeks high quality, original, Larry Holder, University of Texas at Arlington unpublished submissions in all areas of AI, including, but not limited to, holder@cse.uta.edu The FLAIRS conference offers a set of special tracks, and authors are encouraged to submit papers to a relevant track.