Rapid improvements in the performance of machine learning models have pushed them to the forefront of data-driven decision-making. Meanwhile, the increased integration of these models into various application domains has further highlighted the need
for greater interpretability and transparency. To identify problems such as bias, overfitting, and incorrect correlations, data scientists require tools that explain the mechanisms with which these model decisions are made. In this paper we introduce AdViCE, a visual analytics tool that aims to guide users in black-box model debugging and validation. The solution rests on two main visual user interface innovations: (1) an interactive visualization design that enables the comparison of decisions on user-defined data subsets; (2) an algorithm and visual design to compute and visualize counterfactual explanations - explanations that depict model outcomes when data features are perturbed from their original values. We provide a demonstration of the tool through a use case that showcases the capabilities and potential limitations of the proposed approach.
Federated edge learning (FEEL) has emerged as a revolutionary paradigm to develop AI services at the edge of 6G wireless networks as it supports collaborative model training at a massive number of mobile devices. However, model communication over wir
eless channels, especially in uplink model uploading of FEEL, has been widely recognized as a bottleneck that critically limits the efficiency of FEEL. Although over-the-air computation can alleviate the excessive cost of radio resources in FEEL model uploading, practical implementations of over-the-air FEEL still suffer from several challenges, including strong straggler issues, large communication overheads, and potential privacy leakage. In this article, we study these challenges in over-the-air FEEL and leverage reconfigurable intelligent surface (RIS), a key enabler of future wireless systems, to address these challenges. We study the state-of-the-art solutions on RIS-empowered FEEL and explore the promising research opportunities for adopting RIS to enhance FEEL performance.
This paper presents INVIGORATE, a robot system that interacts with human through natural language and grasps a specified object in clutter. The objects may occlude, obstruct, or even stack on top of one another. INVIGORATE embodies several challenges
: (i) infer the target object among other occluding objects, from input language expressions and RGB images, (ii) infer object blocking relationships (OBRs) from the images, and (iii) synthesize a multi-step plan to ask questions that disambiguate the target object and to grasp it successfully. We train separate neural networks for object detection, for visual grounding, for question generation, and for OBR detection and grasping. They allow for unrestricted object categories and language expressions, subject to the training datasets. However, errors in visual perception and ambiguity in human languages are inevitable and negatively impact the robots performance. To overcome these uncertainties, we build a partially observable Markov decision process (POMDP) that integrates the learned neural network modules. Through approximate POMDP planning, the robot tracks the history of observations and asks disambiguation questions in order to achieve a near-optimal sequence of actions that identify and grasp the target object. INVIGORATE combines the benefits of model-based POMDP planning and data-driven deep learning. Preliminary experiments with INVIGORATE on a Fetch robot show significant benefits of this integrated approach to object grasping in clutter with natural language interactions. A demonstration video is available at https://youtu.be/zYakh80SGcU.
Resonant modes in a lossy periodic structure sandwiched between two lossless homogeneous media form bands that depend on the Bloch wavevector continuously and have a complex frequency due to radiation and absorption losses. A complex bound state in t
he continuum (cBIC) is a special state with a zero radiation loss in such a band. Plane waves incident upon the periodic structure induce local fields that are resonantly enhanced. In this paper, we derive a rigorous formula for field enhancement, and analyze its dependence on the frequency, wavevector and amplitude of the incident wave. For resonances with multiple radiation channels, we determine the incident wave that maximizes the field enhancement, and find conditions under which the field enhancement can be related to the radiation and dissipation quality factors. We also show that with respect to the Bloch wavevector, the largest field enhancement is obtained approximately when the radiation and dissipation quality factors are equal. Our study clarifies the various factors related to field enhancement, and provides a useful guideline for applications where a strong local field is important.
This study investigated the effect of harsh winter climate on the performance of high speed passenger trains in northern Sweden. Novel approaches based on heterogeneous statistical models were introduced to analyse the train performance in order to t
ake the time-varying risks of train delays into consideration. Specifically, stratified Cox model and heterogeneous Markov chain model were used for modelling primary delays and arrival delays, respectively. Our results showed that the weather variables including temperature, humidity, snow depth, and ice/snow precipitation have significant impact on the train performance.
Ultra-reliability and low latency communication has long been an important but challenging task in the fifth and sixth generation wireless communication systems. Scheduling as many users as possible to serve on the limited time-frequency resource is
one of a crucial topic, subjecting to the maximum allowable transmission power and the minimum rate requirement of each user. We address it by proposing a mixed integer programming model, with the goal of maximizing the set cardinality of users instead of maximizing the system sum rate or energy efficiency. Mathematical transformations and successive convex approximation are combined to solve the complex optimization problem. Numerical results show that the proposed method achieves a considerable performance compared with exhaustive search method, but with lower computational complexity.
Intrinsic ripples with various configurations and sizes were reported to affect the physical and chemical properties of 2D materials. By performing molecular dynamics simulations and theoretical analysis, we use two geometric models of the ripple sha
pe to explore numerically the distribution of ripples in graphene membrane. We focus on the ratio of ripple height to its diameter (t/D) which was recently shown to be the most relevant for chemical activity of graphene membranes. Our result demonstrates that the ripple density decreases as the coefficient t/D increases, in a qualitative agreement with the Boltzmann distribution derived analytically from the bending energy of the membrane. Our theoretical study provides also specific quantitative information on the ripple distribution in graphene and gives new insights applicable to other 2D materials.
In this letter, we propose a multi-task over-theair federated learning (MOAFL) framework, where multiple learning tasks share edge devices for data collection and learning models under the coordination of a edge server (ES). Specially, the model upda
tes for all the tasks are transmitted and superpositioned concurrently over a non-orthogonal uplink channel via over-the-air computation, and the aggregation results of all the tasks are reconstructed at the ES through an extended version of the turbo compressed sensing algorithm. Both the convergence analysis and numerical results demonstrate that the MOAFL framework can significantly reduce the uplink bandwidth consumption of multiple tasks without causing substantial learning performance degradation.
We propose a novel method on refining cross-person gaze prediction task with eye/face images only by explicitly modelling the person-specific differences. Specifically, we first assume that we can obtain some initial gaze prediction results with exis
ting method, which we refer to as InitNet, and then introduce three modules, the Validity Module (VM), Self-Calibration (SC) and Person-specific Transform (PT)) Module. By predicting the reliability of current eye/face images, our VM is able to identify invalid samples, e.g. eye blinking images, and reduce their effects in our modelling process. Our SC and PT module then learn to compensate for the differences on valid samples only. The former models the translation offsets by bridging the gap between initial predictions and dataset-wise distribution. And the later learns more general person-specific transformation by incorporating the information from existing initial predictions of the same person. We validate our ideas on three publicly available datasets, EVE, XGaze and MPIIGaze and demonstrate that our proposed method outperforms the SOTA methods significantly on all of them, e.g. respectively 21.7%, 36.0% and 32.9% relative performance improvements. We won the GAZE 2021 Competition on the EVE dataset. Our code can be found here https://github.com/bjj9/EVE_SCPT.
Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homoge
neous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. To address this limitations, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which preclude noisy connections and include useful connections (e.g., meta-paths) for tasks, while learning effective node representations on the new graphs in an end-to-end fashion. We further propose enhanced version of GTNs, Fast Graph Transformer Networks (FastGTNs), that improve scalability of graph transformations. Compared to GTNs, FastGTNs are 230x faster and use 100x less memory while allowing the identical graph transformations as GTNs. In addition, we extend graph transformations to the semantic proximity of nodes allowing non-local operations beyond meta-paths. Extensive experiments on both homogeneous graphs and heterogeneous graphs show that GTNs and FastGTNs with non-local operations achieve the state-of-the-art performance for node classification tasks. The code is available: https://github.com/seongjunyun/Graph_Transformer_Networks
