We propose semantic communication over wireless channels for various modalities, e.g., text and images, in a task-oriented communications setup where the task is classification. We present two approaches based on memory and learning. Both approaches rely on a pre-trained neural network to extract semantic information but differ in codebook construction. In the memory-based approach, we use semantic quantization and compression models, leveraging past source realizations as a codebook to eliminate the need for further training. In the learning-based approach, we use a semantic vector quantized autoencoder model that learns a codebook from scratch. Both are followed by a channel coder in order to reliably convey semantic information to the receiver (classifier) through the wireless medium. In addition to classification accuracy, we define system time efficiency as a new performance metric. Our results demonstrate that the proposed memory-based approach outperforms its learning-based counterpart with respect to system time efficiency while offering comparable accuracy to semantic agnostic conventional baselines.
相關內容
The sequence reconstruction problem, introduced by Levenshtein in 2001, considers a scenario where the sender transmits a codeword from some codebook, and the receiver obtains $N$ noisy outputs of the codeword. We study the problem of efficient reconstruction using $N$ outputs that are each corrupted by at most $t$ substitutions. Specifically, for the ubiquitous Reed-Solomon codes, we adapt the Koetter-Vardy soft-decoding algorithm, presenting a reconstruction algorithm capable of correcting beyond Johnson radius. Furthermore, the algorithm uses $\mathcal{O}(nN)$ field operations, where $n$ is the codeword length.
Pipelines, vital for fluid transport, pose an important yet challenging inspection task, particularly in small, flexible biological systems, that robots have yet to master. In this study, we explored the development of an innovative robot inspired by the ovipositor of parasitic wasps to navigate and inspect pipelines. The robot features a flexible locomotion system that adapts to different tube sizes and shapes through a mechanical inflation technique. The flexible locomotion system employs a reciprocating motion, in which groups of three sliders extend and retract in a cyclic fashion. In a proof-of-principle experiment, the robot locomotion efficiency demonstrated positive linear correlation (r=0.6434) with the diameter ratio (ratio of robot diameter to tube diameter). The robot showcased a remarkable ability to traverse tubes of different sizes, shapes and payloads with an average of (70%) locomotion efficiency across all testing conditions, at varying diameter ratios (0.7-1.5). Furthermore, the mechanical inflation mechanism displayed substantial load-carrying capacity, producing considerable holding force of (13 N), equivalent to carrying a payload of approximately (5.8 Kg) inclusive the robot weight. This novel soft robotic system shows promise for inspection and navigation within tubular confined spaces, particularly in scenarios requiring adaptability to different tube shapes, sizes, and load-carrying capacities. This novel design serves as a foundation for a new class of pipeline inspection robots that exhibit versatility across various pipeline environments, potentially including biological systems.
This paper addresses point-to-point packet routing in undirected networks, which is the most important communication primitive in most networks. The main result proves the existence of routing tables that guarantee a polylog-competitive completion-time $\textbf{deterministically}$: in any undirected network, it is possible to give each node simple stateless deterministic local forwarding rules, such that, any adversarially chosen set of packets are delivered as fast as possible, up to polylog factors. All previous routing strategies crucially required randomization for both route selection and packet scheduling. The core technical contribution of this paper is a new local packet scheduling result of independent interest. This scheduling strategy integrates well with recent sparse semi-oblivious path selection strategies. Such strategies deterministically select not one but several candidate paths for each packet and require a global coordinator to select a single good path from those candidates for each packet. Another challenge is that, even if a single path is selected for each packet, no strategy for scheduling packets along low-congestion paths that is both local and deterministic is known. Our novel scheduling strategy utilizes the fact that every semi-oblivious routing strategy uses only a small (polynomial) subset of candidate routes. It overcomes the issue of global coordination by furthermore being provably robust to adversarial noise. This avoids the issue of having to choose a single path per packet because congestion caused by ineffective candidate paths can be treated as noise. Our results imply the first deterministic universally-optimal algorithms in the distributed supported-CONGEST model for many important global distributed tasks, including computing minimum spanning trees, approximate shortest paths, and part-wise aggregates.
Robots often need to convey information to human users. For example, robots can leverage visual, auditory, and haptic interfaces to display their intent or express their internal state. In some scenarios there are socially agreed upon conventions for what these signals mean: e.g., a red light indicates an autonomous car is slowing down. But as robots develop new capabilities and seek to convey more complex data, the meaning behind their signals is not always mutually understood: one user might think a flashing light indicates the autonomous car is an aggressive driver, while another user might think the same signal means the autonomous car is defensive. In this paper we enable robots to adapt their interfaces to the current user so that the human's personalized interpretation is aligned with the robot's meaning. We start with an information theoretic end-to-end approach, which automatically tunes the interface policy to optimize the correlation between human and robot. But to ensure that this learning policy is intuitive -- and to accelerate how quickly the interface adapts to the human -- we recognize that humans have priors over how interfaces should function. For instance, humans expect interface signals to be proportional and convex. Our approach biases the robot's interface towards these priors, resulting in signals that are adapted to the current user while still following social expectations. Our simulations and user study results across $15$ participants suggest that these priors improve robot-to-human communication. See videos here: //youtu.be/Re3OLg57hp8
In millimeter-wave (mmWave) integrated sensing and communication networks, users may be within the coverage of multiple access points (AP), which typically employ large-scale antenna arrays to mitigate obstacle occlusion and path loss. However, large-scale arrays generate pencil-shaped beams, which necessitate a higher number of training beams to cover the desired space. Furthermore, as the antenna aperture increases, users are more likely to be situated in the near-field region of the AP antenna array. This motivates our investigation into the near-field beam training problem to achieve effective positioning services. To address the high complexity and low identification accuracy of existing beam training techniques, we propose an efficient hashing multi-arm beam (HMB) training scheme for the near-field scenario. Specifically, we first construct a near-field single-beam training codebook for the uniform planar arrays. Then, the hash functions are chosen independently to construct the multi-arm beam training codebooks for each AP. All APs traverse the predefined multi-arm beam training codeword simultaneously and the multi-AP superimposed signals at the user are recorded. Finally, the soft decision and voting methods are applied to obtain the correctly aligned beams only based on the signal powers. In addition, we logically prove that the traversal complexity is at the logarithmic level. Simulation results show that our proposed near-field HMB training method can achieve 96.4% identification accuracy of the exhaustive beam training method and greatly reduce the training overhead. Furthermore, we verify its applicability under the far-field scenario as well.
Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older layers, has proven quite successful in improving the efficiency of training deep neural networks. In this paper, we propose a theoretical explanation for the efficacy of stacking: viz., stacking implements a form of Nesterov's accelerated gradient descent. The theory also covers simpler models such as the additive ensembles constructed in boosting methods, and provides an explanation for a similar widely-used practical heuristic for initializing the new classifier in each round of boosting. We also prove that for certain deep linear residual networks, stacking does provide accelerated training, via a new potential function analysis of the Nesterov's accelerated gradient method which allows errors in updates. We conduct proof-of-concept experiments to validate our theory as well.
Broadly, the goal when clustering data is to separate observations into meaningful subgroups. The rich variety of methods for clustering reflects the fact that the relevant notion of meaningful clusters varies across applications. The classical Bayesian approach clusters observations by their association with components of a mixture model; the choice in class of components allows flexibility to capture a range of meaningful cluster notions. However, in practice the range is somewhat limited as difficulties with computation and cluster identifiability arise as components are made more flexible. Instead of mixture component attribution, we consider clusterings that are functions of the data and the density $f$, which allows us to separate flexible density estimation from clustering. Within this framework, we develop a method to cluster data into connected components of a level set of $f$. Under mild conditions, we establish that our Bayesian level-set (BALLET) clustering methodology yields consistent estimates, and we highlight its performance in a variety of toy and simulated data examples. Finally, through an application to astronomical data we show the method performs favorably relative to the popular level-set clustering algorithm DBSCAN in terms of accuracy, insensitivity to tuning parameters, and quantification of uncertainty.
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. For example, a robot needs to understand new instructions, and an opinion monitoring system should analyze emerging topics every day. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in deep class-incremental learning and summarize these methods from three aspects, i.e., data-centric, model-centric, and algorithm-centric. We also provide a rigorous and unified evaluation of 16 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures. The source code to reproduce these evaluations is available at //github.com/zhoudw-zdw/CIL_Survey/
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems into consideration and are unsupervised. By leveraging returns, the most important feedback signals in RL, we propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our auxiliary loss is theoretically justified to learn representations that capture the structure of a new form of state-action abstraction, under which state-action pairs with similar return distributions are aggregated together. In low data regime, our algorithm outperforms strong baselines on complex tasks in Atari games and DeepMind Control suite, and achieves even better performance when combined with existing auxiliary tasks.
Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items that the user might be interacted with. Recent works usually give an overall embedding from a user's behavior sequence. However, a unified user embedding cannot reflect the user's multiple interests during a period. In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our multi-interest module captures multiple interests from user behavior sequences, which can be exploited for retrieving candidate items from the large-scale item pool. These items are then fed into an aggregation module to obtain the overall recommendation. The aggregation module leverages a controllable factor to balance the recommendation accuracy and diversity. We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao. Experimental results demonstrate that our framework achieves significant improvements over state-of-the-art models. Our framework has also been successfully deployed on the offline Alibaba distributed cloud platform.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191