Image classifiers often rely on convolutional neural networks (CNN) for their tasks, which are inherently more heavyweight than multilayer perceptrons (MLPs), which can be problematic in real-time applications. Additionally, many image classification models work on both RGB and grayscale datasets. Classifiers that operate solely on grayscale images are much less common. Grayscale image classification has diverse applications, including but not limited to medical image classification and synthetic aperture radar (SAR) automatic target recognition (ATR). Thus, we present a novel grayscale (single channel) image classification approach using a vectorized view of images. We exploit the lightweightness of MLPs by viewing images as a vector and reducing our problem setting to the grayscale image classification setting. We find that using a single graph convolutional layer batch-wise increases accuracy and reduces variance in the performance of our model. Moreover, we develop a customized accelerator on FPGA for the proposed model with several optimizations to improve its performance. Our experimental results on benchmark grayscale image datasets demonstrate the effectiveness of the proposed model, achieving vastly lower latency (up to 16$\times$ less) and competitive or leading performance compared to other state-of-the-art image classification models on various domain-specific grayscale image classification datasets.
In this paper, we investigate how metasurfaces can be deployed to deliver high data rates in a millimeter-wave (mmWave) indoor dense space with many blocking objects. These surfaces can either be static metasurfaces (SMSs) that reflect with fixed phase-shifts or reconfigurable intelligent surfaces (RISs) that can reconfigure their phase-shifts to the currently served user. The latter comes with an increased power, cabling, and signaling cost. To see how reconfigurability affects the network performance, we propose an iterative algorithm based on the feasible point pursuit successive convex approximation method. We jointly optimize the types and phase-shifts of the surfaces and the time portion allocated to each user equipment to maximize the minimum data rate achieved by the network. Our numerical results demonstrate that the minimum data rate improves as more RISs are introduced but the gain diminishes after some point. Therefore, introducing more reconfigurability is not always necessary. Another result shows that to reach the same data rate achieved by using 22 SMSs, at least 18 RISs are needed. This suggests that when it is costly to deploy many RISs, as an inexpensive alternative solution, one can reach the same data rate just by densely deploying more SMSs.
Efficient parallel computing has become a pivotal element in advancing artificial intelligence. Yet, the deployment of Spiking Neural Networks (SNNs) in this domain is hampered by their inherent sequential computational dependency. This constraint arises from the need for each time step's processing to rely on the preceding step's outcomes, significantly impeding the adaptability of SNN models to massively parallel computing environments. Addressing this challenge, our paper introduces the innovative Parallel Spiking Unit (PSU) and its two derivatives, the Input-aware PSU (IPSU) and Reset-aware PSU (RPSU). These variants skillfully decouple the leaky integration and firing mechanisms in spiking neurons while probabilistically managing the reset process. By preserving the fundamental computational attributes of the spiking neuron model, our approach enables the concurrent computation of all membrane potential instances within the SNN, facilitating parallel spike output generation and substantially enhancing computational efficiency. Comprehensive testing across various datasets, including static and sequential images, Dynamic Vision Sensor (DVS) data, and speech datasets, demonstrates that the PSU and its variants not only significantly boost performance and simulation speed but also augment the energy efficiency of SNNs through enhanced sparsity in neural activity. These advancements underscore the potential of our method in revolutionizing SNN deployment for high-performance parallel computing applications.
Recently emerged prompt-based Recommendation Language Models (RLM) can solve multiple recommendation tasks uniformly. The RLMs make full use of the inherited knowledge learned from the abundant pre-training data to solve the downstream recommendation tasks by prompts, without introducing additional parameters or network training. However, handcrafted prompts require significant expertise and human effort since slightly rewriting prompts may cause massive performance changes. In this paper, we propose PAP-REC, a framework to generate the Personalized Automatic Prompt for RECommendation language models to mitigate the inefficiency and ineffectiveness problems derived from manually designed prompts. Specifically, personalized automatic prompts allow different users to have different prompt tokens for the same task, automatically generated using a gradient-based method. One challenge for personalized automatic prompt generation for recommendation language models is the extremely large search space, leading to a long convergence time. To effectively and efficiently address the problem, we develop surrogate metrics and leverage an alternative updating schedule for prompting recommendation language models. Experimental results show that our PAP-REC framework manages to generate personalized prompts, and the automatically generated prompts outperform manually constructed prompts and also outperform various baseline recommendation models. The source code of the work is available at https://github.com/rutgerswiselab/PAP-REC.
Training Large Language Models (LLMs) to follow user instructions has been shown to supply the LLM with ample capacity to converse fluently while being aligned with humans. Yet, it is not completely clear how an LLM can lead a plan-grounded conversation in mixed-initiative settings where instructions flow in both directions of the conversation, i.e. both the LLM and the user provide instructions to one another. In this paper, we tackle a dual goal mixed-initiative conversational setting where the LLM not only grounds the conversation on an arbitrary plan but also seeks to satisfy both a procedural plan and user instructions. The LLM is then responsible for guiding the user through the plan and, at the same time, adapting to new circumstances, answering questions, and activating safety guardrails when needed. We propose a novel LLM that grounds the dialogue on a procedural plan, can take the dialogue initiative, and enforces guardrails on the system's behavior, while also improving the LLM's responses to unexpected user behavior. Experiments in controlled settings and with real users show that the best-performing model, which we call PlanLLM, achieves a 2.1x improvement over a strong baseline. Moreover, experiments also show good generalization to unseen domains.
The Industrial Internet of Things (IIoT) enables industries to build large interconnected systems utilizing various technologies that require high data rates. Terahertz (THz) communication is envisioned as a candidate technology for achieving data rates of several terabits-per-second (Tbps). Despite this, establishing a reliable communication link at THz frequencies remains a challenge due to high pathloss and molecular absorption. To overcome these limitations, this paper proposes using intelligent reconfigurable surfaces (IRSs) with THz communications to enable future smart factories for the IIoT. In this paper, we formulate the power allocation and joint IIoT device and IRS association (JIIA) problem, which is a mixed-integer nonlinear programming (MINLP) problem. {Furthermore, the JIIA problem aims to maximize the sum rate with imperfect channel state information (CSI).} To address this non-deterministic polynomial-time hard (NP-hard) problem, we decompose the problem into multiple sub-problems, which we solve iteratively. Specifically, we propose a Gale-Shapley algorithm-based JIIA solution to obtain stable matching between uplink and downlink IRSs. {We validate the proposed solution by comparing the Gale-Shapley-based JIIA algorithm with exhaustive search (ES), greedy search (GS), and random association (RA) with imperfect CSI.} The complexity analysis shows that our algorithm is more efficient than the ES.
Bias mitigation of Language Models has been the topic of many studies with a recent focus on learning separate modules like adapters for on-demand debiasing. Besides optimizing for a modularized debiased model, it is often critical in practice to control the degree of bias reduction at inference time, e.g., in order to tune for a desired performance-fairness trade-off in search results or to control the strength of debiasing in classification tasks. In this paper, we introduce Controllable Gate Adapter (ConGater), a novel modular gating mechanism with adjustable sensitivity parameters, which allows for a gradual transition from the biased state of the model to the fully debiased version at inference time. We demonstrate ConGater performance by (1) conducting adversarial debiasing experiments with three different models on three classification tasks with four protected attributes, and (2) reducing the bias of search results through fairness list-wise regularization to enable adjusting a trade-off between performance and fairness metrics. Our experiments on the classification tasks show that compared to baselines of the same caliber, ConGater can maintain higher task performance while containing less information regarding the attributes. Our results on the retrieval task show that the fully debiased ConGater can achieve the same fairness performance while maintaining more than twice as high task performance than recent strong baselines. Overall, besides strong performance ConGater enables the continuous transitioning between biased and debiased states of models, enhancing personalization of use and interpretability through controllability.
Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning (SFT) methods have proven promising in terms of performance but their memory requirements increase proportionally to the size of the LLMs. In this work, we scale sparse fine-tuning to state-of-the-art LLMs like LLaMA 2 7B and 13B. At any given time, for a desired density level, we maintain an array of parameter indices and the deltas of these parameters relative to their pretrained values. We iterate among: (a) updating the active deltas, (b) pruning indices (based on the change of magnitude of their deltas) and (c) regrowth of indices. For regrowth, we explore two criteria based on either the accumulated gradients of a few candidate parameters or their approximate momenta estimated using the efficient SM3 optimizer. We experiment with instruction-tuning of LLMs on standard dataset mixtures, finding that SFT is often superior to popular parameter-efficient fine-tuning methods like LoRA (low-rank adaptation) in terms of performance and comparable in terms of run time. We additionally show that SFT is compatible with both quantization and efficient optimizers, to facilitate scaling to ever-larger model sizes. We release the code for SFT at https://github.com/AlanAnsell/peft and for the instruction-tuning experiments at https://github.com/ducdauge/sft-llm.
Safety in the face of uncertainty is a key challenge in robotics. In this work, we propose a real-time capable framework to generate safe and task-efficient robot trajectories for stochastic control problems. For that, we first formulate the problem as a chance-constrained optimisation problem, in which the probability of the controlled system to violate a safety constraint is constrained to be below a user-defined threshold. To solve the chance-constrained optimisation problem, we propose a Monte--Carlo approximation relying on samples of the uncertainty to estimate the probability of violating a safety constraint given a controller. We use this approximation in the motion planner VP-STO to solve the sampled-based problem. Consequently, we refer to our adapted approach as CC-VPSTO, which stands for Chance-Constrained VP-STO. We address the crucial issue concerning the Monte--Carlo approximation: given a predetermined number of uncertainty samples, we propose several ways to define the sample-based problem such that it is a reliable over-approximation of the original problem, i.e. any solution to the sample-based problem adheres to the original chance-constrained problem with high confidence. The strengths of our approach lie in i) its generality, as it does not require any specific assumptions on the underlying uncertainty distribution, the dynamics of the system, the cost function, and for some of the proposed sample-based approximations, on the form of inequality constraints; and ii) its applicability to MPC-settings. We demonstrate the validity and efficiency of our approach on both simulation and real-world robot experiments. For additional material, please visit https://sites.google.com/oxfordrobotics.institute/cc-vpsto.
While state-of-the-art facial expression recognition (FER) classifiers achieve a high level of accuracy, they lack interpretability, an important aspect for end-users. To recognize basic facial expressions, experts resort to a codebook associating a set of spatial action units to a facial expression. In this paper, we follow the same expert footsteps, and propose a learning strategy that allows us to explicitly incorporate spatial action units (aus) cues into the classifier's training to build a deep interpretable model. In particular, using this aus codebook, input image expression label, and facial landmarks, a single action units heatmap is built to indicate the most discriminative regions of interest in the image w.r.t the facial expression. We leverage this valuable spatial cue to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \aus map. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with aus maps, simulating the experts' decision process. This is achieved using only the image class expression as supervision and without any extra manual annotations. Moreover, our method is generic. It can be applied to any CNN- or transformer-based deep classifier without the need for architectural change or adding significant training time. Our extensive evaluation on two public benchmarks RAFDB, and AFFECTNET datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on Class-Activation Mapping methods (CAMs), and we show that our training technique improves the CAM interpretability.