In support of open and reproducible research, there has been a rapidly increasing number of datasets made available for research. As the availability of datasets increases, it becomes more important to have quality metadata for discovering and reusing them. Yet, it is a common issue that datasets often lack quality metadata due to limited resources for data curation. Meanwhile, technologies such as artificial intelligence and large language models (LLMs) are progressing rapidly. Recently, systems based on these technologies, such as ChatGPT, have demonstrated promising capabilities for certain data curation tasks. This paper proposes to leverage LLMs for cost-effective annotation of subject metadata through the LLM-based in-context learning. Our method employs GPT-3.5 with prompts designed for annotating subject metadata, demonstrating promising performance in automatic metadata annotation. However, models based on in-context learning cannot acquire discipline-specific rules, resulting in lower performance in several categories. This limitation arises from the limited contextual information available for subject inference. To the best of our knowledge, we are introducing, for the first time, an in-context learning method that harnesses large language models for automated subject metadata annotation.
Envisioned application areas for reinforcement learning (RL) include autonomous driving, precision agriculture, and finance, which all require RL agents to make decisions in the real world. A significant challenge hindering the adoption of RL methods in these domains is the non-robustness of conventional algorithms. In this paper, we argue that a fundamental issue contributing to this lack of robustness lies in the focus on the expected value of the return as the sole "correct" optimization objective. The expected value is the average over the statistical ensemble of infinitely many trajectories. For non-ergodic returns, this average differs from the average over a single but infinitely long trajectory. Consequently, optimizing the expected value can lead to policies that yield exceptionally high returns with probability zero but almost surely result in catastrophic outcomes. This problem can be circumvented by transforming the time series of collected returns into one with ergodic increments. This transformation enables learning robust policies by optimizing the long-term return for individual agents rather than the average across infinitely many trajectories. We propose an algorithm for learning ergodicity transformations from data and demonstrate its effectiveness in an instructive, non-ergodic environment and on standard RL benchmarks.
We present the design and implementation of WaveFlex, the first smart surface that enhances Private LTE/5G networks operating under the shared-license framework in the Citizens Broadband Radio Service frequency band. WaveFlex works in the presence of frequency diversity: multiple nearby base stations operating on different frequencies, as dictated by a Spectrum Access System coordinator. It also handles time dynamism: due to the dynamic sharing rules of the band, base stations occasionally switch channels, especially when priority users enter the network. Finally, WaveFlex operates independently of the network itself, not requiring access to nor modification of the base station or mobile users, yet it remain compliant with and effective on prevailing cellular protocols. We have designed and fabricated WaveFlex on a custom multi-layer PCB, software defined radio-based network monitor, and supporting control software and hardware. Our experimental evaluation benchmarks an operational Private LTE network running at full line rate. Results demonstrate an 8.50 dB average SNR gain, and an average throughput gain of 4.36 Mbps for a single small cell, and 3.19 Mbps for four small cells, in a realistic indoor office scenario.
With momentum increasing in the use of social robots as long-term assistive and collaborative partners, humans developing social bonds with these artificial agents appears to be inevitable. In human-human dyads, social bonding plays a powerful role in regulating behaviours, emotions, and even health. If this is to extend to human-robot dyads, the phenomenology of such relationships (including their emergence and stability) must be better understood. In this paper, we discuss potential approaches towards operationalizing the phenomenon of social bonding between human-robot dyads. We will discuss a number of biobehavioural proxies of social bonding, moving away from existing approaches that use subjective, psychological measures, and instead grounding our approach in some of the evolutionary, neurobiological and physiological correlates of social bond formation in natural systems: (a) reductions in physiological stress (the ''social buffering'' phenomenon), (b) narrowing of spatial proximity between dyads, and (c) inter-dyad behavioural synchrony. We provide relevant evolutionary support for each proposed component, with suggestions and considerations for how they can be recorded in (real-time) human-robot interaction scenarios. With this, we aim to inspire more robust operationalisation of ''social bonding'' between human and artificial (robotic) agents.
Selective robotic harvesting is a promising technological solution to address labour shortages which are affecting modern agriculture in many parts of the world. For an accurate and efficient picking process, a robotic harvester requires the precise location and orientation of the fruit to effectively plan the trajectory of the end effector. The current methods for estimating fruit orientation employ either complete 3D information which typically requires registration from multiple views or rely on fully-supervised learning techniques, which require difficult-to-obtain manual annotation of the reference orientation. In this paper, we introduce a novel key-point-based fruit orientation estimation method allowing for the prediction of 3D orientation from 2D images directly. The proposed technique can work without full 3D orientation annotations but can also exploit such information for improved accuracy. We evaluate our work on two separate datasets of strawberry images obtained from real-world data collection scenarios. Our proposed method achieves state-of-the-art performance with an average error as low as $8^{\circ}$, improving predictions by $\sim30\%$ compared to previous work presented in~\cite{wagner2021efficient}. Furthermore, our method is suited for real-time robotic applications with fast inference times of $\sim30$ms.
In the wake of relentless digital transformation, data-driven solutions are emerging as powerful tools to address multifarious industrial tasks such as forecasting, anomaly detection, planning, and even complex decision-making. Although data-centric R&D has been pivotal in harnessing these solutions, it often comes with significant costs in terms of human, computational, and time resources. This paper delves into the potential of large language models (LLMs) to expedite the evolution cycle of data-centric R&D. Assessing the foundational elements of data-centric R&D, including heterogeneous task-related data, multi-facet domain knowledge, and diverse computing-functional tools, we explore how well LLMs can understand domain-specific requirements, generate professional ideas, utilize domain-specific tools to conduct experiments, interpret results, and incorporate knowledge from past endeavors to tackle new challenges. We take quantitative investment research as a typical example of industrial data-centric R&D scenario and verified our proposed framework upon our full-stack open-sourced quantitative research platform Qlib and obtained promising results which shed light on our vision of automatic evolving of industrial data-centric R&D cycle.
Handwritten document analysis is an area of forensic science, with the goal of establishing authorship of documents through examination of inherent characteristics. Law enforcement agencies use standard protocols based on manual processing of handwritten documents. This method is time-consuming, is often subjective in its evaluation, and is not replicable. To overcome these limitations, in this paper we present a framework capable of extracting and analyzing intrinsic measures of manuscript documents related to text line heights, space between words, and character sizes using image processing and deep learning techniques. The final feature vector for each document involved consists of the mean and standard deviation for every type of measure collected. By quantifying the Euclidean distance between the feature vectors of the documents to be compared, authorship can be discerned. We also proposed a new and challenging dataset consisting of 362 handwritten manuscripts written on paper and digital devices by 124 different people. Our study pioneered the comparison between traditionally handwritten documents and those produced with digital tools (e.g., tablets). Experimental results demonstrate the ability of our method to objectively determine authorship in different writing media, outperforming the state of the art.
Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee exists for multi-player games. We show that in games that approximately decompose into a set of two-player constant-sum games (called polymatrix games) where global $\epsilon$-Nash equilibria are boundedly far from Nash-equilibria in each subgame, any no-external-regret algorithm that learns by self-play will produce a strategy with bounded vulnerability. For the first time, our results identify a structural property of multi-player games that enable performance guarantees for the strategies produced by a broad class of self-play algorithms. We demonstrate our findings through experiments on Leduc poker.
For the adversarial multi-armed bandit problem with delayed feedback, we consider that the delayed feedback results are from multiple users and are unrestricted on internal distribution. As the player picks an arm, feedback from multiple users may not be received instantly yet after an arbitrary delay of time which is unknown to the player in advance. For different users in a round, the delays in feedback have no latent correlation. Thus, we formulate an adversarial multi-armed bandit problem with multi-user delayed feedback and design a modified EXP3 algorithm named MUD-EXP3, which makes a decision at each round by considering the importance-weighted estimator of the received feedback from different users. On the premise of known terminal round index $T$, the number of users $M$, the number of arms $N$, and upper bound of delay $d_{max}$, we prove a regret of $\mathcal{O}(\sqrt{TM^2\ln{N}(N\mathrm{e}+4d_{max})})$. Furthermore, for the more common case of unknown $T$, an adaptive algorithm named AMUD-EXP3 is proposed with a sublinear regret with respect to $T$. Finally, extensive experiments are conducted to indicate the correctness and effectiveness of our algorithms.
Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models while maintaining a constant number of computational operations. Existing MoE model adopts a fixed gating network where each token is computed by the same number of experts. However, this approach contradicts our intuition that the tokens in each sequence vary in terms of their linguistic complexity and, consequently, require different computational costs. Little is discussed in prior research on the trade-off between computation per token and model performance. This paper introduces adaptive gating in MoE, a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution. The proposed framework preserves sparsity while improving training efficiency. Additionally, curriculum learning is leveraged to further reduce training time. Extensive experiments on diverse NLP tasks show that adaptive gating reduces at most 22.5% training time while maintaining inference quality. Moreover, we conduct a comprehensive analysis of the routing decisions and present our insights when adaptive gating is used.