Authors: Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati
Abstract: Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated by modifying prompts to include examples with chains of thought--demonstrations of solution procedures--with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examine the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems queried with each prompt. While our problems are very simple, we only find meaningful performance improvements from chain of thought prompts when those prompts are exceedingly specific to their problem class, and that those improvements quickly deteriorate as the size n of the query-specified stack grows past the size of stacks shown in the examples. Our results hint that, contrary to previous claims in the literature, CoT's performance improvements do not stem from the model learning general algorithmic procedures via demonstrations and depend on carefully engineering highly problem specific prompts. This spotlights drawbacks of chain of thought, especially because of the sharp tradeoff between possible performance gains and the amount of human labor necessary to generate examples with correct reasoning traces.
Authors: Olga Mashkova, Fernando Zhapa-Camacho, Robert Hoehndorf
Abstract: Ontology embeddings map classes, relations, and individuals in ontologies into $\mathbb{R}^n$, and within $\mathbb{R}^n$ similarity between entities can be computed or new axioms inferred. For ontologies in the Description Logic $\mathcal{EL}^{++}$, several embedding methods have been developed that explicitly generate models of an ontology. However, these methods suffer from some limitations; they do not distinguish between statements that are unprovable and provably false, and therefore they may use entailed statements as negatives. Furthermore, they do not utilize the deductive closure of an ontology to identify statements that are inferred but not asserted. We evaluated a set of embedding methods for $\mathcal{EL}^{++}$ ontologies based on high-dimensional ball representation of concept descriptions, incorporating several modifications that aim to make use of the ontology deductive closure. In particular, we designed novel negative losses that account both for the deductive closure and different types of negatives. We demonstrate that our embedding methods improve over the baseline ontology embedding in the task of knowledge base or ontology completion.
Authors: Michael Mock (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Sebastian Schmidt (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Felix M\"uller (University of Bonn, Bonn, Germany, Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Rebekka G\"orge (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Anna Schmitz (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Elena Haedecke (University of Bonn, Bonn, Germany, Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Angelika Voss (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Dirk Hecker (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany), Maximillian Poretschkin (Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS Sankt Augustin, Germany, University of Bonn, Bonn, Germany)
Abstract: The trustworthiness of AI applications has been the subject of recent research and is also addressed in the EU's recently adopted AI Regulation. The currently emerging foundation models in the field of text, speech and image processing offer completely new possibilities for developing AI applications. This whitepaper shows how the trustworthiness of an AI application developed with foundation models can be evaluated and ensured. For this purpose, the application-specific, risk-based approach for testing and ensuring the trustworthiness of AI applications, as developed in the 'AI Assessment Catalog - Guideline for Trustworthy Artificial Intelligence' by Fraunhofer IAIS, is transferred to the context of foundation models. Special consideration is given to the fact that specific risks of foundation models can have an impact on the AI application and must also be taken into account when checking trustworthiness. Chapter 1 of the white paper explains the fundamental relationship between foundation models and AI applications based on them in terms of trustworthiness. Chapter 2 provides an introduction to the technical construction of foundation models and Chapter 3 shows how AI applications can be developed based on them. Chapter 4 provides an overview of the resulting risks regarding trustworthiness. Chapter 5 shows which requirements for AI applications and foundation models are to be expected according to the draft of the European Union's AI Regulation and Chapter 6 finally shows the system and procedure for meeting trustworthiness requirements.
Authors: Eline M. Bovy, Marnix Suilen, Sebastian Junges, Nils Jansen
Abstract: Partially observable Markov decision processes (POMDPs) rely on the key assumption that probability distributions are precisely known. Robust POMDPs (RPOMDPs) alleviate this concern by defining imprecise probabilities, referred to as uncertainty sets. While robust MDPs have been studied extensively, work on RPOMDPs is limited and primarily focuses on algorithmic solution methods. We expand the theoretical understanding of RPOMDPs by showing that 1) different assumptions on the uncertainty sets affect optimal policies and values; 2) RPOMDPs have a partially observable stochastic game (POSG) semantic; and 3) the same RPOMDP with different assumptions leads to semantically different POSGs and, thus, different policies and values. These novel semantics for RPOMDPS give access to results for the widely studied POSG model; concretely, we show the existence of a Nash equilibrium. Finally, we classify the existing RPOMDP literature using our semantics, clarifying under which uncertainty assumptions these existing works operate.
Authors: Karim Hamade, Reid McIlroy-Young, Siddhartha Sen, Jon Kleinberg, Ashton Anderson
Abstract: Powerful artificial intelligence systems are often used in settings where they must interact with agents that are computationally much weaker, for example when they work alongside humans or operate in complex environments where some tasks are handled by algorithms, heuristics, or other entities of varying computational power. For AI agents to successfully interact in these settings, however, achieving superhuman performance alone is not sufficient; they also need to account for suboptimal actions or idiosyncratic style from their less-skilled counterparts. We propose a formal evaluation framework for assessing the compatibility of near-optimal AI with interaction partners who may have much lower levels of skill; we use popular collaborative chess variants as model systems to study and develop AI agents that can successfully interact with lower-skill entities. Traditional chess engines designed to output near-optimal moves prove to be inadequate partners when paired with engines of various lower skill levels in this domain, as they are not designed to consider the presence of other agents. We contribute three methodologies to explicitly create skill-compatible AI agents in complex decision-making settings, and two chess game frameworks designed to foster collaboration between powerful AI agents and less-skilled partners. On these frameworks, our agents outperform state-of-the-art chess AI (based on AlphaZero) despite being weaker in conventional chess, demonstrating that skill-compatibility is a tangible trait that is qualitatively and measurably distinct from raw performance. Our evaluations further explore and clarify the mechanisms by which our agents achieve skill-compatibility.
Authors: Hans Dermot Doran, Suzana Veljanovska
Abstract: Making AI safe and dependable requires the generation of dependable models and dependable execution of those models. We propose redundant execution as a well-known technique that can be used to ensure reliable execution of the AI model. This generic technique will extend the application scope of AI-accelerators that do not feature well-documented safety or dependability properties. Typical redundancy techniques incur at least double or triple the computational expense of the original. We adopt a co-design approach, integrating reliable model execution with non-reliable execution, focusing that additional computational expense only where it is strictly necessary. We describe the design, implementation and some preliminary results of a hybrid CNN.
Authors: Liangqi Lei, Keke Gai, Jing Yu, Liehuang Zhu
Abstract: Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization.Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating potential risks associated with AI-generated content. However, post-hoc watermarking techniques are susceptible to evasion. Existing watermarking methods for LDMs can only embed fixed messages. Watermark message alteration requires model retraining. The stability of the watermark is influenced by model updates and iterations. Furthermore, the current reconstruction-based watermark removal techniques utilizing variational autoencoders (VAE) and diffusion models have the capability to remove a significant portion of watermarks. Therefore, we propose a novel technique called DiffuseTrace. The goal is to embed invisible watermarks in all generated images for future detection semantically. The method establishes a unified representation of the initial latent variables and the watermark information through training an encoder-decoder model. The watermark information is embedded into the initial latent variables through the encoder and integrated into the sampling process. The watermark information is extracted by reversing the diffusion process and utilizing the decoder. DiffuseTrace does not rely on fine-tuning of the diffusion model components. The watermark is embedded into the image space semantically without compromising image quality. The encoder-decoder can be utilized as a plug-in in arbitrary diffusion models. We validate through experiments the effectiveness and flexibility of DiffuseTrace. DiffuseTrace holds an unprecedented advantage in combating the latest attacks based on variational autoencoders and Diffusion Models.
Authors: Tobias Meggendorfer, Maximilian Weininger
Abstract: We present version 2.0 of the Partial Exploration Tool (PET), a tool for verification of probabilistic systems. We extend the previous version by adding support for stochastic games, based on a recent unified framework for sound value iteration algorithms. Thereby, PET2 is the first tool implementing a sound and efficient approach for solving stochastic games with objectives of the type reachability/safety and mean payoff. We complement this approach by developing and implementing a partial-exploration based variant for all three objectives. Our experimental evaluation shows that PET2 offers the most efficient partial-exploration based algorithm and is the most viable tool on SGs, even outperforming unsound tools.
Authors: Qiqi Zhou, Yichen Zhu
Abstract: This paper investigates the Neural Tangent Kernel (NTK) to search vision transformers without training. In contrast with the previous observation that NTK-based metrics can effectively predict CNNs performance at initialization, we empirically show their inefficacy in the ViT search space. We hypothesize that the fundamental feature learning preference within ViT contributes to the ineffectiveness of applying NTK to NAS for ViT. We both theoretically and empirically validate that NTK essentially estimates the ability of neural networks that learn low-frequency signals, completely ignoring the impact of high-frequency signals in feature learning. To address this limitation, we propose a new method called ViNTK that generalizes the standard NTK to the high-frequency domain by integrating the Fourier features from inputs. Experiments with multiple ViT search spaces on image classification and semantic segmentation tasks show that our method can significantly speed up search costs over prior state-of-the-art NAS for ViT while maintaining similar performance on searched architectures.
Authors: Dongwon Son, Jaehyung Kim, Sanghyeon Son, Beomjoon Kim
Abstract: The usage of 3D vision algorithms, such as shape reconstruction, remains limited because they require inputs to be at a fixed canonical rotation. Recently, a simple equivariant network, Vector Neuron (VN) has been proposed that can be easily used with the state-of-the-art 3D neural network (NN) architectures. However, its performance is limited because it is designed to use only three-dimensional features, which is insufficient to capture the details present in 3D data. In this paper, we introduce an equivariant feature representation for mapping a 3D point to a high-dimensional feature space. Our feature can discern multiple frequencies present in 3D data, which is the key to designing an expressive feature for 3D vision tasks. Our representation can be used as an input to VNs, and the results demonstrate that with our feature representation, VN captures more details, overcoming the limitation raised in its original paper.
Authors: Freddie Grabovski, Lior Yasur, Yaniv Hacmon, Lior Nisimov, Stav Nimrod
Abstract: This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.
Authors: Michele Farisco, Kathinka Evers, Jean-Pierre Changeux
Abstract: We here analyse the question of developing artificial consciousness from an evolutionary perspective, taking the evolution of the human brain and its relation with consciousness as a reference model. This kind of analysis reveals several structural and functional features of the human brain that appear to be key for reaching human-like complex conscious experience and that current research on Artificial Intelligence (AI) should take into account in its attempt to develop systems capable of conscious processing. We argue that, even if AI is limited in its ability to emulate human consciousness for both intrinsic (structural and architectural) and extrinsic (related to the current stage of scientific and technological knowledge) reasons, taking inspiration from those characteristics of the brain that make conscious processing possible and/or modulate it, is a potentially promising strategy towards developing conscious AI. Also, it is theoretically possible that AI research can develop partial or potentially alternative forms of consciousness that is qualitatively different from the human, and that may be either more or less sophisticated depending on the perspectives. Therefore, we recommend neuroscience-inspired caution in talking about artificial consciousness: since the use of the same word consciousness for humans and AI becomes ambiguous and potentially misleading, we propose to clearly specify what is common and what differs in AI conscious processing from full human conscious experience.
Authors: Libing Yang, Yang Li, Long Chen
Abstract: Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this end, we redefine the cloth manipulation problem as a partially observable Markov decision process. A supervised pre-training stage is employed to train a baseline model of our policy. In the second stage, the Proximal Policy Optimization (PPO) is utilized to guide the supervised model within the observation-aligned action space. By optimizing and updating the strategy, our proposed method increases the garment's surface area for cloth unfolding under the soft-body manipulation task. Experimental results show that our proposed framework can further improve the unfolding performance of other state-of-the-art methods.
Authors: Cole Gawin
Abstract: The acquisition and performance of arithmetic skills and basic operations such as addition, subtraction, multiplication, and division are essential for daily functioning, and reflect complex cognitive processes. This paper explores the cognitive mechanisms powering arithmetic learning, presenting a neurobiologically plausible cognitive architecture that simulates the acquisition of these skills. I implement a number vectorization embedding network and an associative memory model to investigate how an intelligent system can learn and recall arithmetic equations in a manner analogous to the human brain. I perform experiments that provide insights into the generalization capabilities of connectionist models, neurological causes of dyscalculia, and the influence of network architecture on cognitive performance. Through this interdisciplinary investigation, I aim to contribute to ongoing research into the neural correlates of mathematical cognition in intelligent systems.
Authors: Felipe Moreno-Vera
Abstract: The increasing sophistication of cyber threats necessitates proactive measures to identify vulnerabilities and potential exploits. Underground hacking forums serve as breeding grounds for the exchange of hacking techniques and discussions related to exploitation. In this research, we propose an innovative approach using topic modeling to analyze and uncover key themes in vulnerabilities discussed within these forums. The objective of our study is to develop a machine learning-based model that can automatically detect and classify vulnerability-related discussions in underground hacking forums. By monitoring and analyzing the content of these forums, we aim to identify emerging vulnerabilities, exploit techniques, and potential threat actors. To achieve this, we collect a large-scale dataset consisting of posts and threads from multiple underground forums. We preprocess and clean the data to ensure accuracy and reliability. Leveraging topic modeling techniques, specifically Latent Dirichlet Allocation (LDA), we uncover latent topics and their associated keywords within the dataset. This enables us to identify recurring themes and prevalent discussions related to vulnerabilities, exploits, and potential targets.
Authors: Arpit Aggarwal
Abstract: There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in higher dimensions on crucial aspects of the attention mechanism, the model's capacity to learn relative positional information, and the convergence of models, all stemming from the choice of sinusoidal basis functions. Through a combination of theoretical insights and empirical analyses, we elucidate how these challenges extend beyond APEs and may adversely affect the performance of Relative Positional Encoding (RPE) methods, such as Rotatory Positional Encoding (RoPE). Subsequently, we introduce an innovative solution termed Orthogonal Polynomial Based Positional Encoding (PoPE) to address some of the limitations associated with existing methods. The PoPE method encodes positional information by leveraging Orthogonal Legendre polynomials. Legendre polynomials as basis functions offers several desirable properties for positional encoding, including improved correlation structure, non-periodicity, orthogonality, and distinct functional forms among polynomials of varying orders. Our experimental findings demonstrate that transformer models incorporating PoPE outperform baseline transformer models on the $Multi30k$ English-to-German translation task, thus establishing a new performance benchmark. Furthermore, PoPE-based transformers exhibit significantly accelerated convergence rates. Additionally, we will present novel theoretical perspectives on position encoding based on the superior performance of PoPE.
Authors: Fakrul Islam Tushar, Avivah Wang, Lavsen Dahal, Michael R. Harowicz, Kyle J. Lafata, Tina D. Tailor, Joseph Y. Lo
Abstract: BACKGROUND: Lung cancer's high mortality rate can be mitigated by early detection, which is increasingly reliant on artificial intelligence (AI) for diagnostic imaging. However, the performance of AI models is contingent upon the datasets used for their training and validation. METHODS: This study developed and validated the DLCSD-mD and LUNA16-mD models utilizing the Duke Lung Cancer Screening Dataset (DLCSD), encompassing over 2,000 CT scans with more than 3,000 annotations. These models were rigorously evaluated against the internal DLCSD and external LUNA16 and NLST datasets, aiming to establish a benchmark for imaging-based performance. The assessment focused on creating a standardized evaluation framework to facilitate consistent comparison with widely utilized datasets, ensuring a comprehensive validation of the model's efficacy. Diagnostic accuracy was assessed using free-response receiver operating characteristic (FROC) and area under the curve (AUC) analyses. RESULTS: On the internal DLCSD set, the DLCSD-mD model achieved an AUC of 0.93 (95% CI:0.91-0.94), demonstrating high accuracy. Its performance was sustained on the external datasets, with AUCs of 0.97 (95% CI: 0.96-0.98) on LUNA16 and 0.75 (95% CI: 0.73-0.76) on NLST. Similarly, the LUNA16-mD model recorded an AUC of 0.96 (95% CI: 0.95-0.97) on its native dataset and showed transferable diagnostic performance with AUCs of 0.91 (95% CI: 0.89-0.93) on DLCSD and 0.71 (95% CI: 0.70-0.72) on NLST. CONCLUSION: The DLCSD-mD model exhibits reliable performance across different datasets, establishing the DLCSD as a robust benchmark for lung cancer detection and diagnosis. Through the provision of our models and code to the public domain, we aim to accelerate the development of AI-based diagnostic tools and encourage reproducibility and collaborative advancements within the medical machine-learning (ML) field.
Authors: Won-Gi Paeng, Daesuk Kwon
Abstract: This short note is written for rapid communication of long context training and to share the idea of how to train it with low memory usage. In the note, we generalize the attention algorithm and neural network of Generative Pre-Trained Transformers and reinterpret it in Path integral formalism. First, the role of the transformer is understood as the time evolution of the token state and second, it is suggested that the all key-token states in the same time as the query-token can attend to the attention with the query token states. As a result of the repetitive time evolution, it is discussed that the token states in the past sequence meats the token states in the present sequence so that the attention between separated sequences becomes possible for maintaining infinite contextual information just by using low memory for limited size of sequence. For the experiment, the $12$ input token window size was taken and one GPU with $24$GB memory was used for the pre-training. It was confirmed that more than $150$ length context is preserved. The sampling result of the training, the code and the other details will be included in the revised version of this note later.
Authors: Syed Jamal Safdar Gardezi (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Lucas Aronson (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Peter Wawrzyn (Department of Biomedical Engineering, University of Wisconsin Madison, Madison, WI, USA), Hongkun Yu (Department of Biomedical Engineering, University of Wisconsin Madison, Madison, WI, USA), E. Jason Abel (Department of Urology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Daniel D. Shapiro (Department of Urology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Meghan G. Lubner (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Joshua Warner (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Giuseppe Toia (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Lu Mao (Department of Biostatistics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA), Pallavi Tiwari (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA, Department of Biomedical Engineering, University of Wisconsin Madison, Madison, WI, USA), Andrew L. Wentland (Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA, Department of Biomedical Engineering, University of Wisconsin Madison, Madison, WI, USA, Department of Medical Physics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA)
Abstract: Purpose: To develop and evaluate a transformer-based deep learning model for the synthesis of nephrographic phase images in CT urography (CTU) examinations from the unenhanced and urographic phases. Materials and Methods: This retrospective study was approved by the local Institutional Review Board. A dataset of 119 patients (mean $\pm$ SD age, 65 $\pm$ 12 years; 75/44 males/females) with three-phase CT urography studies was curated for deep learning model development. The three phases for each patient were aligned with an affine registration algorithm. A custom model, coined Residual transformer model for Nephrographic phase CT image synthesis (ResNCT), was developed and implemented with paired inputs of non-contrast and urographic sets of images trained to produce the nephrographic phase images, that were compared with the corresponding ground truth nephrographic phase images. The synthesized images were evaluated with multiple performance metrics, including peak signal to noise ratio (PSNR), structural similarity index (SSIM), normalized cross correlation coefficient (NCC), mean absolute error (MAE), and root mean squared error (RMSE). Results: The ResNCT model successfully generated synthetic nephrographic images from non-contrast and urographic image inputs. With respect to ground truth nephrographic phase images, the images synthesized by the model achieved high PSNR (27.8 $\pm$ 2.7 dB), SSIM (0.88 $\pm$ 0.05), and NCC (0.98 $\pm$ 0.02), and low MAE (0.02 $\pm$ 0.005) and RMSE (0.042 $\pm$ 0.016). Conclusion: The ResNCT model synthesized nephrographic phase CT images with high similarity to ground truth images. The ResNCT model provides a means of eliminating the acquisition of the nephrographic phase with a resultant 33% reduction in radiation dose for CTU examinations.
Authors: L\'aszl\'o Kop\'acsi, \'Aron F\'othi, Andr\'as L\H{o}rincz
Abstract: Recognition of individual components and keypoint detection supported by instance segmentation is crucial to analyze the behavior of agents on the scene. Such systems could be used for surveillance, self-driving cars, and also for medical research, where behavior analysis of laboratory animals is used to confirm the aftereffects of a given medicine. A method capable of solving the aforementioned tasks usually requires a large amount of high-quality hand-annotated data, which takes time and money to produce. In this paper, we propose a method that alleviates the need for manual labeling of laboratory rats. To do so, first, we generate initial annotations with a computer vision-based approach, then through extensive augmentation, we train a deep neural network on the generated data. The final system is capable of instance segmentation, keypoint detection, and body part segmentation even when the objects are heavily occluded.
Authors: Albert Bou, Morgan Thomas, Sebastian Dittert, Carles Navarro Ram\'irez, Maciej Majewski, Ye Wang, Shivam Patel, Gary Tresadern, Mazen Ahmad, Vincent Moens, Woody Sherman, Simone Sciabola, Gianni De Fabritiis
Abstract: In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a balance between capability, flexibility, and reliability remains challenging due to the complexity of advanced RL algorithms and the significant reliance on specialized code. In this work, we introduce ACEGEN, a comprehensive and streamlined toolkit tailored for generative drug design, built using TorchRL, a modern decision-making library that offers efficient and thoroughly tested reusable components. ACEGEN provides a robust, flexible, and efficient platform for molecular design. We validate its effectiveness by benchmarking it across various algorithms and conducting multiple drug discovery case studies. ACEGEN is accessible at https://github.com/acellera/acegen-open.
Authors: Andrei Lixandru
Abstract: Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute new insights into reinforcement learning algorithm design. The proposed adaptive exploration framework dynamically adjusts the exploration magnitude during training based on the recent performance of the agent. Our proposed method outperforms standard PPO algorithms in learning efficiency, particularly when significant exploratory behavior is needed at the beginning of the learning process.
Authors: Jesse Josua Benjamin, Joseph Lindley, Elizabeth Edwards, Elisa Rubegni, Tim Korjakow, David Grist, Rhiannon Sharkey
Abstract: Generative AI technologies demand new practical and critical competencies, which call on design to respond to and foster these. We present an exploratory study guided by Research-through-Design, in which we partnered with a primary school to develop a constructionist curriculum centered on students interacting with a generative AI technology. We provide a detailed account of the design of and outputs from the curriculum and learning materials, finding centrally that the reflexive and prolonged `hands-on' approach led to a co-development of students' practical and critical competencies. From the study, we contribute guidance for designing constructionist approaches to generative AI technology education; further arguing to do so with `critical responsivity.' We then discuss how HCI researchers may leverage constructionist strategies in designing interactions with generative AI technologies; and suggest that Research-through-Design can play an important role as a `rapid response methodology' capable of reacting to fast-evolving, disruptive technologies such as generative AI.
Authors: Hritik Bansal, Yonatan Bitton, Michal Yarom, Idan Szpektor, Aditya Grover, Kai-Wei Chang
Abstract: Recent advances in diffusion-based generative modeling have led to the development of text-to-video (T2V) models that can generate high-quality videos conditioned on a text prompt. Most of these T2V models often produce single-scene video clips that depict an entity performing a particular action (e.g., `a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., `a red panda climbing a tree' followed by `the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture to recognize the temporal alignment between the video scenes and scene descriptions. For instance, we condition the visual features of the earlier and later scenes of the generated video with the representations of the first scene description (e.g., `a red panda climbing a tree') and second scene description (e.g., `the red panda sleeps on the top of the tree'), respectively. As a result, we show that the T2V model can generate multi-scene videos that adhere to the multi-scene text descriptions and be visually consistent (e.g., entity and background). Further, we finetune the pretrained T2V model with multi-scene video-text data using the TALC framework. We show that the TALC-finetuned model outperforms the baseline methods by 15.5 points in the overall score, which averages visual consistency and text adherence using human evaluation. The project website is https://talc-mst2v.github.io/.
Authors: Emre Can Acikgoz, Mete Erdogan, Deniz Yuret
Abstract: Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations, with a special focus on Turkish. We conduct an in-depth analysis to evaluate the impact of training strategies, model choices, and data availability on the performance of LLMs designed for underrepresented languages. Our approach includes two methodologies: (i) adapting existing LLMs originally pretrained in English to understand Turkish, and (ii) developing a model from the ground up using Turkish pretraining data, both supplemented with supervised fine-tuning on a novel Turkish instruction-tuning dataset aimed at enhancing reasoning capabilities. The relative performance of these methods is evaluated through the creation of a new leaderboard for Turkish LLMs, featuring benchmarks that assess different reasoning and knowledge skills. Furthermore, we conducted experiments on data and model scaling, both during pretraining and fine-tuning, simultaneously emphasizing the capacity for knowledge transfer across languages and addressing the challenges of catastrophic forgetting encountered during fine-tuning on a different language. Our goal is to offer a detailed guide for advancing the LLM framework in low-resource linguistic contexts, thereby making natural language processing (NLP) benefits more globally accessible.
Authors: Xiaomei Wang, Xiaoyu Chen
Abstract: This paper describes a new research paradigm for studying human-AI collaboration, named "human-AI mutual learning", defined as the process where humans and AI agents preserve, exchange, and improve knowledge during human-AI collaboration. We describe relevant methodologies, motivations, domain examples, benefits, challenges, and future research agenda under this paradigm.
Authors: Ruiyang Qin, Zheyu Yan, Dewen Zeng, Zhenge Jia, Dancheng Liu, Jianbo Liu, Zhi Zheng, Ningyuan Cao, Kai Ni, Jinjun Xiong, Yiyu Shi
Abstract: Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required resources remain a heavy burden on edge devices. Instead, Retrieval-Augmented Generation (RAG), a resource-efficient LLM learning method, can improve the quality of the LLM-generated content without updating model parameters. However, the RAG-based LLM may involve repetitive searches on the profile data in every user-LLM interaction. This search can lead to significant latency along with the accumulation of user data. Conventional efforts to decrease latency result in restricting the size of saved user data, thus reducing the scalability of RAG as user data continuously grows. It remains an open question: how to free RAG from the constraints of latency and scalability on edge devices? In this paper, we propose a novel framework to accelerate RAG via Computing-in-Memory (CiM) architectures. It accelerates matrix multiplications by performing in-situ computation inside the memory while avoiding the expensive data transfer between the computing unit and memory. Our framework, Robust CiM-backed RAG (RoCR), utilizing a novel contrastive learning-based training method and noise-aware training, can enable RAG to efficiently search profile data with CiM. To the best of our knowledge, this is the first work utilizing CiM to accelerate RAG.
Authors: Kyle Stachowicz, Sergey Levine
Abstract: Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding catastrophic failures during training, which might severely impede both learning progress and the performance of the final policy. In many robotics settings, this amounts to avoiding certain "unsafe" states. The high-speed off-road driving task represents a particularly challenging instantiation of this problem: a high-return policy should drive as aggressively and as quickly as possible, which often requires getting close to the edge of the set of "safe" states, and therefore places a particular burden on the method to avoid frequent failures. To both learn highly performant policies and avoid excessive failures, we propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. Furthermore, we show that our risk-sensitive objective automatically avoids out-of-distribution states when equipped with an estimator for epistemic uncertainty. We implement our algorithm on a small-scale rally car and show that it is capable of learning high-speed policies for a real-world off-road driving task. We show that our method greatly reduces the number of safety violations during the training process, and actually leads to higher-performance policies in both driving and non-driving simulation environments with similar challenges.
Authors: Cong Cao, Ramit Debnath, R. Michael Alvarez
Abstract: Policymakers frequently analyze air quality and climate change in isolation, disregarding their interactions. This study explores the influence of specific climate factors on air quality by contrasting a regression model with K-Means Clustering, Hierarchical Clustering, and Random Forest techniques. We employ Physics-based Deep Learning (PBDL) and Long Short-Term Memory (LSTM) to examine the air pollution predictions. Our analysis utilizes ten years (2009-2018) of daily traffic, weather, and air pollution data from three major cities in Norway. Findings from feature selection reveal a correlation between rising heating degree days and heightened air pollution levels, suggesting increased heating activities in Norway are a contributing factor to worsening air quality. PBDL demonstrates superior accuracy in air pollution predictions compared to LSTM. This paper contributes to the growing literature on PBDL methods for more accurate air pollution predictions using environmental variables, aiding policymakers in formulating effective data-driven climate policies.
Authors: Danda B. Rawat, Hassan El alami, Desta Haileselassie Hagos
Abstract: In this paper, we present a comprehensive survey of the metaverse, envisioned as a transformative dimension of next-generation Internet technologies. This study not only outlines the structural components of our survey but also makes a substantial scientific contribution by elucidating the foundational concepts underlying the emergence of the metaverse. We analyze its architecture by defining key characteristics and requirements, thereby illuminating the nascent reality set to revolutionize digital interactions. Our analysis emphasizes the importance of collaborative efforts in developing metaverse standards, thereby fostering a unified understanding among industry stakeholders, organizations, and regulatory bodies. We extend our scrutiny to critical technologies integral to the metaverse, including interactive experiences, communication technologies, ubiquitous computing, digital twins, artificial intelligence, and cybersecurity measures. For each technological domain, we rigorously assess current contributions, principal techniques, and representative use cases, providing a nuanced perspective on their potential impacts. Furthermore, we delve into the metaverse's diverse applications across education, healthcare, business, social interactions, industrial sectors, defense, and mission-critical operations, highlighting its extensive utility. Each application is thoroughly analyzed, demonstrating its value and addressing associated challenges. The survey concludes with an overview of persistent challenges and future directions, offering insights into essential considerations and strategies necessary to harness the full potential of the metaverse. Through this detailed investigation, our goal is to articulate the scientific contributions of this survey paper, transcending a mere structural overview to highlight the transformative implications of the metaverse.
Authors: Vishnu Sashank Dorbala, Prasoon Goyal, Robinson Piramuthu, Michael Johnston, Dinesh Manocha, Reza Ghanadhan
Abstract: We present and tackle the problem of Embodied Question Answering (EQA) with Situational Queries (S-EQA) in a household environment. Unlike prior EQA work tackling simple queries that directly reference target objects and quantifiable properties pertaining them, EQA with situational queries (such as "Is the bathroom clean and dry?") is more challenging, as the agent needs to figure out not just what the target objects pertaining to the query are, but also requires a consensus on their states to be answerable. Towards this objective, we first introduce a novel Prompt-Generate-Evaluate (PGE) scheme that wraps around an LLM's output to create a dataset of unique situational queries, corresponding consensus object information, and predicted answers. PGE maintains uniqueness among the generated queries, using multiple forms of semantic similarity. We validate the generated dataset via a large scale user-study conducted on M-Turk, and introduce it as S-EQA, the first dataset tackling EQA with situational queries. Our user study establishes the authenticity of S-EQA with a high 97.26% of the generated queries being deemed answerable, given the consensus object data. Conversely, we observe a low correlation of 46.2% on the LLM-predicted answers to human-evaluated ones; indicating the LLM's poor capability in directly answering situational queries, while establishing S-EQA's usability in providing a human-validated consensus for an indirect solution. We evaluate S-EQA via Visual Question Answering (VQA) on VirtualHome, which unlike other simulators, contains several objects with modifiable states that also visually appear different upon modification -- enabling us to set a quantitative benchmark for S-EQA. To the best of our knowledge, this is the first work to introduce EQA with situational queries, and also the first to use a generative approach for query creation.
Authors: Seoyoung Hong, Jeongwhan Choi, Yeon-Chang Lee, Srijan Kumar, Noseong Park
Abstract: Collaborative filtering (CF) methods for recommendation systems have been extensively researched, ranging from matrix factorization and autoencoder-based to graph filtering-based methods. Recently, lightweight methods that require almost no training have been recently proposed to reduce overall computation. However, existing methods still have room to improve the trade-offs among accuracy, efficiency, and robustness. In particular, there are no well-designed closed-form studies for \emph{balanced} CF in terms of the aforementioned trade-offs. In this paper, we design SVD-AE, a simple yet effective singular vector decomposition (SVD)-based linear autoencoder, whose closed-form solution can be defined based on SVD for CF. SVD-AE does not require iterative training processes as its closed-form solution can be calculated at once. Furthermore, given the noisy nature of the rating matrix, we explore the robustness against such noisy interactions of existing CF methods and our SVD-AE. As a result, we demonstrate that our simple design choice based on truncated SVD can be used to strengthen the noise robustness of the recommendation while improving efficiency. Code is available at https://github.com/seoyoungh/svd-ae.
Authors: Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee-Chien Chang
Abstract: Attack knowledge graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structured representations, portraying the evolutionary traces of cyber attacks. Even though previous research has proposed various methods to construct attack knowledge graphs, they generally suffer from limited generalization capability to diverse knowledge types as well as requirement of expertise in model design and tuning. Addressing these limitations, we seek to utilize Large Language Models (LLMs), which have achieved enormous success in a broad range of tasks given exceptional capabilities in both language understanding and zero-shot task fulfillment. Thus, we propose a fully automatic LLM-based framework to construct attack knowledge graphs named: AttacKG+. Our framework consists of four consecutive modules: rewriter, parser, identifier, and summarizer, each of which is implemented by instruction prompting and in-context learning empowered by LLMs. Furthermore, we upgrade the existing attack knowledge schema and propose a comprehensive version. We represent a cyber attack as a temporally unfolding event, each temporal step of which encapsulates three layers of representation, including behavior graph, MITRE TTP labels, and state summary. Extensive evaluation demonstrates that: 1) our formulation seamlessly satisfies the information needs in threat event analysis, 2) our construction framework is effective in faithfully and accurately extracting the information defined by AttacKG+, and 3) our attack graph directly benefits downstream security practices such as attack reconstruction. All the code and datasets will be released upon acceptance.
Authors: Roelien C. Timmer, David Liebowitz, Surya Nepal, Salil S. Kanhere
Abstract: Honeyfiles are a particularly useful type of honeypot: fake files deployed to detect and infer information from malicious behaviour. This paper considers the challenge of naming honeyfiles so they are camouflaged when placed amongst real files in a file system. Based on cosine distances in semantic vector spaces, we develop two metrics for filename camouflage: one based on simple averaging and one on clustering with mixture fitting. We evaluate and compare the metrics, showing that both perform well on a publicly available GitHub software repository dataset.
Authors: HanXiang Xu, ShenAo Wang, Ningke Li, Yanjie Zhao, Kai Chen, Kailong Wang, Yang Liu, Ting Yu, HaoYu Wang
Abstract: The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in various domains, including cybersecurity. As the volume and sophistication of cyber threats continue to grow, there is an increasing need for intelligent systems that can automatically detect vulnerabilities, analyze malware, and respond to attacks. In this survey, we conduct a comprehensive review of the literature on the application of LLMs in cybersecurity (LLM4Security). By comprehensively collecting over 30K relevant papers and systematically analyzing 127 papers from top security and software engineering venues, we aim to provide a holistic view of how LLMs are being used to solve diverse problems across the cybersecurity domain. Through our analysis, we identify several key findings. First, we observe that LLMs are being applied to a wide range of cybersecurity tasks, including vulnerability detection, malware analysis, network intrusion detection, and phishing detection. Second, we find that the datasets used for training and evaluating LLMs in these tasks are often limited in size and diversity, highlighting the need for more comprehensive and representative datasets. Third, we identify several promising techniques for adapting LLMs to specific cybersecurity domains, such as fine-tuning, transfer learning, and domain-specific pre-training. Finally, we discuss the main challenges and opportunities for future research in LLM4Security, including the need for more interpretable and explainable models, the importance of addressing data privacy and security concerns, and the potential for leveraging LLMs for proactive defense and threat hunting. Overall, our survey provides a comprehensive overview of the current state-of-the-art in LLM4Security and identifies several promising directions for future research.
Authors: Pengyu Zhang, Yingjie Liu, Yingbo Zhou, Xiao Du, Xian Wei, Ting Wang, Mingsong Chen
Abstract: Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated pruning methods are proposed to reduce memory usage during inference. However, few of them can substantially mitigate the memory burdens during pruning and training. As an alternative, zeroth-order or backpropagation-free (BP-Free) methods can partially alleviate the memory consumption, but they suffer from scaling up and large computation overheads, since the gradient estimation error and floating point operations (FLOPs) increase as the dimensionality of the model parameters grows. In this paper, we propose a federated foresight pruning method based on Neural Tangent Kernel (NTK), which can seamlessly integrate with federated BP-Free training frameworks. We present an approximation to the computation of federated NTK by using the local NTK matrices. Moreover, we demonstrate that the data-free property of our method can substantially reduce the approximation error in extreme data heterogeneity scenarios. Since our approach improves the performance of the vanilla BP-Free method with fewer FLOPs and truly alleviates memory pressure during training and inference, it makes FL more friendly to low-memory devices. Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.
Authors: Wei Ju, Zhengyang Mao, Siyu Yi, Yifang Qin, Yiyang Gu, Zhiping Xiao, Yifan Wang, Xiao Luo, Ming Zhang
Abstract: In this paper, we study semi-supervised graph classification, which aims at accurately predicting the categories of graphs in scenarios with limited labeled graphs and abundant unlabeled graphs. Despite the promising capability of graph neural networks (GNNs), they typically require a large number of costly labeled graphs, while a wealth of unlabeled graphs fail to be effectively utilized. Moreover, GNNs are inherently limited to encoding local neighborhood information using message-passing mechanisms, thus lacking the ability to model higher-order dependencies among nodes. To tackle these challenges, we propose a Hypergraph-Enhanced DuAL framework named HEAL for semi-supervised graph classification, which captures graph semantics from the perspective of the hypergraph and the line graph, respectively. Specifically, to better explore the higher-order relationships among nodes, we design a hypergraph structure learning to adaptively learn complex node dependencies beyond pairwise relations. Meanwhile, based on the learned hypergraph, we introduce a line graph to capture the interaction between hyperedges, thereby better mining the underlying semantic structures. Finally, we develop a relational consistency learning to facilitate knowledge transfer between the two branches and provide better mutual guidance. Extensive experiments on real-world graph datasets verify the effectiveness of the proposed method against existing state-of-the-art methods.
Authors: Amrita Bhattacharjee, Raha Moraffah, Joshua Garland, Huan Liu
Abstract: Counterfactual examples are frequently used for model development and evaluation in many natural language processing (NLP) tasks. Although methods for automated counterfactual generation have been explored, such methods depend on models such as pre-trained language models that are then fine-tuned on auxiliary, often task-specific datasets. Collecting and annotating such datasets for counterfactual generation is labor intensive and therefore, infeasible in practice. Therefore, in this work, we focus on a novel problem setting: \textit{zero-shot counterfactual generation}. To this end, we propose a structured way to utilize large language models (LLMs) as general purpose counterfactual example generators. We hypothesize that the instruction-following and textual understanding capabilities of recent LLMs can be effectively leveraged for generating high quality counterfactuals in a zero-shot manner, without requiring any training or fine-tuning. Through comprehensive experiments on various downstream tasks in natural language processing (NLP), we demonstrate the efficacy of LLMs as zero-shot counterfactual generators in evaluating and explaining black-box NLP models.
Authors: Yide Shentu, Philipp Wu, Aravind Rajeswaran, Pieter Abbeel
Abstract: Hierarchical control for robotics has long been plagued by the need to have a well defined interface layer to communicate between high-level task planners and low-level policies. With the advent of LLMs, language has been emerging as a prospective interface layer. However, this has several limitations. Not all tasks can be decomposed into steps that are easily expressible in natural language (e.g. performing a dance routine). Further, it makes end-to-end finetuning on embodied data challenging due to domain shift and catastrophic forgetting. We introduce our method -- Learnable Latent Codes as Bridges (LCB) -- as an alternate architecture to overcome these limitations. \method~uses a learnable latent code to act as a bridge between LLMs and low-level policies. This enables LLMs to flexibly communicate goals in the task plan without being entirely constrained by language limitations. Additionally, it enables end-to-end finetuning without destroying the embedding space of word tokens learned during pre-training. Through experiments on Language Table and Calvin, two common language based benchmarks for embodied agents, we find that \method~outperforms baselines (including those w/ GPT-4V) that leverage pure language as the interface layer on tasks that require reasoning and multi-step behaviors.
Authors: Baoming Chang, Amin Kamali, Verena Kantere
Abstract: Learning representations for query plans play a pivotal role in machine learning-based query optimizers of database management systems. To this end, particular model architectures are proposed in the literature to convert the tree-structured query plans into representations with formats learnable by downstream machine learning models. However, existing research rarely compares and analyzes the query plan representation capabilities of these tree models and their direct impact on the performance of the overall optimizer. To address this problem, we perform a comparative study to explore the effect of using different state-of-the-art tree models on the optimizer's cost estimation and plan selection performance in relatively complex workloads. Additionally, we explore the possibility of using graph neural networks (GNN) in the query plan representation task. We propose a novel tree model combining directed GNN with Gated Recurrent Units (GRU) and demonstrate experimentally that the new tree model provides significant improvements to cost estimation tasks and relatively excellent plan selection performance compared to the state-of-the-art tree models.
Authors: Dawei Li, Shu Yang, Zhen Tan, Jae Young Baik, Sunkwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen
Abstract: Recent advancements in large language models (LLMs) have achieved promising performances across various applications. Nonetheless, the ongoing challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains. In this work, we introduce DALK, a.k.a. Dynamic Co-Augmentation of LLMs and KG, to address this limitation and demonstrate its ability on studying Alzheimer's Disease (AD), a specialized sub-field in biomedicine and a global health priority. With a synergized framework of LLM and KG mutually enhancing each other, we first leverage LLM to construct an evolving AD-specific knowledge graph (KG) sourced from AD-related scientific literature, and then we utilize a coarse-to-fine sampling method with a novel self-aware knowledge retrieval approach to select appropriate knowledge from the KG to augment LLM inference capabilities. The experimental results, conducted on our constructed AD question answering (ADQA) benchmark, underscore the efficacy of DALK. Additionally, we perform a series of detailed analyses that can offer valuable insights and guidelines for the emerging topic of mutually enhancing KG and LLM. We will release the code and data at https://github.com/David-Li0406/DALK.
Authors: Yikuan Xia, Jiazun Chen, Xinchi Li, Jun Gao
Abstract: Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language models (PLMs), including the recent PromptEM model, effectively addresses the challenges of low-resource GEM in practical applications, offering a robust solution when labeled data is scarce. However, existing prompt tuning models for GEM face the challenges of prompt design and information gap. This paper introduces an augmented prompt tuning framework for the challenges, which consists of two main improvements. The first is an augmented contextualized soft token-based prompt tuning method that extracts a guiding soft token benefit for the PLMs' prompt tuning, and the second is a cost-effective information augmentation strategy leveraging large language models (LLMs). Our approach performs well on the low-resource GEM challenges. Extensive experiments show promising advancements of our basic model without information augmentation over existing methods based on moderate-size PLMs (average 5.24%+), and our model with information augmentation achieves comparable performance compared with fine-tuned LLMs, using less than 14% of the API fee.
Authors: Shuo Shao, Yiming Li, Hongwei Yao, Yiling He, Zhan Qin, Kui Ren
Abstract: Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including harmfulness and ambiguity. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity. In this paper, we argue that both limitations stem from the `zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.
Authors: Huy Quang Ung, Hao Niu, Minh-Son Dao, Shinya Wada, Atsunori Minamikawa
Abstract: Traffic predictions play a crucial role in intelligent transportation systems. The rapid development of IoT devices allows us to collect different kinds of data with high correlations to traffic predictions, fostering the development of efficient multi-modal traffic prediction models. Until now, there are few studies focusing on utilizing advantages of multi-modal data for traffic predictions. In this paper, we introduce a novel temporal attentive cross-modality transformer model for long-term traffic predictions, namely xMTrans, with capability of exploring the temporal correlations between the data of two modalities: one target modality (for prediction, e.g., traffic congestion) and one support modality (e.g., people flow). We conducted extensive experiments to evaluate our proposed model on traffic congestion and taxi demand predictions using real-world datasets. The results showed the superiority of xMTrans against recent state-of-the-art methods on long-term traffic predictions. In addition, we also conducted a comprehensive ablation study to further analyze the effectiveness of each module in xMTrans.
Authors: Yitian Li, Jidong Tian, Hao He, Yaohui Jin
Abstract: Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability to make logical reasoning. In this work, we focus on the effectiveness of the prompt-based methods on first-order logical reasoning and find that the bottleneck lies in logical negation. Based on our analysis, logical negation tends to result in spurious correlations to negative answers, while propositions without logical negation correlate to positive answers. To solve the problem, we propose a simple but effective method, Negation Augmenting and Negation Debiasing (NAND), which introduces negative propositions to prompt-based methods without updating parameters. Specifically, these negative propositions can counteract spurious correlations by providing "not" for all instances so that models cannot make decisions only by whether expressions contain a logical negation. Experiments on three datasets show that NAND not only solves the problem of calibrating logical negation but also significantly enhances prompt-based methods of logical reasoning without model retraining.
Authors: Jiarong Yang, Yuan Liu
Abstract: Split Federated Learning (SFL) is a distributed machine learning framework which strategically divides the learning process between a server and clients and collaboratively trains a shared model by aggregating local models updated based on data from distributed clients. However, data heterogeneity and partial client participation result in label distribution skew, which severely degrades the learning performance. To address this issue, we propose SFL with Concatenated Activations and Logit Adjustments (SCALA). Specifically, the activations from the client-side models are concatenated as the input of the server-side model so as to centrally adjust label distribution across different clients, and logit adjustments of loss functions on both server-side and client-side models are performed to deal with the label distribution variation across different subsets of participating clients. Theoretical analysis and experimental results verify the superiority of the proposed SCALA on public datasets.
Authors: Yuankun Xie, Yi Lu, Ruibo Fu, Zhengqi Wen, Zhiyong Wang, Jianhua Tao, Xin Qi, Xiaopeng Wang, Yukun Liu, Haonan Cheng, Long Ye, Yi Sun
Abstract: With the proliferation of Audio Language Model (ALM) based deepfake audio, there is an urgent need for effective detection methods. Unlike traditional deepfake audio generation, which often involves multi-step processes culminating in vocoder usage, ALM directly utilizes neural codec methods to decode discrete codes into audio. Moreover, driven by large-scale data, ALMs exhibit remarkable robustness and versatility, posing a significant challenge to current audio deepfake detection (ADD) models. To effectively detect ALM-based deepfake audio, we focus on the mechanism of the ALM-based audio generation method, the conversion from neural codec to waveform. We initially construct the Codecfake dataset, an open-source large-scale dataset, including two languages, millions of audio samples, and various test conditions, tailored for ALM-based audio detection. Additionally, to achieve universal detection of deepfake audio and tackle domain ascent bias issue of original SAM, we propose the CSAM strategy to learn a domain balanced and generalized minima. Experiment results demonstrate that co-training on Codecfake dataset and vocoded dataset with CSAM strategy yield the lowest average Equal Error Rate (EER) of 0.616% across all test conditions compared to baseline models.
Authors: Zehan Wang, Ziang Zhang, Xize Cheng, Rongjie Huang, Luping Liu, Zhenhui Ye, Haifeng Huang, Yang Zhao, Tao Jin, Peng Gao, Zhou Zhao
Abstract: Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting problems make it challenging to further enhance pre-trained unified spaces. In this work, we propose Molecule-Space, an idea that treats multimodal representation spaces as "molecules", and augments pre-trained unified space by integrating knowledge from extra expert spaces via "molecules space reactions". Specifically, we introduce two kinds of basic space reactions: 1) Space Displacement Reaction and 2) Space Combination Reaction. Based on these defined basic reactions, we design Complex Sequential & Parallel Reactions to effectively integrate multiple spaces simultaneously. Benefiting from the modularization concept, we further propose a coarse-to-fine customized inference strategy to flexibly adjust the enhanced unified space for different purposes. Experimentally, we fuse the audio-image-text space of ImageBind with the image-text and audio-text expert spaces. The resulting space outperforms ImageBind on 5 downstream tasks across 9 datasets. Moreover, via customized inference, it even surpasses the used image-text and audio-text expert spaces.
Authors: Ivan Bili\'c, Filip Mari\'c, Fabio Bonsignorio, Ivan Petrovi\'c
Abstract: For autonomous robotics applications, it is crucial that robots are able to accurately measure their potential state and perceive their environment, including other agents within it (e.g., cobots interacting with humans). The redundancy of these measurements is important, as it allows for planning and execution of recovery protocols in the event of sensor failure or external disturbances. Visual estimation can provide this redundancy through the use of low-cost sensors and server as a standalone source of proprioception when no encoder-based sensing is available. Therefore, we estimate the configuration of the robot jointly with its pose, which provides a complete spatial understanding of the observed robot. We present GISR - a method for deep configuration and robot-to-camera pose estimation that prioritizes real-time execution. GISR is comprised of two modules: (i) a geometric initialization module, efficiently computing an approximate robot pose and configuration, and (ii) an iterative silhouette-based refinement module that refines the initial solution in only a few iterations. We evaluate our method on a publicly available dataset and show that GISR performs competitively with existing state-of-the-art approaches, while being significantly faster compared to existing methods of the same class. Our code is available at https://github.com/iwhitey/GISR-robot.
Authors: Paul Jideani, Aurona Gerber
Abstract: Recent social media posts on the cholera outbreak in Hammanskraal have highlighted the diverse range of emotions people experienced in response to such an event. The extent of people's opinions varies greatly depending on their level of knowledge and information about the disease. The documented re-search about Cholera lacks investigations into the classification of emotions. This study aims to examine the emotions expressed in social media posts about Chol-era. A dataset of 23,000 posts was extracted and pre-processed. The Python Nat-ural Language Toolkit (NLTK) sentiment analyzer library was applied to deter-mine the emotional significance of each text. Additionally, Machine Learning (ML) models were applied for emotion classification, including Long short-term memory (LSTM), Logistic regression, Decision trees, and the Bidirectional En-coder Representations from Transformers (BERT) model. The results of this study demonstrated that LSTM achieved the highest accuracy of 75%. Emotion classification presents a promising tool for gaining a deeper understanding of the impact of Cholera on society. The findings of this study might contribute to the development of effective interventions in public health strategies.
Authors: Zhengxing Lan, Hongbo Li, Lingshan Liu, Bo Fan, Yisheng Lv, Yilong Ren, Zhiyong Cui
Abstract: Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents' past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features into a form that LLMs understand. On this basis, we innovatively explore LLMs' powerful comprehension abilities to capture a spectrum of high-level scene knowledge and interactive information. Emulating the human-like lane focus cognitive function and enhancing Traj-LLM's scene comprehension, we introduce lane-aware probabilistic learning powered by the pioneering Mamba module. Finally, a multi-modal Laplace decoder is designed to achieve scene-compliant multi-modal predictions. Extensive experiments manifest that Traj-LLM, fortified by LLMs' strong prior knowledge and understanding prowess, together with lane-aware probability learning, outstrips state-of-the-art methods across evaluation metrics. Moreover, the few-shot analysis further substantiates Traj-LLM's performance, wherein with just 50% of the dataset, it outperforms the majority of benchmarks relying on complete data utilization. This study explores equipping the trajectory prediction task with advanced capabilities inherent in LLMs, furnishing a more universal and adaptable solution for forecasting agent motion in a new way.
Authors: Haichen Zhou, Yixiong Zou, Ruixuan Li, Yuhua Li, Kui Xiao
Abstract: Few-shot class-incremental learning (FSCIL) aims to acquire knowledge from novel classes with limited samples while retaining information about base classes. Existing methods address catastrophic forgetting and overfitting by freezing the feature extractor during novel-class learning. However, these methods usually tend to cause the confusion between base and novel classes, i.e., classifying novel-class samples into base classes. In this paper, we delve into this phenomenon to study its cause and solution. We first interpret the confusion as the collision between the novel-class and the base-class region in the feature space. Then, we find the collision is caused by the label-irrelevant redundancies within the base-class feature and pixel space. Through qualitative and quantitative experiments, we identify this redundancy as the shortcut in the base-class training, which can be decoupled to alleviate the collision. Based on this analysis, to alleviate the collision between base and novel classes, we propose a method for FSCIL named Redundancy Decoupling and Integration (RDI). RDI first decouples redundancies from base-class space to shrink the intra-base-class feature space. Then, it integrates the redundancies as a dummy class to enlarge the inter-base-class feature space. This process effectively compresses the base-class feature space, creating buffer space for novel classes and alleviating the model's confusion between the base and novel classes. Extensive experiments across benchmark datasets, including CIFAR-100, miniImageNet, and CUB-200-2011 demonstrate that our method achieves state-of-the-art performance.
Authors: Alan A. Lahoud, Erik Schaffernicht, Johannes A. Stork
Abstract: Learning latent costs of transitions on graphs from trajectories demonstrations under various contextual features is challenging but useful for path planning. Yet, existing methods either oversimplify cost assumptions or scale poorly with the number of observed trajectories. This paper introduces DataSP, a differentiable all-to-all shortest path algorithm to facilitate learning latent costs from trajectories. It allows to learn from a large number of trajectories in each learning step without additional computation. Complex latent cost functions from contextual features can be represented in the algorithm through a neural network approximation. We further propose a method to sample paths from DataSP in order to reconstruct/mimic observed paths' distributions. We prove that the inferred distribution follows the maximum entropy principle. We show that DataSP outperforms state-of-the-art differentiable combinatorial solver and classical machine learning approaches in predicting paths on graphs.
Authors: Yunxin Li, Baotian Hu, Haoyuan Shi, Wei Wang, Longyue Wang, Min Zhang
Abstract: Large Multimodal Models (LMMs) have achieved impressive success in visual understanding and reasoning, remarkably improving the performance of mathematical reasoning in a visual context. Yet, a challenging type of visual math lies in the multimodal graph theory problem, which demands that LMMs understand the graphical structures accurately and perform multi-step reasoning on the visual graph. Additionally, exploring multimodal graph theory problems will lead to more effective strategies in fields like biology, transportation, and robotics planning. To step forward in this direction, we are the first to design a benchmark named VisionGraph, used to explore the capabilities of advanced LMMs in solving multimodal graph theory problems. It encompasses eight complex graph problem tasks, from connectivity to shortest path problems. Subsequently, we present a Description-Program-Reasoning (DPR) chain to enhance the logical accuracy of reasoning processes through graphical structure description generation and algorithm-aware multi-step reasoning. Our extensive study shows that 1) GPT-4V outperforms Gemini Pro in multi-step graph reasoning; 2) All LMMs exhibit inferior perception accuracy for graphical structures, whether in zero/few-shot settings or with supervised fine-tuning (SFT), which further affects problem-solving performance; 3) DPR significantly improves the multi-step graph reasoning capabilities of LMMs and the GPT-4V (DPR) agent achieves SOTA performance.
Authors: Yan Liu, Yazheng Yang, Xiaokang Chen
Abstract: Long text understanding is important yet challenging for natural language processing. A long article or document usually contains many redundant words that are not pertinent to its gist and sometimes can be regarded as noise. With recent advances of abstractive summarization, we propose our \emph{Gist Detector} to leverage the gist detection ability of a summarization model and integrate the extracted gist into downstream models to enhance their long text understanding ability. Specifically, Gist Detector first learns the gist detection knowledge distilled from a summarization model, and then produces gist-aware representations to augment downstream models. We evaluate our method on three different tasks: long document classification, distantly supervised open-domain question answering, and non-parallel text style transfer. The experimental results show that our method can significantly improve the performance of baseline models on all tasks.
Authors: Nikolaos Giakoumoglou, Tania Stathaki
Abstract: In the field of computer vision, self-supervised learning has emerged as a method to extract robust features from unlabeled data, where models derive labels autonomously from the data itself, without the need for manual annotation. This paper provides a comprehensive review of discriminative approaches of self-supervised learning within the domain of computer vision, examining their evolution and current status. Through an exploration of various methods including contrastive, self-distillation, knowledge distillation, feature decorrelation, and clustering techniques, we investigate how these approaches leverage the abundance of unlabeled data. Finally, we have comparison of self-supervised learning methods on the standard ImageNet classification benchmark.
Authors: Felix Haag, Carlo Stingl, Katrin Zerfass, Konstantin Hopf, Thorsten Staake
Abstract: Information systems (IS) are frequently designed to leverage the negative effect of anchoring bias to influence individuals' decision-making (e.g., by manipulating purchase decisions). Recent advances in Artificial Intelligence (AI) and the explanations of its decisions through explainable AI (XAI) have opened new opportunities for mitigating biased decisions. So far, the potential of these technological advances to overcome anchoring bias remains widely unclear. To this end, we conducted two online experiments with a total of N=390 participants in the context of purchase decisions to examine the impact of AI and XAI-based decision support on anchoring bias. Our results show that AI alone and its combination with XAI help to mitigate the negative effect of anchoring bias. Ultimately, our findings have implications for the design of AI and XAI-based decision support and IS to overcome cognitive biases.
Authors: Keqiang Fan, Xiaohao Cai, Mahesan Niranjan
Abstract: Diffusion probabilistic models (DPMs) have exhibited significant effectiveness in computer vision tasks, particularly in image generation. However, their notable performance heavily relies on labelled datasets, which limits their application in medical images due to the associated high-cost annotations. Current DPM-related methods for lesion detection in medical imaging, which can be categorized into two distinct approaches, primarily rely on image-level annotations. The first approach, based on anomaly detection, involves learning reference healthy brain representations and identifying anomalies based on the difference in inference results. In contrast, the second approach, resembling a segmentation task, employs only the original brain multi-modalities as prior information for generating pixel-level annotations. In this paper, our proposed model - discrepancy distribution medical diffusion (DDMD) - for lesion detection in brain MRI introduces a novel framework by incorporating distinctive discrepancy features, deviating from the conventional direct reliance on image-level annotations or the original brain modalities. In our method, the inconsistency in image-level annotations is translated into distribution discrepancies among heterogeneous samples while preserving information within homogeneous samples. This property retains pixel-wise uncertainty and facilitates an implicit ensemble of segmentation, ultimately enhancing the overall detection performance. Thorough experiments conducted on the BRATS2020 benchmark dataset containing multimodal MRI scans for brain tumour detection demonstrate the great performance of our approach in comparison to state-of-the-art methods.
Authors: Kristupas Bajarunas, Marcia L. Baptista, Kai Goebel, Manuel A. Chao
Abstract: Accurately estimating a Health Index (HI) from condition monitoring data (CM) is essential for reliable and interpretable prognostics and health management (PHM) in complex systems. In most scenarios, complex systems operate under varying operating conditions and can exhibit different fault modes, making unsupervised inference of an HI from CM data a significant challenge. Hybrid models combining prior knowledge about degradation with deep learning models have been proposed to overcome this challenge. However, previously suggested hybrid models for HI estimation usually rely heavily on system-specific information, limiting their transferability to other systems. In this work, we propose an unsupervised hybrid method for HI estimation that integrates general knowledge about degradation into the convolutional autoencoder's model architecture and learning algorithm, enhancing its applicability across various systems. The effectiveness of the proposed method is demonstrated in two case studies from different domains: turbofan engines and lithium batteries. The results show that the proposed method outperforms other competitive alternatives, including residual-based methods, in terms of HI quality and their utility for Remaining Useful Life (RUL) predictions. The case studies also highlight the comparable performance of our proposed method with a supervised model trained with HI labels.
Authors: Zijia Wang, Zhi-Song Liu
Abstract: We present StyleMamba, an efficient image style transfer framework that translates text prompts into corresponding visual styles while preserving the content integrity of the original images. Existing text-guided stylization requires hundreds of training iterations and takes a lot of computing resources. To speed up the process, we propose a conditional State Space Model for Efficient Text-driven Image Style Transfer, dubbed StyleMamba, that sequentially aligns the image features to the target text prompts. To enhance the local and global style consistency between text and image, we propose masked and second-order directional losses to optimize the stylization direction to significantly reduce the training iterations by 5 times and the inference time by 3 times. Extensive experiments and qualitative evaluation confirm the robust and superior stylization performance of our methods compared to the existing baselines.
Authors: Zine el abidine Kherroubi
Abstract: Current autonomous driving systems heavily rely on V2X communication data to enhance situational awareness and the cooperation between vehicles. However, a major challenge when using V2X data is that it may not be available periodically because of unpredictable delays and data loss during wireless transmission between road stations and the receiver vehicle. This issue should be considered when designing control strategies for connected and autonomous vehicles. Therefore, this paper proposes a novel 'Blind Actor-Critic' algorithm that guarantees robust driving performance in V2X environment with delayed and/or lost data. The novel algorithm incorporates three key mechanisms: a virtual fixed sampling period, a combination of Temporal-Difference and Monte Carlo learning, and a numerical approximation of immediate reward values. To address the temporal aperiodicity problem of V2X data, we first illustrate this challenge. Then, we provide a detailed explanation of the Blind Actor-Critic algorithm where we highlight the proposed components to compensate for the temporal aperiodicity problem of V2X data. We evaluate the performance of our algorithm in a simulation environment and compare it to benchmark approaches. The results demonstrate that training metrics are improved compared to conventional actor-critic algorithms. Additionally, testing results show that our approach provides robust control, even under low V2X network reliability levels.
Authors: Helena A. Haxvig
Abstract: This position paper explores the benefits, drawbacks, and ethical considerations of incorporating synthetic personae in HCI research, particularly focusing on the customization challenges beyond the limitations of current Large Language Models (LLMs). These perspectives are derived from the initial results of a sub-study employing vignettes to showcase the existence of bias within black-box LLMs and explore methods for manipulating them. The study aims to establish a foundation for understanding the challenges associated with these models, emphasizing the necessity of thorough testing before utilizing them to create synthetic personae for HCI research.
Authors: Weijia Zhang, Vaishali Pal, Jia-Hong Huang, Evangelos Kanoulas, Maarten de Rijke
Abstract: Table summarization is a crucial task aimed at condensing information from tabular data into concise and comprehensible textual summaries. However, existing approaches often fall short of adequately meeting users' information and quality requirements and tend to overlook the complexities of real-world queries. In this paper, we propose a novel method to address these limitations by introducing query-focused multi-table summarization. Our approach, which comprises a table serialization module, a summarization controller, and a large language model (LLM), utilizes textual queries and multiple tables to generate query-dependent table summaries tailored to users' information needs. To facilitate research in this area, we present a comprehensive dataset specifically tailored for this task, consisting of 4909 query-summary pairs, each associated with multiple tables. Through extensive experiments using our curated dataset, we demonstrate the effectiveness of our proposed method compared to baseline approaches. Our findings offer insights into the challenges of complex table reasoning for precise summarization, contributing to the advancement of research in query-focused multi-table summarization.
Authors: Chuanbo Hu, Jacob Thrasher, Wenqi Li, Mindi Ruan, Xiangxu Yu, Lynn K Paul, Shuo Wang, Xin Li
Abstract: Diagnosing autism spectrum disorder (ASD) by identifying abnormal speech patterns from examiner-patient dialogues presents significant challenges due to the subtle and diverse manifestations of speech-related symptoms in affected individuals. This study presents a comprehensive approach to identify distinctive speech patterns through the analysis of examiner-patient dialogues. Utilizing a dataset of recorded dialogues, we extracted 40 speech-related features, categorized into frequency, zero-crossing rate, energy, spectral characteristics, Mel Frequency Cepstral Coefficients (MFCCs), and balance. These features encompass various aspects of speech such as intonation, volume, rhythm, and speech rate, reflecting the complex nature of communicative behaviors in ASD. We employed machine learning for both classification and regression tasks to analyze these speech features. The classification model aimed to differentiate between ASD and non-ASD cases, achieving an accuracy of 87.75%. Regression models were developed to predict speech pattern related variables and a composite score from all variables, facilitating a deeper understanding of the speech dynamics associated with ASD. The effectiveness of machine learning in interpreting intricate speech patterns and the high classification accuracy underscore the potential of computational methods in supporting the diagnostic processes for ASD. This approach not only aids in early detection but also contributes to personalized treatment planning by providing insights into the speech and communication profiles of individuals with ASD.
Authors: Ming Kuo, Shouvon Sarker, Lijun Qian, Yujian Fu, Xiangfang Li, Xishuang Dong
Abstract: In contrast to pedagogies like evidence-based teaching, personalized adaptive learning (PAL) distinguishes itself by closely monitoring the progress of individual students and tailoring the learning path to their unique knowledge and requirements. A crucial technique for effective PAL implementation is knowledge tracing, which models students' evolving knowledge to predict their future performance. Based on these predictions, personalized recommendations for resources and learning paths can be made to meet individual needs. Recent advancements in deep learning have successfully enhanced knowledge tracking through Deep Knowledge Tracing (DKT). This paper introduces generative AI models to further enhance DKT. Generative AI models, rooted in deep learning, are trained to generate synthetic data, addressing data scarcity challenges in various applications across fields such as natural language processing (NLP) and computer vision (CV). This study aims to tackle data shortage issues in student learning records to enhance DKT performance for PAL. Specifically, it employs TabDDPM, a diffusion model, to generate synthetic educational records to augment training data for enhancing DKT. The proposed method's effectiveness is validated through extensive experiments on ASSISTments datasets. The experimental results demonstrate that the AI-generated data by TabDDPM significantly improves DKT performance, particularly in scenarios with small data for training and large data for testing.
Authors: Zhaoxing Li, Jujie Yang, Jindi Wang, Lei Shi, Sebastian Stein
Abstract: The field of Knowledge Tracing aims to understand how students learn and master knowledge over time by analyzing their historical behaviour data. To achieve this goal, many researchers have proposed Knowledge Tracing models that use data from Intelligent Tutoring Systems to predict students' subsequent actions. However, with the development of Intelligent Tutoring Systems, large-scale datasets containing long-sequence data began to emerge. Recent deep learning based Knowledge Tracing models face obstacles such as low efficiency, low accuracy, and low interpretability when dealing with large-scale datasets containing long-sequence data. To address these issues and promote the sustainable development of Intelligent Tutoring Systems, we propose a LSTM BERT-based Knowledge Tracing model for long sequence data processing, namely LBKT, which uses a BERT-based architecture with a Rasch model-based embeddings block to deal with different difficulty levels information and an LSTM block to process the sequential characteristic in students' actions. LBKT achieves the best performance on most benchmark datasets on the metrics of ACC and AUC. Additionally, an ablation study is conducted to analyse the impact of each component of LBKT's overall performance. Moreover, we used t-SNE as the visualisation tool to demonstrate the model's embedding strategy. The results indicate that LBKT is faster, more interpretable, and has a lower memory cost than the traditional deep learning based Knowledge Tracing methods.
Authors: Dariush Salami, Francesc Wilhelmi, Lorenzo Galati-Giordano, Mika Kasslin
Abstract: The increasing cloudification and softwarization of networks foster the interplay among multiple independently managed deployments. An appealing reason for such an interplay lies in distributed Machine Learning (ML), which allows the creation of robust ML models by leveraging collective intelligence and computational power. In this paper, we study the application of the two cornerstones of distributed learning, namely Federated Learning (FL) and Knowledge Distillation (KD), on the Wi-Fi Access Point (AP) load prediction use case. The analysis conducted in this paper is done on a dataset that contains real measurements from a large Wi-Fi campus network, which we use to train the ML model under study based on different strategies. Performance evaluation includes relevant aspects for the suitability of distributed learning operation in real use cases, including the predictive performance, the associated communication overheads, or the energy consumption. In particular, we prove that distributed learning can improve the predictive accuracy centralized ML solutions by up to 93% while reducing the communication overheads and the energy cost by 80%.
Authors: Thomas Trask
Abstract: The study in interaction patterns between students in on-campus and MOOC-style online courses has been broadly studied for the last 11 years. Yet there remains a gap in the literature comparing the habits of students completing the same course offered in both on-campus and MOOC-style online formats. This study will look at browser-based usage patterns for students in the Georgia Tech CS1301 edx course for both the online course offered to on-campus students and the MOOCstyle course offered to anyone to determine what, if any, patterns exist between the two cohorts.
Authors: Ahmed Kharrufa, Ian G Johnson
Abstract: Generative AI (GAI) is impacting teaching and learning directly or indirectly across a range of subjects and disciplines. As educators, we need to understand the potential and limitations of AI in HCI education and ensure our graduating HCI students are aware of the potential and limitations of AI in HCI. In this paper, we report on the main pedagogical insights gained from the inclusion of generative AI into a 10 week undergraduate module. We designed the module to encourage student experimentation with GAI models as part of the design brief requirement and planned practical sessions and discussions. Our insights are based on replies to a survey sent out to the students after completing the module. Our key findings, for HCI educators, report on the use of AI as a persona for developing project ideas and creating resources for design, and AI as a mirror for reflecting students' understanding of key concepts and ideas and highlighting knowledge gaps. We also discuss potential pitfalls that should be considered and the need to assess students' literacies and assumptions of GAIs as pedagogical tools. Finally, we put forward the case for educators to take the opportunities GAI presents as an educational tool and be experimental, creative, and courageous in their practice. We end with a discussion of our findings in relation to the TPACK framework in HCI.
Authors: Hengyue Liang, Le Peng, Ju Sun
Abstract: In selective classification (SC), a classifier abstains from making predictions that are likely to be wrong to avoid excessive errors. To deploy imperfect classifiers -- imperfect either due to intrinsic statistical noise of data or for robustness issue of the classifier or beyond -- in high-stakes scenarios, SC appears to be an attractive and necessary path to follow. Despite decades of research in SC, most previous SC methods still focus on the ideal statistical setting only, i.e., the data distribution at deployment is the same as that of training, although practical data can come from the wild. To bridge this gap, in this paper, we propose an SC framework that takes into account distribution shifts, termed generalized selective classification, that covers label-shifted (or out-of-distribution) and covariate-shifted samples, in addition to typical in-distribution samples, the first of its kind in the SC literature. We focus on non-training-based confidence-score functions for generalized SC on deep learning (DL) classifiers and propose two novel margin-based score functions. Through extensive analysis and experiments, we show that our proposed score functions are more effective and reliable than the existing ones for generalized SC on a variety of classification tasks and DL classifiers.
Authors: Huaiyuan Xu, Junliang Chen, Shiyu Meng, Yi Wang, Lap-Pui Chau
Abstract: 3D occupancy perception technology aims to observe and understand dense 3D environments for autonomous vehicles. Owing to its comprehensive perception capability, this technology is emerging as a trend in autonomous driving perception systems, and is attracting significant attention from both industry and academia. Similar to traditional bird's-eye view (BEV) perception, 3D occupancy perception has the nature of multi-source input and the necessity for information fusion. However, the difference is that it captures vertical structures that are ignored by 2D BEV. In this survey, we review the most recent works on 3D occupancy perception, and provide in-depth analyses of methodologies with various input modalities. Specifically, we summarize general network pipelines, highlight information fusion techniques, and discuss effective network training. We evaluate and analyze the occupancy perception performance of the state-of-the-art on the most popular datasets. Furthermore, challenges and future research directions are discussed. We hope this report will inspire the community and encourage more research work on 3D occupancy perception. A comprehensive list of studies in this survey is available in an active repository that continuously collects the latest work: https://github.com/HuaiyuanXu/3D-Occupancy-Perception.
URLs: https://github.com/HuaiyuanXu/3D-Occupancy-Perception.
Authors: Inderjeet Nair, Lu Wang
Abstract: We study the task of conducting structured reasoning as generating a reasoning graph from natural language input using large language models (LLMs). Previous approaches have explored various prompting schemes, yet they suffer from error propagation due to the autoregressive nature and single-pass-based decoding, which lack error correction capability. Additionally, relying solely on a single sample may result in the omission of true nodes and edges. To counter this, we draw inspiration from self-consistency (SC), which involves sampling a diverse set of reasoning chains and taking the majority vote as the final answer. To tackle the substantial challenge of applying SC on generated graphs, we propose MIDGARD (MInimum Description length Guided Aggregation of Reasoning in Directed acyclic graph) that leverages Minimum Description Length (MDL)-based formulation to identify consistent properties among the different graph samples generated by an LLM. This formulation helps reject properties that appear in only a few samples, which are likely to be erroneous, while enabling the inclusion of missing elements without compromising precision. Our method demonstrates superior performance than comparisons across various structured reasoning tasks, including argument structure extraction, explanation graph generation, inferring dependency relations among actions for everyday tasks, and semantic graph generation from natural texts.
Authors: Jiuxiang Gu, Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Junze Yin
Abstract: Large Language Models (LLMs) have profoundly changed the world. Their self-attention mechanism is the key to the success of transformers in LLMs. However, the quadratic computational cost $O(n^2)$ to the length $n$ input sequence is the notorious obstacle for further improvement and scalability in the longer context. In this work, we leverage the convolution-like structure of attention matrices to develop an efficient approximation method for attention computation using convolution matrices. We propose a $\mathsf{conv}$ basis system, "similar" to the rank basis, and show that any lower triangular (attention) matrix can always be decomposed as a sum of $k$ structured convolution matrices in this basis system. We then design an algorithm to quickly decompose the attention matrix into $k$ convolution matrices. Thanks to Fast Fourier Transforms (FFT), the attention {\it inference} can be computed in $O(knd \log n)$ time, where $d$ is the hidden dimension. In practice, we have $ d \ll n$, i.e., $d=3,072$ and $n=1,000,000$ for Gemma. Thus, when $kd = n^{o(1)}$, our algorithm achieve almost linear time, i.e., $n^{1+o(1)}$. Furthermore, the attention {\it training forward} and {\it backward gradient} can be computed in $n^{1+o(1)}$ as well. Our approach can avoid explicitly computing the $n \times n$ attention matrix, which may largely alleviate the quadratic computational complexity. Furthermore, our algorithm works on any input matrices. This work provides a new paradigm for accelerating attention computation in transformers to enable their application to longer contexts.
Authors: You Zhang, Yongyi Zang, Jiatong Shi, Ryuichi Yamamoto, Jionghao Han, Yuxun Tang, Tomoki Toda, Zhiyao Duan
Abstract: The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry. Unlike spoken voice, singing voice presents unique challenges due to its musical nature and the presence of strong background music, making singing voice deepfake detection (SVDD) a specialized field requiring focused attention. To promote SVDD research, we recently proposed the "SVDD Challenge," the very first research challenge focusing on SVDD for lab-controlled and in-the-wild bonafide and deepfake singing voice recordings. The challenge will be held in conjunction with the 2024 IEEE Spoken Language Technology Workshop (SLT 2024).
Authors: Sean Noh, Ho-Chun Herbert Chang
Abstract: Powered by large language models (LLMs), AI agents have become capable of many human tasks. Using the most canonical definitions of the Big Five personality, we measure the ability of LLMs to negotiate within a game-theoretical framework, as well as methodological challenges to measuring notions of fairness and risk. Simulations (n=1,500) for both single-issue and multi-issue negotiation reveal increase in domain complexity with asymmetric issue valuations improve agreement rates but decrease surplus from aggressive negotiation. Through gradient-boosted regression and Shapley explainers, we find high openness, conscientiousness, and neuroticism are associated with fair tendencies; low agreeableness and low openness are associated with rational tendencies. Low conscientiousness is associated with high toxicity. These results indicate that LLMs may have built-in guardrails that default to fair behavior, but can be "jail broken" to exploit agreeable opponents. We also offer pragmatic insight in how negotiation bots can be designed, and a framework of assessing negotiation behavior based on game theory and computational social science.
Authors: Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj K. Jha, Yuchen Liu
Abstract: Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module heavily used in leading models. Existing works mainly adopt a retraining process to enhance DM efficiency. This is computationally expensive and not very scalable. To this end, we introduce the Attention-driven Training-free Efficient Diffusion Model (AT-EDM) framework that leverages attention maps to perform run-time pruning of redundant tokens, without the need for any retraining. Specifically, for single-denoising-step pruning, we develop a novel ranking algorithm, Generalized Weighted Page Rank (G-WPR), to identify redundant tokens, and a similarity-based recovery method to restore tokens for the convolution operation. In addition, we propose a Denoising-Steps-Aware Pruning (DSAP) approach to adjust the pruning budget across different denoising timesteps for better generation quality. Extensive evaluations show that AT-EDM performs favorably against prior art in terms of efficiency (e.g., 38.8% FLOPs saving and up to 1.53x speed-up over Stable Diffusion XL) while maintaining nearly the same FID and CLIP scores as the full model. Project webpage: https://atedm.github.io.
URLs: https://atedm.github.io.
Authors: Charles Koutcheme, Nicola Dainese, Sami Sarsa, Arto Hellas, Juho Leinonen, Paul Denny
Abstract: Large language models (LLMs) have shown great potential for the automatic generation of feedback in a wide range of computing contexts. However, concerns have been voiced around the privacy and ethical implications of sending student work to proprietary models. This has sparked considerable interest in the use of open source LLMs in education, but the quality of the feedback that such open models can produce remains understudied. This is a concern as providing flawed or misleading generated feedback could be detrimental to student learning. Inspired by recent work that has utilised very powerful LLMs, such as GPT-4, to evaluate the outputs produced by less powerful models, we conduct an automated analysis of the quality of the feedback produced by several open source models using a dataset from an introductory programming course. First, we investigate the viability of employing GPT-4 as an automated evaluator by comparing its evaluations with those of a human expert. We observe that GPT-4 demonstrates a bias toward positively rating feedback while exhibiting moderate agreement with human raters, showcasing its potential as a feedback evaluator. Second, we explore the quality of feedback generated by several leading open-source LLMs by using GPT-4 to evaluate the feedback. We find that some models offer competitive performance with popular proprietary LLMs, such as ChatGPT, indicating opportunities for their responsible use in educational settings.
Authors: Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto
Abstract: Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead, they focus on hallucinations responding to very specific question formats -- typically a multiple-choice response regarding a particular object or attribute -- which we term "Type II hallucinations". Additionally, such benchmarks often require external API calls to models which are subject to change. In practice, we observe that a reduction in Type II hallucinations does not lead to a reduction in Type I hallucinations but rather that the two forms of hallucinations are often anti-correlated. To address this, we propose THRONE, a novel object-based automatic framework for quantitatively evaluating Type I hallucinations in LVLM free-form outputs. We use public language models (LMs) to identify hallucinations in LVLM responses and compute informative metrics. By evaluating a large selection of recent LVLMs using public datasets, we show that an improvement in existing metrics do not lead to a reduction in Type I hallucinations, and that established benchmarks for measuring Type I hallucinations are incomplete. Finally, we provide a simple and effective data augmentation method to reduce Type I and Type II hallucinations as a strong baseline.
Authors: Sicen Liu, Xiaolong Wang, Xianbing Zhao, Hao Chen
Abstract: Medication recommendation is a fundamental yet crucial branch of healthcare that presents opportunities to assist physicians in making more accurate medication prescriptions for patients with complex health conditions. Previous studies have primarily focused on learning patient representation from electronic health records (EHR). While considering the clinical manifestations of the patient is important, incorporating domain-specific prior knowledge is equally significant in diagnosing the patient's health conditions. However, effectively integrating domain knowledge with the patient's clinical manifestations can be challenging, particularly when dealing with complex clinical manifestations. Therefore, in this paper, we first identify comprehensive domain-specific prior knowledge, namely the Unified Medical Language System (UMLS), which is a comprehensive repository of biomedical vocabularies and standards, for knowledge extraction. Subsequently, we propose a knowledge injection module that addresses the effective integration of domain knowledge with complex clinical manifestations, enabling an effective characterization of the health conditions of the patient. Furthermore, considering the significant impact of a patient's medication history on their current medication, we introduce a historical medication-aware patient representation module to capture the longitudinal influence of historical medication information on the representation of current patients. Extensive experiments on three publicly benchmark datasets verify the superiority of our proposed method, which outperformed other methods by a significant margin. The code is available at: https://github.com/sherry6247/DKINet.
Authors: Zoe Porter, Philippa Ryan, Phillip Morgan, Joanna Al-Qaddoumi, Bernard Twomey, John McDermid, Ibrahim Habli
Abstract: It is widely acknowledged that we need to establish where responsibility lies for the outputs and impacts of AI-enabled systems. But without a clear and precise understanding of what "responsibility" means, deliberations about where responsibility lies will be, at best, unfocused and incomplete and, at worst, misguided. To address this concern, this paper draws upon central distinctions in philosophy and law to clarify the concept of responsibility for AI for policymakers, practitioners, researchers and students from non-philosophical and non-legal backgrounds. Taking the three-part formulation "Actor A is responsible for Occurrence O," the paper unravels the concept of responsibility to clarify that there are different possibilities of who is responsible for AI, the senses in which they are responsible, and aspects of events they are responsible for. Criteria and conditions for fitting attributions of responsibility in the core senses (causal responsibility, role-responsibility, liability responsibility and moral responsibility) are articulated to promote an understanding of when responsibility attributions would be inappropriate or unjust. The analysis is presented with a graphical notation to facilitate informal diagrammatic reasoning and discussion about specific cases. It is illustrated by application to a scenario of a fatal collision between an autonomous AI-enabled ship and a traditional, crewed vessel at sea.
Authors: Ming Li, Ariunaa Enkhtur, Fei Cheng, Beverley Anne Yamamoto
Abstract: This scoping review explores the ethical challenges of using ChatGPT in higher education. By reviewing recent academic articles in English, Chinese, and Japanese, we aimed to provide a deep dive review and identify gaps in the literature. Drawing on Arksey and O'Malley's (2005) scoping review framework, we defined search terms and identified relevant publications from four databases in the three target languages. The research results showed that the majority of the papers were discussion papers, but there was some early empirical work. The ethical issues highlighted in these works mainly concern academic integrity, assessment issues, and data protection. Given the rapid deployment of generative artificial intelligence, it is imperative for educators to conduct more empirical studies to develop sound ethical policies for its use.
Authors: Can Cui, Zichong Yang, Yupeng Zhou, Yunsheng Ma, Juanwu Lu, Lingxi Li, Yaobin Chen, Jitesh Panchal, Ziran Wang
Abstract: Integrating large language models (LLMs) in autonomous vehicles enables conversation with AI systems to drive the vehicle. However, it also emphasizes the requirement for such systems to comprehend commands accurately and achieve higher-level personalization to adapt to the preferences of drivers or passengers over a more extended period. In this paper, we introduce an LLM-based framework, Talk2Drive, capable of translating natural verbal commands into executable controls and learning to satisfy personal preferences for safety, efficiency, and comfort with a proposed memory module. This is the first-of-its-kind multi-scenario field experiment that deploys LLMs on a real-world autonomous vehicle. Experiments showcase that the proposed system can comprehend human intentions at different intuition levels, ranging from direct commands like "can you drive faster" to indirect commands like "I am really in a hurry now". Additionally, we use the takeover rate to quantify the trust of human drivers in the LLM-based autonomous driving system, where Talk2Drive significantly reduces the takeover rate in highway, intersection, and parking scenarios. We also validate that the proposed memory module considers personalized preferences and further reduces the takeover rate by up to 65.2% compared with those without a memory module. The experiment video can be watched at https://www.youtube.com/watch?v=4BWsfPaq1Ro
Authors: Paul Friedrich, Yulun Zhang, Michael Curry, Ludwig Dierks, Stephen McAleer, Jiaoyang Li, Tuomas Sandholm, Sven Seuken
Abstract: Multi-Agent Path Finding (MAPF) involves determining paths for multiple agents to travel simultaneously and collision-free through a shared area toward given goal locations. This problem is computationally complex, especially when dealing with large numbers of agents, as is common in realistic applications like autonomous vehicle coordination. Finding an optimal solution is often computationally infeasible, making the use of approximate, suboptimal algorithms essential. Adding to the complexity, agents might act in a self-interested and strategic way, possibly misrepresenting their goals to the MAPF algorithm if it benefits them. Although the field of mechanism design offers tools to align incentives, using these tools without careful consideration can fail when only having access to approximately optimal outcomes. In this work, we introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms. We test our mechanisms on realistic MAPF domains with problem sizes ranging from dozens to hundreds of agents. We find that they improve welfare beyond a simple baseline.
Authors: Sofiene Lassoued, Andreas Schwung
Abstract: Resource utilization and production process optimization are crucial for companies in today's competitive industrial landscape. Addressing the complexities of job shop scheduling problems (JSSP) is essential to improving productivity, reducing costs, and ensuring timely delivery. We propose PetriRL, a novel framework integrating Petri nets and deep reinforcement learning (DRL) for JSSP optimization. PetriRL capitalizes on the inherent strengths of Petri nets in modelling discrete event systems while leveraging the advantages of a graph structure. The Petri net governs automated components of the process, ensuring adherence to JSSP constraints. This allows for synergistic collaboration with optimization algorithms such as DRL, particularly in critical decision-making. Unlike traditional methods, PetriRL eliminates the need to preprocess JSSP instances into disjunctive graphs and enhances the explainability of process status through its graphical structure based on places and transitions. Additionally, the inherent graph structure of Petri nets enables the dynamic additions of job operations during the inference phase without requiring agent retraining, thus enhancing flexibility. Experimental results demonstrate PetriRL's robust generalization across various instance sizes and its competitive performance on public test benchmarks and randomly generated instances. Results are compared to a wide range of optimization solutions such as heuristics, metaheuristics, and learning-based algorithms. Finally, the added values of the framework's key elements, such as event-based control and action masking, are studied in the ablation study.
Authors: Tyler Bikaun, Michael Stewart, Wei Liu
Abstract: This paper presents CleanGraph, an interactive web-based tool designed to facilitate the refinement and completion of knowledge graphs. Maintaining the reliability of knowledge graphs, which are grounded in high-quality and error-free facts, is crucial for real-world applications such as question-answering and information retrieval systems. These graphs are often automatically assembled from textual sources by extracting semantic triples via information extraction. However, assuring the quality of these extracted triples, especially when dealing with large or low-quality datasets, can pose a significant challenge and adversely affect the performance of downstream applications. CleanGraph allows users to perform Create, Read, Update, and Delete (CRUD) operations on their graphs, as well as apply models in the form of plugins for graph refinement and completion tasks. These functionalities enable users to enhance the integrity and reliability of their graph data. A demonstration of CleanGraph and its source code can be accessed at https://github.com/nlp-tlp/CleanGraph under the MIT License.
Authors: Xuwei Tan, Yangming Zhou, MengChu Zhou, Zhang-Hua Fu
Abstract: Detecting critical nodes in sparse graphs is important in a variety of application domains, such as network vulnerability assessment, epidemic control, and drug design. The critical node problem (CNP) aims to find a set of critical nodes from a network whose deletion maximally degrades the pairwise connectivity of the residual network. Due to its general NP-hard nature, state-of-the-art CNP solutions are based on heuristic approaches. Domain knowledge and trial-and-error are usually required when designing such approaches, thus consuming considerable effort and time. This work proposes a feature importance-aware graph attention network for node representation and combines it with dueling double deep Q-network to create an end-to-end algorithm to solve CNP for the first time. It does not need any problem-specific knowledge or labeled datasets as required by most of existing methods. Once the model is trained, it can be generalized to cope with various types of CNPs (with different sizes and topological structures) without re-training. Computational experiments on 28 real-world networks show that the proposed method is highly comparable to state-of-the-art methods. It does not require any problem-specific knowledge and, hence, can be applicable to many applications including those impossible ones by using the existing approaches. It can be combined with some local search methods to further improve its solution quality. Extensive comparison results are given to show its effectiveness in solving CNP.
Authors: Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian
Abstract: With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former needs to tune numerous hyper-parameters for each scenario, and the latter limits the application of different types of RL algorithm and ignores the large energy consumption in training. To develop a robust spike-based RL method, we draw inspiration from non-spiking interneurons found in insects and propose the deep spiking Q-network (DSQN), using the membrane voltage of non-spiking neurons as the representation of Q-value, which can directly learn robust policies from high-dimensional sensory inputs using end-to-end RL. Experiments conducted on 17 Atari games demonstrate the DSQN is effective and even outperforms the ANN-based deep Q-network (DQN) in most games. Moreover, the experiments show superior learning stability and robustness to adversarial attacks of DSQN.
Authors: Xin Liu, Wei Tao, Wei Li, Dazhi Zhan, Jun Wang, Zhisong Pan
Abstract: Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural network is non-convex, recent research has proved that the first-order method is capable of attaining a global minimum during training over-parameterized neural networks, where the number of parameters is significantly larger than that of training instances. Momentum methods, including the heavy ball (HB) method and Nesterov's accelerated gradient (NAG) method, are the workhorse of first-order gradient methods owning to their accelerated convergence. In practice, NAG often exhibits superior performance than HB. However, current theoretical works fail to distinguish their convergence difference in training neural networks. To fill this gap, we consider the training problem of the two-layer ReLU neural network under over-parameterization and random initialization. Leveraging high-resolution dynamical systems and neural tangent kernel (NTK) theory, our result not only establishes tighter upper bounds of the convergence rate for both HB and NAG, but also provides the first theoretical guarantee for the acceleration of NAG over HB in training neural networks. Finally, we validate our theoretical results on three benchmark datasets.
Authors: Pedram Agand, Michael Chang, Mo Chen
Abstract: Utilizing a single camera for measuring object distances is a cost-effective alternative to stereo-vision and LiDAR. Although monocular distance estimation has been explored in the literature, most existing techniques rely on object class knowledge to achieve high performance. Without this contextual data, monocular distance estimation becomes more challenging, lacking reference points and object-specific cues. However, these cues can be misleading for objects with wide-range variation or adversarial situations, which is a challenging aspect of object-agnostic distance estimation. In this paper, we propose DMODE, a class-agnostic method for monocular distance estimation that does not require object class knowledge. DMODE estimates an object's distance by fusing its fluctuation in size over time with the camera's motion, making it adaptable to various object detectors and unknown objects, thus addressing these challenges. We evaluate our model on the KITTI MOTS dataset using ground-truth bounding box annotations and outputs from TrackRCNN and EagerMOT. The object's location is determined using the change in bounding box sizes and camera position without measuring the object's detection source or class attributes. Our approach demonstrates superior performance in multi-class object distance detection scenarios compared to conventional methods.
Authors: Chong Ma, Zihao Wu, Jiaqi Wang, Shaochen Xu, Yaonai Wei, Fang Zeng, Zhengliang Liu, Xi Jiang, Lei Guo, Xiaoyan Cai, Shu Zhang, Tuo Zhang, Dajiang Zhu, Dinggang Shen, Tianming Liu, Xiang Li
Abstract: The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians, and it is typically written by radiologists based on the 'Findings' section. However, writing numerous impressions can be laborious and error-prone for radiologists. Although recent studies have achieved promising results in automatic impression generation using large-scale medical text data for pre-training and fine-tuning pre-trained language models, such models often require substantial amounts of medical text data and have poor generalization performance. While large language models (LLMs) like ChatGPT have shown strong generalization capabilities and performance, their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, which leverages the in-context learning capability of LLMs by constructing dynamic contexts using domain-specific, individualized data. This dynamic prompt approach enables the model to learn contextual knowledge from semantically similar examples from existing data. Additionally, we design an iterative optimization algorithm that performs automatic evaluation on the generated impression results and composes the corresponding instruction prompts to further optimize the model. The proposed ImpressionGPT model achieves state-of-the-art performance on both MIMIC-CXR and OpenI datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains.
Authors: Fernando Zhapa-Camacho, Robert Hoehndorf
Abstract: Generating vector representations (embeddings) of OWL ontologies is a growing task due to its applications in predicting missing facts and knowledge-enhanced learning in fields such as bioinformatics. The underlying semantics of OWL ontologies is expressed using Description Logics (DLs). Initial approaches to generate embeddings relied on constructing a graph out of ontologies, neglecting the semantics of the logic therein. Recent semantic-preserving embedding methods often target lightweight DL languages like $\mathcal{EL}^{++}$, ignoring more expressive information in ontologies. Although some approaches aim to embed more descriptive DLs like $\mathcal{ALC}$, those methods require the existence of individuals, while many real-world ontologies are devoid of them. We propose an ontology embedding method for the $\mathcal{ALC}$ DL language that considers the lattice structure of concept descriptions. We use connections between DL and Category Theory to materialize the lattice structure and embed it using an order-preserving embedding method. We show that our method outperforms state-of-the-art methods in several knowledge base completion tasks. We make our code and data available at https://github.com/bio-ontology-research-group/catE.
Authors: Amit Rozner, Barak Battash, Henry Li, Lior Wolf, Ofir Lindenbaum
Abstract: We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model.
Authors: Katelyn Morrison, Philipp Spitzer, Violet Turri, Michelle Feng, Niklas K\"uhl, Adam Perer
Abstract: Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by investigating appropriate reliance and task performance with the aim of designing more human-centered computer-supported collaborative tools. Several human-centered explainable AI (XAI) techniques have been proposed in hopes of improving decision-makers' collaboration with AI; however, these techniques are grounded in findings from previous studies that primarily focus on the impact of incorrect AI advice. Few studies acknowledge the possibility of the explanations being incorrect even if the AI advice is correct. Thus, it is crucial to understand how imperfect XAI affects human-AI decision-making. In this work, we contribute a robust, mixed-methods user study with 136 participants to evaluate how incorrect explanations influence humans' decision-making behavior in a bird species identification task, taking into account their level of expertise and an explanation's level of assertiveness. Our findings reveal the influence of imperfect XAI and humans' level of expertise on their reliance on AI and human-AI team performance. We also discuss how explanations can deceive decision-makers during human-AI collaboration. Hence, we shed light on the impacts of imperfect XAI in the field of computer-supported cooperative work and provide guidelines for designers of human-AI collaboration systems.
Authors: Shiguang Wu, Yaqing Wang, Quanming Yao
Abstract: Molecular property prediction (MPP) plays a crucial role in biomedical applications, but it often encounters challenges due to a scarcity of labeled data. Existing works commonly adopt gradient-based strategy to update a large amount of parameters for task-level adaptation. However, the increase of adaptive parameters can lead to overfitting and poor performance. Observing that graph neural network (GNN) performs well as both encoder and predictor, we propose PACIA, a parameter-efficient GNN adapter for few-shot MPP. We design a unified adapter to generate a few adaptive parameters to modulate the message passing process of GNN. We then adopt a hierarchical adaptation mechanism to adapt the encoder at task-level and the predictor at query-level by the unified GNN adapter. Extensive results show that PACIA obtains the state-of-the-art performance in few-shot MPP problems, and our proposed hierarchical adaptation mechanism is rational and effective.
Authors: Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
Abstract: Differentially private learning algorithms inject noise into the learning process. While the most common private learning algorithm, DP-SGD, adds independent Gaussian noise in each iteration, recent work on matrix factorization mechanisms has shown empirically that introducing correlations in the noise can greatly improve their utility. We characterize the asymptotic learning utility for any choice of the correlation function, giving precise analytical bounds for linear regression and as the solution to a convex program for general convex functions. We show, using these bounds, how correlated noise provably improves upon vanilla DP-SGD as a function of problem parameters such as the effective dimension and condition number. Moreover, our analytical expression for the near-optimal correlation function circumvents the cubic complexity of the semi-definite program used to optimize the noise correlation matrix in previous work. We validate our theory with experiments on private deep learning. Our work matches or outperforms prior work while being efficient both in terms of compute and memory.
Authors: Jannik Deuschel, Caleb N. Ellington, Yingtao Luo, Benjamin J. Lengerich, Pascal Friederich, Eric P. Xing
Abstract: Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretability, limiting data-driven interpretations of human decision-making processes. Fundamentally, existing approaches are burdened by this tradeoff because they represent the underlying decision process as a universal policy, when in fact human decisions are dynamic and can change drastically under different contexts. Thus, we develop Contextualized Policy Recovery (CPR), which re-frames the problem of modeling complex decision processes as a multi-task learning problem, where each context poses a unique task and complex decision policies can be constructed piece-wise from many simple context-specific policies. CPR models each context-specific policy as a linear map, and generates new policy models $\textit{on-demand}$ as contexts are updated with new observations. We provide two flavors of the CPR framework: one focusing on exact local interpretability, and one retaining full global interpretability. We assess CPR through studies on simulated and real data, achieving state-of-the-art performance on predicting antibiotic prescription in intensive care units ($+22\%$ AUROC vs. previous SOTA) and predicting MRI prescription for Alzheimer's patients ($+7.7\%$ AUROC vs. previous SOTA). With this improvement, CPR closes the accuracy gap between interpretable and black-box methods, allowing high-resolution exploration and analysis of context-specific decision models.
Authors: Ming Zhong, Chenxin An, Weizhu Chen, Jiawei Han, Pengcheng He
Abstract: Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying implicit knowledge (encompassing detection, editing, and merging), there remains an ambiguous understanding regarding their transferability across models with varying scales. In this paper, we seek to empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. To achieve this, we employ sensitivity-based techniques to extract and align knowledge-specific parameters between different LLMs. Moreover, the LoRA module is used as the intermediary mechanism for injecting the extracted knowledge into smaller models. Evaluations across four benchmarks validate the efficacy of our proposed method. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer, underscoring the transferability of model parameters across LLMs of different scales. Project website: https://maszhongming.github.io/ParaKnowTransfer.
Authors: Daniel Gei{\ss}ler, Bo Zhou, Mengxi Liu, Sungho Suh, Paul Lukowicz
Abstract: This work offers a heuristic evaluation of the effects of variations in machine learning training regimes and learning paradigms on the energy consumption of computing, especially HPC hardware with a life-cycle aware perspective. While increasing data availability and innovation in high-performance hardware fuels the training of sophisticated models, it also fosters the fading perception of energy consumption and carbon emission. Therefore, the goal of this work is to raise awareness about the energy impact of general training parameters and processes, from learning rate over batch size to knowledge transfer. Multiple setups with different hyperparameter configurations are evaluated on three different hardware systems. Among many results, we have found out that even with the same model and hardware to reach the same accuracy, improperly set training hyperparameters consume up to 5 times the energy of the optimal setup. We also extensively examined the energy-saving benefits of learning paradigms including recycling knowledge through pretraining and sharing knowledge through multitask training.
Authors: Haonan Shi, Tu Ouyang, An Wang
Abstract: Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security. One method that has emerged to verify if the trained models are privacy-preserving is Membership Inference Attacks (MIA), which allows adversaries to determine whether a specific data point was part of a model's training dataset. While a series of MIAs have been proposed in the literature, only a few can achieve high True Positive Rates (TPR) in the low False Positive Rate (FPR) region (0.01%~1%). This is a crucial factor to consider for an MIA to be practically useful in real-world settings. In this paper, we present a novel approach to MIA that is aimed at significantly improving TPR at low FPRs. Our method, named learning-based difficulty calibration for MIA(LDC-MIA), characterizes data records by their hardness levels using a neural network classifier to determine membership. The experiment results show that LDC-MIA can improve TPR at low FPR by up to 4x compared to the other difficulty calibration based MIAs. It also has the highest Area Under ROC curve (AUC) across all datasets. Our method's cost is comparable with most of the existing MIAs, but is orders of magnitude more efficient than one of the state-of-the-art methods, LiRA, while achieving similar performance.
Authors: Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, Yunxin Liu
Abstract: Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.
Authors: Zheqi He, Xinya Wu, Pengfei Zhou, Richeng Xuan, Guang Liu, Xi Yang, Qiannan Zhu, Hua Huang
Abstract: Multi-modal large language models(MLLMs) have achieved remarkable progress and demonstrated powerful knowledge comprehension and reasoning abilities. However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge. Current multi-modal benchmarks for domain-specific knowledge concentrate on multiple-choice questions and are predominantly available in English, which imposes limitations on the comprehensiveness of the evaluation. To this end, we introduce CMMU, a novel benchmark for multi-modal and multi-type question understanding and reasoning in Chinese. CMMU consists of 3,603 questions in 7 subjects, covering knowledge from primary to high school. The questions can be categorized into 3 types: multiple-choice, multiple-response, and fill-in-the-blank, bringing greater challenges to MLLMs. In addition, we propose an evaluation strategy called Positional Error Variance for assessing multiple-choice questions. The strategy aims to perform a quantitative analysis of position bias. We evaluate seven open-source MLLMs along with GPT4-V, Gemini-Pro, and Qwen-VL-Plus. The results demonstrate that CMMU poses a significant challenge to the recent MLLMs. The data and code are available at https://github.com/FlagOpen/CMMU.
Authors: Paolo Sortino, Salvatore Contino, Ugo Perricone, Roberto Pirrone
Abstract: Background: Graph Neural Networks (GNN) have emerged in very recent years as a powerful tool for supporting in silico Virtual Screening. In this work we present a GNN which uses Graph Convolutional architectures to achieve very accurate multi-target screening. We also devised a hierarchical Explainable Artificial Intelligence (XAI) technique to catch information directly at atom, ring, and whole molecule level by leveraging the message passing mechanism. In this way, we find the most relevant moieties involved in bioactivity prediction. Results: We report a state-of-the-art GNN classifier on twenty Cyclin-dependent Kinase targets in support of VS. Our classifier outperforms previous SOTA approaches proposed by the authors. Moreover, a CDK1-only high-sensitivity version of the GNN has been designed to use our explainer in order to avoid the inherent bias of multi-class models. The hierarchical explainer has been validated by an expert chemist on 19 approved drugs on CDK1. Our explainer provided information in accordance to the docking analysis for 17 out of the 19 test drugs. Conclusion: Our approach is a valid support for shortening both the screening and the hit-to-lead phase. Detailed knowledge about the molecular substructures that play a role in the inhibitory action, can help the computational chemist to gain insights into the pharmacophoric function of the molecule also for repurposing purposes. Scientific Contribution Statement: The core scientific innovation of our work is the use of a hierarchical XAI approach on a GNN trained for a ligand-based VS task. The application of the hierarchical explainer allows for eliciting also structural information...
Authors: Akifumi Wachi, Xun Shen, Yanan Sui
Abstract: Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent safe RL approach is based on a constrained criterion, which seeks to maximize the expected cumulative reward subject to specific safety constraints. Despite recent effort to enhance safety in RL, a systematic understanding of the field remains difficult. This challenge stems from the diversity of constraint representations and little exploration of their interrelations. To bridge this knowledge gap, we present a comprehensive review of representative constraint formulations, along with a curated selection of algorithms designed specifically for each formulation. In addition, we elucidate the theoretical underpinnings that reveal the mathematical mutual relations among common problem formulations. We conclude with a discussion of the current state and future directions of safe reinforcement learning research.
Authors: Bibrak Qamar Chandio, Prateek Srivastava, Maciej Brodowicz, Martin Swany, Thomas Sterling
Abstract: The paper provides a unified co-design of 1) a programming and execution model that allows spawning tasks from within the vertex data at runtime, 2) language constructs for \textit{actions} that send work to where the data resides, combining parallel expressiveness of local control objects (LCOs) to implement asynchronous graph processing primitives, 3) and an innovative vertex-centric data-structure, using the concept of Rhizomes, that parallelizes both the out and in-degree load of vertex objects across many cores and yet provides a single programming abstraction to the vertex objects. The data structure hierarchically parallelizes the out-degree load of vertices and the in-degree load laterally. The rhizomes internally communicate and remain consistent, using event-driven synchronization mechanisms, to provide a unified and correct view of the vertex. Simulated experimental results show performance gains for BFS, SSSP, and Page Rank on large chip sizes for the tested input graph datasets containing highly skewed degree distribution. The improvements come from the ability to express and create fine-grain dynamic computing task in the form of \textit{actions}, language constructs that aid the compiler to generate code that the runtime system uses to optimally schedule tasks, and the data structure that shares both in and out-degree compute workload among memory-processing elements.
Authors: Z Liu, J Lou, W Bao, Y Hu, B Li, Z Qin, K Ren
Abstract: Fine-tuning on task-specific datasets is a widely-embraced paradigm of harnessing the powerful capability of pretrained LLMs for various downstream tasks. Due to the popularity of LLMs fine-tuning and its accompanying privacy concerns, differentially private (DP) fine-tuning of pretrained LLMs has been widely used to safeguarding the privacy of task-specific datasets. Lying at the design core of DP LLM fine-tuning methods is the satisfactory tradeoff among privacy, utility, and scalability. Most existing methods build upon the seminal work of DP-SGD. Despite pushing the scalability of DP-SGD to its limit, DP-SGD-based fine-tuning methods are unfortunately limited by the inherent inefficiency of SGD. In this paper, we investigate the potential of DP zeroth-order methods for LLM pretraining, which avoids the scalability bottleneck of SGD by approximating the gradient with the more efficient zeroth-order gradient. Rather than treating the zeroth-order method as a drop-in replacement for SGD, this paper presents a comprehensive study both theoretically and empirically. First, we propose the stagewise DP zeroth-order method (DP-ZOSO) that dynamically schedules key hyperparameters. This design is grounded on the synergy between DP random perturbation and the gradient approximation error of the zeroth-order method, and its effect on fine-tuning trajectory. We provide theoretical analysis for both proposed methods. We conduct extensive empirical analysis on both encoder-only masked language model and decoder-only autoregressive language model, achieving impressive results in terms of scalability and utility (compared with DPZero, DP-ZOPO improves 4.5% on SST-5, 5.5% on MNLI with RoBERTa-Large and 9.2% on CB, 3.9% on BoolQ with OPT-2.7B when $\epsilon=4$).
Authors: Ethan Smith, Nayan Saxena, Aninda Saha
Abstract: Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the importance of dense attention in generative image models, which often contain redundant features, making them suitable for sparser attention mechanisms. We propose a novel training-free method ToDo that relies on token downsampling of key and value tokens to accelerate Stable Diffusion inference by up to 2x for common sizes and up to 4.5x or more for high resolutions like 2048x2048. We demonstrate that our approach outperforms previous methods in balancing efficient throughput and fidelity.
Authors: Yiming Huang, Xiao Liu, Yeyun Gong, Zhibin Gou, Yelong Shen, Nan Duan, Weizhu Chen
Abstract: Large language models (LLMs) have shown great potential in complex reasoning tasks, yet their performance is often hampered by the scarcity of high-quality and reasoning-focused training datasets. Addressing this challenge, we propose Key-Point-Driven Data Synthesis (KPDDS), a novel data synthesis framework that synthesizes question-answer pairs by leveraging key points and exemplar practices from authentic data sources. KPDDS ensures the generation of novel questions with rigorous quality control and substantial scalability. As a result, we present KPMath, an extensive synthetic dataset tailored for mathematical reasoning, comprising over 800K question-answer pairs. Utilizing KPMath and augmenting it with additional reasoning-intensive corpora, we create the comprehensive KPMath-Plus dataset. The Qwen1.5-72B model, fine-tuned on KPMath-Plus, achieves 87.0% PASS@1 accuracy on GSM8K and 58.3% on MATH, surpassing competitors in the 7B to 70B range and best commercial models like GPT-4 across multiple math reasoning datasets.
Authors: Vincent Freiberger, Erik Buchmann
Abstract: Privacy policies are expected to inform data subjects about their data protection rights and should explain the data controller's data management practices. Privacy policies only fulfill their purpose, if they are correctly interpreted, understood, and trusted by the data subject. This implies that a privacy policy is written in a fair way, e.g., it does not use polarizing terms, does not require a certain education, or does not assume a particular social background. We outline our approach to assessing fairness in privacy policies. We identify from fundamental legal sources and fairness research, how the dimensions informational fairness, representational fairness and ethics / morality are related to privacy policies. We propose options to automatically assess policies in these fairness dimensions, based on text statistics, linguistic methods and artificial intelligence. We conduct initial experiments with German privacy policies to provide evidence that our approach is applicable. Our experiments indicate that there are issues in all three dimensions of fairness. This is important, as future privacy policies may be used in a corpus for legal artificial intelligence models.
Authors: Shahin Atakishiyev, Mohammad Salameh, Randy Goebel
Abstract: The end-to-end learning pipeline is gradually creating a paradigm shift in the ongoing development of highly autonomous vehicles, largely due to advances in deep learning, the availability of large-scale training datasets, and improvements in integrated sensor devices. However, a lack of interpretability in real-time decisions with contemporary learning methods impedes user trust and attenuates the widespread deployment and commercialization of such vehicles. Moreover, the issue is exacerbated when these cars are involved in or cause traffic accidents. Such drawback raises serious safety concerns from societal and legal perspectives. Consequently, explainability in end-to-end autonomous driving is essential to build trust in vehicular automation. However, the safety and explainability aspects of end-to-end driving have generally been investigated disjointly by researchers in today's state of the art. This survey aims to bridge the gaps between these topics and seeks to answer the following research question: When and how can explanations improve safety of end-to-end autonomous driving? In this regard, we first revisit established safety and state-of-the-art explainability techniques in end-to-end driving. Furthermore, we present three critical case studies and show the pivotal role of explanations in enhancing self-driving safety. Finally, we describe insights from empirical studies and reveal potential value, limitations, and caveats of practical explainable AI methods with respect to their safety assurance in end-to-end autonomous driving.
Authors: Ayushi Nirmal, Amrita Bhattacharjee, Paras Sheth, Huan Liu
Abstract: Although social media platforms are a prominent arena for users to engage in interpersonal discussions and express opinions, the facade and anonymity offered by social media may allow users to spew hate speech and offensive content. Given the massive scale of such platforms, there arises a need to automatically identify and flag instances of hate speech. Although several hate speech detection methods exist, most of these black-box methods are not interpretable or explainable by design. To address the lack of interpretability, in this paper, we propose to use state-of-the-art Large Language Models (LLMs) to extract features in the form of rationales from the input text, to train a base hate speech classifier, thereby enabling faithful interpretability by design. Our framework effectively combines the textual understanding capabilities of LLMs and the discriminative power of state-of-the-art hate speech classifiers to make these classifiers faithfully interpretable. Our comprehensive evaluation on a variety of English language social media hate speech datasets demonstrate: (1) the goodness of the LLM-extracted rationales, and (2) the surprising retention of detector performance even after training to ensure interpretability. All code and data will be made available at https://github.com/AmritaBh/shield.
Authors: Olga Golovneva, Zeyuan Allen-Zhu, Jason Weston, Sainbayar Sukhbaatar
Abstract: Large language models (LLMs) have a surprising failure: when trained on "A has a feature B", they do not generalize to "B is a feature of A", which is termed the Reversal Curse. Even when training with trillions of tokens this issue still appears due to Zipf's law - hence even if we train on the entire internet. This work proposes an alternative training scheme, called reverse training, whereby all words are used twice, doubling the amount of available tokens. The LLM is trained in both forward and reverse directions by reversing the training strings while preserving (i.e., not reversing) chosen substrings, such as entities. We show that data-matched reverse-trained models provide superior performance to standard models on standard tasks, and compute-matched reverse-trained models provide far superior performance on reversal tasks, helping resolve the reversal curse issue.
Authors: Yasin Sonmez, Neelay Junnarkar, Murat Arcak
Abstract: Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry. However, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model: the reward may not satisfy the same symmetries as the dynamics. In this paper, we investigate scenarios where only the dynamics are assumed to exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory where symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics which, by construction, exhibit specified symmetries. We demonstrate through numerical experiments that the proposed method learns a more accurate dynamical model.
Authors: Jiawu Tian, Liwei Xu, Xiaowei Zhang, Yongqi Li
Abstract: Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate it into the generic Adam, and thus propose a new optimization algorithm named CG-like-Adam for deep learning. Specifically, both the first-order and the second-order moment estimation of generic Adam are replaced by the conjugate-gradient-like. Convergence analysis handles the cases where the exponential moving average coefficient of the first-order moment estimation is constant and the first-order moment estimation is unbiased. Numerical experiments show the superiority of the proposed algorithm based on the CIFAR10/100 dataset.
Authors: David S. Watson, Jordan Penn, Lee M. Gunderson, Gecia Bravo-Hermsdorff, Afsaneh Mastouri, Ricardo Silva
Abstract: Instrumental variables (IVs) are a popular and powerful tool for estimating causal effects in the presence of unobserved confounding. However, classical approaches rely on strong assumptions such as the $\textit{exclusion criterion}$, which states that instrumental effects must be entirely mediated by treatments. This assumption often fails in practice. When IV methods are improperly applied to data that do not meet the exclusion criterion, estimated causal effects may be badly biased. In this work, we propose a novel solution that provides $\textit{partial}$ identification in linear systems given a set of $\textit{leaky instruments}$, which are allowed to violate the exclusion criterion to some limited degree. We derive a convex optimization objective that provides provably sharp bounds on the average treatment effect under some common forms of information leakage, and implement inference procedures to quantify the uncertainty of resulting estimates. We demonstrate our method in a set of experiments with simulated data, where it performs favorably against the state of the art. An accompanying $\texttt{R}$ package, $\texttt{leakyIV}$, is available from $\texttt{CRAN}$.
Authors: Ahmad Idrissi-Yaghir, Amin Dada, Henning Sch\"afer, Kamyar Arzideh, Giulia Baldini, Jan Trienes, Max Hasin, Jeanette Bewersdorff, Cynthia S. Schmidt, Marie Bauer, Kaleb E. Smith, Jiang Bian, Yonghui Wu, J\"org Schl\"otterer, Torsten Zesch, Peter A. Horn, Christin Seifert, Felix Nensa, Jens Kleesiek, Christoph M. Friedrich
Abstract: Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datasets, they can struggle in specialized domains such as medicine, where unique domain-specific terminologies, domain-specific abbreviations, and varying document structures are common. This paper explores strategies for adapting these models to domain-specific requirements, primarily through continuous pre-training on domain-specific data. We pre-trained several German medical language models on 2.4B tokens derived from translated public English medical data and 3B tokens of German clinical data. The resulting models were evaluated on various German downstream tasks, including named entity recognition (NER), multi-label classification, and extractive question answering. Our results suggest that models augmented by clinical and translation-based pre-training typically outperform general domain models in medical contexts. We conclude that continuous pre-training has demonstrated the ability to match or even exceed the performance of clinical models trained from scratch. Furthermore, pre-training on clinical data or leveraging translated texts have proven to be reliable methods for domain adaptation in medical NLP tasks.
Authors: Tianyu Cao, Natraj Raman, Danial Dervovic, Chenhao Tan
Abstract: As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiquity and controversy (e.g., researchers have declared the death of summarization). In this paper, we use financial report summarization as a case study because financial reports not only are long but also use numbers and tables extensively. We propose a computational framework for characterizing multimodal long-form summarization and investigate the behavior of Claude 2.0/2.1, GPT-4/3.5, and Command. We find that GPT-3.5 and Command fail to perform this summarization task meaningfully. For Claude 2 and GPT-4, we analyze the extractiveness of the summary and identify a position bias in LLMs. This position bias disappears after shuffling the input for Claude, which suggests that Claude has the ability to recognize important information. We also conduct a comprehensive investigation on the use of numeric data in LLM-generated summaries and offer a taxonomy of numeric hallucination. We employ prompt engineering to improve GPT-4's use of numbers with limited success. Overall, our analyses highlight the strong capability of Claude 2 in handling long multimodal inputs compared to GPT-4.
Authors: Peyman Gholami, Hulya Seferoglu
Abstract: This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first characterize a tighter generalization bound for one-round federated learning based on local clients' generalizations and heterogeneity of data distribution (non-iid scenario). We also characterize a generalization bound in R-round federated learning and its relation to the number of local updates (local stochastic gradient descents (SGDs)). Then, based on our generalization bound analysis and our representation learning interpretation of this analysis, we show for the first time that less frequent aggregations, hence more local updates, for the representation extractor (usually corresponds to initial layers) leads to the creation of more generalizable models, particularly for non-iid scenarios. We design a novel Federated Learning with Adaptive Local Steps (FedALS) algorithm based on our generalization bound and representation learning analysis. FedALS employs varying aggregation frequencies for different parts of the model, so reduces the communication cost. The paper is followed with experimental results showing the effectiveness of FedALS.
Authors: Aleksi Huotala, Miikka Kuutila, Paul Ralph, Mika M\"antyl\"a
Abstract: Systematic review (SR) is a popular research method in software engineering (SE). However, conducting an SR takes an average of 67 weeks. Thus, automating any step of the SR process could reduce the effort associated with SRs. Our objective is to investigate if Large Language Models (LLMs) can accelerate title-abstract screening by simplifying abstracts for human screeners, and automating title-abstract screening. We performed an experiment where humans screened titles and abstracts for 20 papers with both original and simplified abstracts from a prior SR. The experiment with human screeners was reproduced with GPT-3.5 and GPT-4 LLMs to perform the same screening tasks. We also studied if different prompting techniques (Zero-shot (ZS), One-shot (OS), Few-shot (FS), and Few-shot with Chain-of-Thought (FS-CoT)) improve the screening performance of LLMs. Lastly, we studied if redesigning the prompt used in the LLM reproduction of screening leads to improved performance. Text simplification did not increase the screeners' screening performance, but reduced the time used in screening. Screeners' scientific literacy skills and researcher status predict screening performance. Some LLM and prompt combinations perform as well as human screeners in the screening tasks. Our results indicate that the GPT-4 LLM is better than its predecessor, GPT-3.5. Additionally, Few-shot and One-shot prompting outperforms Zero-shot prompting. Using LLMs for text simplification in the screening process does not significantly improve human performance. Using LLMs to automate title-abstract screening seems promising, but current LLMs are not significantly more accurate than human screeners. To recommend the use of LLMs in the screening process of SRs, more research is needed. We recommend future SR studies publish replication packages with screening data to enable more conclusive experimenting with LLM screening.
Authors: Zeyu Hu, Yuzhi Xiao, Tao Huang, Xuanrong Huo
Abstract: Sequential recommendation is one of the important branches of recommender system, aiming to achieve personalized recommended items for the future through the analysis and prediction of users' ordered historical interactive behaviors. However, along with the growth of the user volume and the increasingly rich behavioral information, how to understand and disentangle the user's interactive multi-intention effectively also poses challenges to behavior prediction and sequential recommendation. In light of these challenges, we propose a Contrastive Learning sequential recommendation method based on Multi-Intention Disentanglement (MIDCL). In our work, intentions are recognized as dynamic and diverse, and user behaviors are often driven by current multi-intentions, which means that the model needs to not only mine the most relevant implicit intention for each user, but also impair the influence from irrelevant intentions. Therefore, we choose Variational Auto-Encoder (VAE) to realize the disentanglement of users' multi-intentions. We propose two types of contrastive learning paradigms for finding the most relevant user's interactive intention, and maximizing the mutual information of positive sample pairs, respectively. Experimental results show that MIDCL not only has significant superiority over most existing baseline methods, but also brings a more interpretable case to the research about intention-based prediction and recommendation.
Authors: Abdoul Jalil Djiberou Mahamadou, Lea Goetz, Russ Altman
Abstract: Inherent bias within society can be amplified and perpetuated by artificial intelligence (AI) systems. To address this issue, a wide range of solutions have been proposed to identify and mitigate bias and enforce fairness for individuals and groups. Recently, Graph Laplacian Regularizer (GLR), a regularization technique from the semi-supervised learning literature has been used as a substitute for the common Lipschitz condition to enhance individual fairness. Notable prior work has shown that enforcing individual fairness through a GLR can improve the transfer learning accuracy of AI models under covariate shifts. However, the prior work defines a GLR on the source and target data combined, implicitly assuming that the target data are available at train time, which might not hold in practice. In this work, we investigated whether defining a GLR independently on the train and target data could maintain similar accuracy. Furthermore, we introduced the Normalized Fairness Gain score (NFG) to measure individual fairness by measuring the amount of gained fairness when a GLR is used versus not. We evaluated the new and original methods under NFG, the Prediction Consistency (PC), and traditional classification metrics on the German Credit Approval dataset. The results showed that the two models achieved similar statistical mean performances over five-fold cross-validation. Furthermore, the proposed metric showed that PC scores can be misleading as the scores can be high and statistically similar to fairness-enhanced models while NFG scores are small. This work therefore provides new insights into when a GLR effectively enhances individual fairness and the pitfalls of PC.
Authors: Luise Ge, Brendan Juba, Yevgeniy Vorobeychik
Abstract: We study learnability of linear utility functions from pairwise comparison queries. In particular, we consider two learning objectives. The first objective is to predict out-of-sample responses to pairwise comparisons, whereas the second is to approximately recover the true parameters of the utility function. We show that in the passive learning setting, linear utilities are efficiently learnable with respect to the first objective, both when query responses are uncorrupted by noise, and under Tsybakov noise when the distributions are sufficiently "nice". In contrast, we show that utility parameters are not learnable for a large set of data distributions without strong modeling assumptions, even when query responses are noise-free. Next, we proceed to analyze the learning problem in an active learning setting. In this case, we show that even the second objective is efficiently learnable, and present algorithms for both the noise-free and noisy query response settings. Our results thus exhibit a qualitative learnability gap between passive and active learning from pairwise preference queries, demonstrating the value of the ability to select pairwise queries for utility learning.
Authors: Sher Badshah, Hassan Sajjad
Abstract: Scale is often attributed as one of the factors that cause an increase in the performance of LLMs, resulting in models with billion and trillion parameters. One of the limitations of such large models is the high computational requirements that limit their usage, deployment, and debugging in resource-constrained scenarios. Two commonly used alternatives to bypass these limitations are to use the smaller versions of LLMs (e.g. Llama 7B instead of Llama 70B) and lower the memory requirements by using quantization. While these approaches effectively address the limitation of resources, their impact on model performance needs thorough examination. In this study, we perform a comprehensive evaluation to investigate the effect of model scale and quantization on the performance. We experiment with two major families of open-source instruct models ranging from 7 billion to 70 billion parameters. Our extensive zero-shot experiments across various tasks including natural language understanding, reasoning, misinformation detection, and hallucination reveal that larger models generally outperform their smaller counterparts, suggesting that scale remains an important factor in enhancing performance. We found that larger models show exceptional resilience to precision reduction and can maintain high accuracy even at 4-bit quantization for numerous tasks and they serve as a better solution than using smaller models at high precision under similar memory requirements.
Authors: Chunyan Zheng, Keke Sun, Wenhao Zhao, Haibo Zhou, Lixin Jiang, Shaoyang Song, Chunlai Zhou
Abstract: Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem with this promising commercial use is that LLMs have been shown to memorize their training data and their prompt data are vulnerable to membership inference attacks (MIA) and prompt leaking attacks. In order to deal with this problem, we treat LLMs as untrusted in privacy and propose a locally differentially private framework of in-context learning(LDP-ICL) in the settings where labels are sensitive. Considering the mechanisms of in-context learning in Transformers by gradient descent, we provide an analysis of the trade-off between privacy and utility in such LDP-ICL for classification. Moreover, we apply LDP-ICL to the discrete distribution estimation problem. In the end, we perform several experiments to demonstrate our analysis results.
Authors: Riccardo Simionato, Stefano Fasciani
Abstract: Analog electronic circuits are at the core of an important category of musical devices. The nonlinear features of their electronic components give analog musical devices a distinctive timbre and sound quality, making them highly desirable. Artificial neural networks have rapidly gained popularity for the emulation of analog audio effects circuits, particularly recurrent networks. While neural approaches have been successful in accurately modeling distortion circuits, they require architectural improvements that account for parameter conditioning and low latency response. In this article, we explore the application of recent machine learning advancements for virtual analog modeling. We compare State Space models and Linear Recurrent Units against the more common Long Short Term Memory networks. These have shown promising ability in sequence to sequence modeling tasks, showing a notable improvement in signal history encoding. Our comparative study uses these black box neural modeling techniques with a variety of audio effects. We evaluate the performance and limitations using multiple metrics aiming to assess the models' ability to accurately replicate energy envelopes, frequency contents, and transients in the audio signal. To incorporate control parameters we employ the Feature wise Linear Modulation method. Long Short Term Memory networks exhibit better accuracy in emulating distortions and equalizers, while the State Space model, followed by Long Short Term Memory networks when integrated in an encoder decoder structure, outperforms others in emulating saturation and compression. When considering long time variant characteristics, the State Space model demonstrates the greatest accuracy. The Long Short Term Memory and, in particular, Linear Recurrent Unit networks present more tendency to introduce audio artifacts.
Authors: Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Alessandro De Palma, Robert Stanforth
Abstract: We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verification algorithm without any human input. Prior work on neural network verification has focused on partial specifications that, even when satisfied, are not sufficient to ensure that a neural network never makes errors. We focus on applying neural network verification to computational tasks with a precise notion of correctness, where a verifiably correct neural network provably solves the task at hand with no caveats. In particular, we develop an approach to train and verify the first provably correct neural networks for compressed sensing, i.e., recovering sparse vectors from a number of measurements smaller than the dimension of the vector. We show that for modest problem dimensions (up to 50), we can train neural networks that provably recover a sparse vector from linear and binarized linear measurements. Furthermore, we show that the complexity of the network (number of neurons/layers) can be adapted to the problem difficulty and solve problems where traditional compressed sensing methods are not known to provably work.
Authors: DeepSeek-AI
Abstract: We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.