Authors: Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton
Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD) detection for segmentation, we introduce a metacognitive approach in the form of a lightweight module that leverages entropy measures, segmentation predictions, and spatial context to characterize the segmentation model's uncertainty and detect pixel-wise OOD data in real-time. Additionally, our approach incorporates a novel method of generating synthetic OOD data in context with in-distribution data, which we use to fine-tune existing segmentation models with maximum entropy training. This further improves the metacognitive module's performance without requiring access to OOD data while enabling compatibility with established pre-trained models. Our resulting approach can reliably detect OOD instances in a scene, as shown by state-of-the-art performance on OOD detection for semantic segmentation benchmarks.
Authors: Oliver J. Sutton, Qinghua Zhou, Alexander N. Gorban, Ivan Y. Tyukin
High dimensional data can have a surprising property: pairs of data points may be easily separated from each other, or even from arbitrary subsets, with high probability using just simple linear classifiers. However, this is more of a rule of thumb than a reliable property as high dimensionality alone is neither necessary nor sufficient for successful learning. Here, we introduce a new notion of the intrinsic dimension of a data distribution, which precisely captures the separability properties of the data. For this intrinsic dimension, the rule of thumb above becomes a law: high intrinsic dimension guarantees highly separable data. We extend this notion to that of the relative intrinsic dimension of two data distributions, which we show provides both upper and lower bounds on the probability of successfully learning and generalising in a binary classification problem
Authors: Akshansh Mishra, Vijaykumar S Jatti, Vaishnavi More, Anish Dasgupta, Devarrishi Dixit, Eyob Messele Sefene
The ability to interpret spoken language is connected to natural language processing. It involves teaching the AI how words relate to one another, how they are meant to be used, and in what settings. The goal of natural language processing (NLP) is to get a machine intelligence to process words the same way a human brain does. This enables machine intelligence to interpret, arrange, and comprehend textual data by processing the natural language. The technology can comprehend what is communicated, whether it be through speech or writing because AI pro-cesses language more quickly than humans can. In the present study, five NLP algorithms, namely, Geneism, Sumy, Luhn, Latent Semantic Analysis (LSA), and Kull-back-Liebler (KL) al-gorithm, are implemented for the first time for the knowledge summarization purpose of the High Entropy Alloys (HEAs). The performance prediction of these algorithms is made by using the BLEU score and ROUGE score. The results showed that the Luhn algorithm has the highest accuracy score for the knowledge summarization tasks compared to the other used algorithms.
Authors: C. Daniel Freeman, Laura Culp, Aaron Parisi, Maxwell L Bileschi, Gamaleldin F Elsayed, Alex Rizkowsky, Isabelle Simpson, Alex Alemi, Azade Nova, Ben Adlam, Bernd Bohnet, Gaurav Mishra, Hanie Sedghi, Igor Mordatch, Izzeddin Gur, Jaehoon Lee, JD Co-Reyes, Jeffrey Pennington, Kelvin Xu, Kevin Swersky, Kshiteej Mahajan, Lechao Xiao, Rosanne Liu, Simon Kornblith, Noah Constant, Peter J. Liu, Roman Novak, Sharad Vikram, Yundi Qian, Noah Fiedel, Jascha Sohl-Dickstein
We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic questions posed in natural language, with an arbitrary adversarial string inserted before the question is complete. Even in the simple setting of 1-digit addition problems, it is easy to find adversarial prompts that make all tested models (including PaLM2, GPT4, Claude2) misbehave, and even to steer models to a particular wrong answer. We additionally provide a simple algorithm for finding successful attacks by querying those same models, which we name "prompt inversion rejection sampling" (PIRS). We finally show that models can be partially hardened against these attacks via reinforcement learning and via agentic constitutional loops. However, we were not able to make a language model fully robust against adversarial arithmetic attacks.
Authors: Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn
We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely, we deploy GPT-4 as an agent in a realistic, simulated environment, where it assumes the role of an autonomous stock trading agent. Within this environment, the model obtains an insider tip about a lucrative stock trade and acts upon it despite knowing that insider trading is disapproved of by company management. When reporting to its manager, the model consistently hides the genuine reasons behind its trading decision. We perform a brief investigation of how this behavior varies under changes to the setting, such as removing model access to a reasoning scratchpad, attempting to prevent the misaligned behavior by changing system instructions, changing the amount of pressure the model is under, varying the perceived risk of getting caught, and making other simple changes to the environment. To our knowledge, this is the first demonstration of Large Language Models trained to be helpful, harmless, and honest, strategically deceiving their users in a realistic situation without direct instructions or training for deception.
Authors: Alp Niksarli, Sadik Ozan Gorgu, Ege Gencer
Reading right books contributes to children's imagination and brain development, enhances their language and emotional comprehension abilities, and strengthens their relationships with others. Building upon the critical role of reading books in individual development, this paper aims to develop an algorithm that determines the suitability of books for middle school students by analyzing their structural and semantic features. Using methods described, an algorithm will be created that can be utilized by institutions and individuals responsible for children's education, such as the Ministry of National Education officials and schools. This algorithm will facilitate the selection of books to be taught at the middle school level. With the algorithm, the book selection process for the middle school curriculum can be expedited, and it will serve as a preliminary reference source for those who evaluate books by reading them. In this paper, the Python programming language was employed, utilizing natural language processing methods. Additionally, an artificial neural network (ANN) was trained using the data which had been preprocessed to construct an original dataset. To train this network, suitable books for middle school students were provided by the MEB, Oxford and Cambridge and with content assessed based on the "R" criterion, and inappropriate books for middle school students in terms of content were included. This trained neural network achieved a 90.06% consistency rate in determining the appropriateness of the test-provided books. Considering the obtained findings, it can be concluded that the developed software has achieved the desired objective.
Authors: Reza Esfandiarpoor, Stephen H. Bach
A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.
Authors: Ritesh Chandra, Sadhana Tiwari, Satyam Rastogi, Sonali Agarwal
Liver diseases pose a significant global health burden, impacting a substantial number of individuals and exerting substantial economic and social consequences. Rising liver problems are considered a fatal disease in many countries, such as Egypt, Molda, etc. The objective of this study is to construct a predictive model for liver illness using Basic Formal Ontology (BFO) and detection rules derived from a decision tree algorithm. Based on these rules, events are detected through batch processing using the Apache Jena framework. Based on the event detected, queries can be directly processed using SPARQL. To make the ontology operational, these Decision Tree (DT) rules are converted into Semantic Web Rule Language (SWRL). Using this SWRL in the ontology for predicting different types of liver disease with the help of the Pellet and Drool inference engines in Protege Tools, a total of 615 records are taken from different liver diseases. After inferring the rules, the result can be generated for the patient according to the DT rules, and other patient-related details along with different precautionary suggestions can be obtained based on these results. Combining query results of batch processing and ontology-generated results can give more accurate suggestions for disease prevention and detection. This work aims to provide a comprehensive approach that is applicable for liver disease prediction, rich knowledge graph representation, and smart querying capabilities. The results show that combining RDF data, SWRL rules, and SPARQL queries for analysing and predicting liver disease can help medical professionals to learn more about liver diseases and make a Decision Support System (DSS) for health care.
Authors: Jinhao Gu, Ángel F. García-Fernández, Robert E. Firth, Lennart Svensson
This paper proposes a metric to measure the dissimilarity between graphs that may have a different number of nodes. The proposed metric extends the generalised optimal subpattern assignment (GOSPA) metric, which is a metric for sets, to graphs. The proposed graph GOSPA metric includes costs associated with node attribute errors for properly assigned nodes, missed and false nodes and edge mismatches between graphs. The computation of this metric is based on finding the optimal assignments between nodes in the two graphs, with the possibility of leaving some of the nodes unassigned. We also propose a lower bound for the metric, which is also a metric for graphs and is computable in polynomial time using linear programming. The metric is first derived for undirected unweighted graphs and it is then extended to directed and weighted graphs. The properties of the metric are demonstrated via simulated and empirical datasets.
Authors: Alexej Brauer
Currently, there is a lot of research in the field of neural networks for non-life insurance pricing. The usual goal is to improve the predictive power via neural networks while building upon the generalized linear model, which is the current industry standard. Our paper contributes to this current journey via novel methods to enhance actuarial non-life models with transformer models for tabular data. We build here upon the foundation laid out by the combined actuarial neural network as well as the localGLMnet and enhance those models via the feature tokenizer transformer. The manuscript demonstrates the performance of the proposed methods on a real-world claim frequency dataset and compares them with several benchmark models such as generalized linear models, feed-forward neural networks, combined actuarial neural networks, LocalGLMnet, and pure feature tokenizer transformer. The paper shows that the new methods can achieve better results than the benchmark models while preserving certain generalized linear model advantages. The paper also discusses the practical implications and challenges of applying transformer models in actuarial settings.
Authors: Moritz Scherrmann
This paper presents a multi-label topic model for financial texts like ad-hoc announcements, 8-K filings, finance related news or annual reports. I train the model on a new financial multi-label database consisting of 3,044 German ad-hoc announcements that are labeled manually using 20 predefined, economically motivated topics. The best model achieves a macro F1 score of more than 85%. Translating the data results in an English version of the model with similar performance. As application of the model, I investigate differences in stock market reactions across topics. I find evidence for strong positive or negative market reactions for some topics, like announcements of new Large Scale Projects or Bankruptcy Filings, while I do not observe significant price effects for some other topics. Furthermore, in contrast to previous studies, the multi-label structure of the model allows to analyze the effects of co-occurring topics on stock market reactions. For many cases, the reaction to a specific topic depends heavily on the co-occurrence with other topics. For example, if allocated capital from a Seasoned Equity Offering (SEO) is used for restructuring a company in the course of a Bankruptcy Proceeding, the market reacts positively on average. However, if that capital is used for covering unexpected, additional costs from the development of new drugs, the SEO implies negative reactions on average.
Authors: Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a distorted worldview and limit opportunities for minority groups. In this work, we frame fairness as a distributional alignment problem. Our solution consists of two main technical contributions: (1) a distributional alignment loss that steers specific characteristics of the generated images towards a user-defined target distribution, and (2) biased direct finetuning of diffusion model's sampling process, which leverages a biased gradient to more effectively optimize losses defined on the generated images. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Gender bias is significantly reduced even when finetuning just five soft tokens. Crucially, our method supports diverse perspectives of fairness beyond absolute equality, which is demonstrated by controlling age to a $75\%$ young and $25\%$ old distribution while simultaneously debiasing gender and race. Finally, our method is scalable: it can debias multiple concepts at once by simply including these prompts in the finetuning data. We hope our work facilitates the social alignment of T2I generative AI. We will share code and various debiased diffusion model adaptors.
Authors: Joohwan Ko, Andrew A. Li
Models of choice are a fundamental input to many now-canonical optimization problems in the field of Operations Management, including assortment, inventory, and price optimization. Naturally, accurate estimation of these models from data is a critical step in the application of these optimization problems in practice, and so it is perhaps surprising that such choice estimation has to now been accomplished almost exclusively, both in theory and in practice, (a) without the use of deep learning in any meaningful way, and (b) via evaluation on limited data with constantly-changing metrics. This is in stark contrast to the vast majority of similar learning applications, for which the practice of machine learning suggests that (a) neural network-based models are typically state-of-the-art, and (b) strict standardization on evaluation procedures (datasets, metrics, etc.) is crucial. Thus motivated, we first propose a choice model that is the first to successfully (both theoretically and practically) leverage a modern neural network architectural concept (self-attention). Theoretically, we show that our attention-based choice model is a low-rank generalization of the Halo Multinomial Logit model, a recent model that parsimoniously captures irrational choice effects and has seen empirical success. We prove that whereas the Halo-MNL requires $\Omega(m^2)$ data samples to estimate, where $m$ is the number of products, our model supports a natural nonconvex estimator (in particular, that which a standard neural network implementation would apply) which admits a near-optimal stationary point with $O(m)$ samples. We then establish the first realistic-scale benchmark for choice estimation on real data and use this benchmark to run the largest evaluation of existing choice models to date. We find that the model we propose is dominant over both short-term and long-term data periods.
Hospital readmission prediction is considered an essential approach to decreasing readmission rates, which is a key factor in assessing the quality and efficacy of a healthcare system. Previous studies have extensively utilized three primary modalities, namely electronic health records (EHR), medical images, and clinical notes, to predict hospital readmissions. However, the majority of these studies did not integrate information from all three modalities or utilize the spatiotemporal relationships present in the dataset. This study introduces a novel model called the Multimodal Spatiotemporal Graph-Transformer (MuST) for predicting hospital readmissions. By employing Graph Convolution Networks and temporal transformers, we can effectively capture spatial and temporal dependencies in EHR and chest radiographs. We then propose a fusion transformer to combine the spatiotemporal features from the two modalities mentioned above with the features from clinical notes extracted by a pre-trained, domain-specific transformer. We assess the effectiveness of our methods using the latest publicly available dataset, MIMIC-IV. The experimental results indicate that the inclusion of multimodal features in MuST improves its performance in comparison to unimodal methods. Furthermore, our proposed pipeline outperforms the current leading methods in the prediction of hospital readmissions.
Authors: Mason Ma, Jiajie Wu, Chase Post, Tony Shi, Jingang Yi, Tony Schmitz, Hong Wang
This study presents a physics-informed machine learning-based control method for nonlinear dynamic systems with highly noisy measurements. Existing data-driven control methods that use machine learning for system identification cannot effectively cope with highly noisy measurements, resulting in unstable control performance. To address this challenge, the present study extends current physics-informed machine learning capabilities for modeling nonlinear dynamics with control and integrates them into a model predictive control framework. To demonstrate the capability of the proposed method we test and validate with two noisy nonlinear dynamic systems: the chaotic Lorenz 3 system, and turning machine tool. Analysis of the results illustrate that the proposed method outperforms state-of-the-art benchmarks as measured by both modeling accuracy and control performance for nonlinear dynamic systems under high-noise conditions.
Authors: Ruijun Wang, Yuan Liu, Zhixia Fan, Xiaogang Xu, Huijie Wang
Although the deep learning recognition model has been widely used in the condition monitoring of rotating machinery. However, it is still a challenge to understand the correspondence between the structure and function of the model and the diagnosis process. Therefore, this paper discusses embedding distributed attention modules into dense connections instead of traditional dense cascading operations. It not only decouples the influence of space and channel on fault feature adaptive recalibration feature weights, but also forms a fusion attention function. The proposed dense fusion focuses on the visualization of the network diagnosis process, which increases the interpretability of model diagnosis. How to continuously and effectively integrate different functions to enhance the ability to extract fault features and the ability to resist noise is answered. Centrifugal fan fault data is used to verify this network. Experimental results show that the network has stronger diagnostic performance than other advanced fault diagnostic models.
Authors: Roozbeh Yousefzadeh, Xuenan Cao
It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding of mathematics as well. Here, we perform a critical inquiry into this claim by evaluating the mathematical understanding of the GPT-4 model. Considering that GPT-4's training set is a secret, it is not straightforward to evaluate whether the model's correct answers are based on a mathematical understanding or based on replication of proofs that the model has seen before. We specifically craft mathematical questions which their formal proofs are not readily available on the web, proofs that are more likely not seen by the GPT-4. We see that GPT-4 is unable to solve those problems despite their simplicity. It is hard to find scientific evidence suggesting that GPT-4 has acquired an understanding of even basic mathematical concepts. A straightforward way to find failure modes of GPT-4 in theorem proving is to craft questions where their formal proofs are not available on the web. Our finding suggests that GPT-4's ability is to reproduce, rephrase, and polish the mathematical proofs that it has seen before, and not in grasping mathematical concepts. We also see that GPT-4's ability to prove mathematical theorems is continuously expanding over time despite the claim that it is a fixed model. We suggest that the task of proving mathematical theorems in formal language is comparable to the methods used in search engines such as Google while predicting the next word in a sentence may be a misguided approach, a recipe that often leads to excessive extrapolation and eventual failures. Prompting the GPT-4 over and over may benefit the GPT-4 and the OpenAI, but we question whether it is valuable for machine learning or for theorem proving.
Authors: Chenyu Wang, Zhen Dong, Daquan Zhou, Zhenhua Zhu, Yu Wang, Jiashi Feng, Kurt Keutzer
The exploration of Processing-In-Memory (PIM) accelerators has garnered significant attention within the research community. However, the utilization of large-scale neural networks on Processing-In-Memory (PIM) accelerators encounters challenges due to constrained on-chip memory capacity. To tackle this issue, current works explore model compression algorithms to reduce the size of Convolutional Neural Networks (CNNs). Most of these algorithms either aim to represent neural operators with reduced-size parameters (e.g., quantization) or search for the best combinations of neural operators (e.g., neural architecture search). Designing neural operators to align with PIM accelerators' specifications is an area that warrants further study. In this paper, we introduce the Epitome, a lightweight neural operator offering convolution-like functionality, to craft memory-efficient CNN operators for PIM accelerators (EPIM). On the software side, we evaluate epitomes' latency and energy on PIM accelerators and introduce a PIM-aware layer-wise design method to enhance their hardware efficiency. We apply epitome-aware quantization to further reduce the size of epitomes. On the hardware side, we modify the datapath of current PIM accelerators to accommodate epitomes and implement a feature map reuse technique to reduce computation cost. Experimental results reveal that our 3-bit quantized EPIM-ResNet50 attains 71.59% top-1 accuracy on ImageNet, reducing crossbar areas by 30.65 times. EPIM surpasses the state-of-the-art pruning methods on PIM.
Authors: Micaela E. Consens, Cameron Dufault, Michael Wainberg, Duncan Forster, Mehran Karimzadeh, Hani Goodarzi, Fabian J. Theis, Alan Moses, Bo Wang
In the rapidly evolving landscape of genomics, deep learning has emerged as a useful tool for tackling complex computational challenges. This review focuses on the transformative role of Large Language Models (LLMs), which are mostly based on the transformer architecture, in genomics. Building on the foundation of traditional convolutional neural networks and recurrent neural networks, we explore both the strengths and limitations of transformers and other LLMs for genomics. Additionally, we contemplate the future of genomic modeling beyond the transformer architecture based on current trends in research. The paper aims to serve as a guide for computational biologists and computer scientists interested in LLMs for genomic data. We hope the paper can also serve as an educational introduction and discussion for biologists to a fundamental shift in how we will be analyzing genomic data in the future.
Authors: Rishav Mukherji, Mark Schöne, Khaleelulla Khan Nazeer, Christian Mayr, Anand Subramoney
Artificial neural networks open up unprecedented machine learning capabilities at the cost of ever growing computational requirements. Sparsifying the parameters, often achieved through weight pruning, has been identified as a powerful technique to compress the number of model parameters and reduce the computational operations of neural networks. Yet, sparse activations, while omnipresent in both biological neural networks and deep learning systems, have not been fully utilized as a compression technique in deep learning. Moreover, the interaction between sparse activations and weight pruning is not fully understood. In this work, we demonstrate that activity sparsity can compose multiplicatively with parameter sparsity in a recurrent neural network model based on the GRU that is designed to be activity sparse. We achieve up to $20\times$ reduction of computation while maintaining perplexities below $60$ on the Penn Treebank language modeling task. This magnitude of reduction has not been achieved previously with solely sparsely connected LSTMs, and the language modeling performance of our model has not been achieved previously with any sparsely activated recurrent neural networks or spiking neural networks. Neuromorphic computing devices are especially good at taking advantage of the dynamic activity sparsity, and our results provide strong evidence that making deep learning models activity sparse and porting them to neuromorphic devices can be a viable strategy that does not compromise on task performance. Our results also drive further convergence of methods from deep learning and neuromorphic computing for efficient machine learning.
Authors: Artur Miroszewski, Jakub Nalepa, Bertrand Le Saux, Jakub Mielczarek
The industry of quantum technologies is rapidly expanding, offering promising opportunities for various scientific domains. Among these emerging technologies, Quantum Machine Learning (QML) has attracted considerable attention due to its potential to revolutionize data processing and analysis. In this paper, we investigate the application of QML in the field of remote sensing. It is believed that QML can provide valuable insights for analysis of data from space. We delve into the common beliefs surrounding the quantum advantage in QML for remote sensing and highlight the open challenges that need to be addressed. To shed light on the challenges, we conduct a study focused on the problem of kernel value concentration, a phenomenon that adversely affects the runtime of quantum computers. Our findings indicate that while this issue negatively impacts quantum computer performance, it does not entirely negate the potential quantum advantage in QML for remote sensing.
Authors: Thomas Bonald (IP Paris), Nathan de Lara (IP Paris)
The task of semi-supervised classification aims at assigning labels to all nodes of a graph based on the labels known for a few nodes, called the seeds. One of the most popular algorithms relies on the principle of heat diffusion, where the labels of the seeds are spread by thermoconductance and the temperature of each node at equilibrium is used as a score function for each label. In this paper, we prove that this algorithm is not consistent unless the temperatures of the nodes at equilibrium are centered before scoring. This crucial step does not only make the algorithm provably consistent on a block model but brings significant performance gains on real graphs.
Authors: Zhaojian Li, Bin Zhao, Yuan Yuan
Binaural stereo audio is recorded by imitating the way the human ear receives sound, which provides people with an immersive listening experience. Existing approaches leverage autoencoders and directly exploit visual spatial information to synthesize binaural stereo, resulting in a limited representation of visual guidance. For the first time, we propose a visually guided generative adversarial approach for generating binaural stereo audio from mono audio. Specifically, we develop a Stereo Audio Generation Model (SAGM), which utilizes shared spatio-temporal visual information to guide the generator and the discriminator to work separately. The shared visual information is updated alternately in the generative adversarial stage, allowing the generator and discriminator to deliver their respective guided knowledge while visually sharing. The proposed method learns bidirectional complementary visual information, which facilitates the expression of visual guidance in generation. In addition, spatial perception is a crucial attribute of binaural stereo audio, and thus the evaluation of stereo spatial perception is essential. However, previous metrics failed to measure the spatial perception of audio. To this end, a metric to measure the spatial perception of audio is proposed for the first time. The proposed metric is capable of measuring the magnitude and direction of spatial perception in the temporal dimension. Further, considering its function, it is feasible to utilize it instead of demanding user studies to some extent. The proposed method achieves state-of-the-art performance on 2 datasets and 5 evaluation metrics. Qualitative experiments and user studies demonstrate that the method generates space-realistic stereo audio.
Authors: Zecheng Yin
Biomedical information graphs are crucial for interaction discovering of biomedical information in modern age, such as identification of multifarious molecular interactions and drug discovery, which attracts increasing interests in biomedicine, bioinformatics, and human healthcare communities. Nowadays, more and more graph neural networks have been proposed to learn the entities of biomedical information and precisely reveal biomedical molecule interactions with state-of-the-art results. These methods remedy the fading of features from a far distance but suffer from remedying such problem at the expensive cost of redundant memory and time. In our paper, we propose a novel Residual Message Graph Convolution Network (ResMGCN) for fast and precise biomedical interaction prediction in a different idea. Specifically, instead of enhancing the message from far nodes, ResMGCN aggregates lower-order information with the next round higher information to guide the node update to obtain a more meaningful node representation. ResMGCN is able to perceive and preserve various messages from the previous layer and high-order information in the current layer with least memory and time cost to obtain informative representations of biomedical entities. We conduct experiments on four biomedical interaction network datasets, including protein-protein, drug-drug, drug-target, and gene-disease interactions, which demonstrates that ResMGCN outperforms previous state-of-the-art models while achieving superb effectiveness on both storage and time.
Authors: Haoyu Geng, Han Ruan, Runzhong Wang, Yang Li, Yang Wang, Lei Chen, Junchi Yan
Numerous web applications rely on solving combinatorial optimization problems, such as energy cost-aware scheduling, budget allocation on web advertising, and graph matching on social networks. However, many optimization problems involve unknown coefficients, and improper predictions of these factors may lead to inferior decisions which may cause energy wastage, inefficient resource allocation, inappropriate matching in social networks, etc. Such a research topic is referred to as "Predict-Then-Optimize (PTO)" which considers the performance of prediction and decision-making in a unified system. A noteworthy recent development is the end-to-end methods by directly optimizing the ultimate decision quality which claims to yield better results in contrast to the traditional two-stage approach. However, the evaluation benchmarks in this field are fragmented and the effectiveness of various models in different scenarios remains unclear, hindering the comprehensive assessment and fast deployment of these methods. To address these issues, we provide a comprehensive categorization of current approaches and integrate existing experimental scenarios to establish a unified benchmark, elucidating the circumstances under which end-to-end training yields improvements, as well as the contexts in which it performs ineffectively. We also introduce a new dataset for the industrial combinatorial advertising problem for inclusive finance to open-source. We hope the rethinking and benchmarking of PTO could facilitate more convenient evaluation and deployment, and inspire further improvements both in the academy and industry within this field.
Authors: Amina Mollaysa, Ahmed Allam, Michael Krauthamme
Human genetic diseases often arise from point mutations, emphasizing the critical need for precise genome editing techniques. Among these, base editing stands out as it allows targeted alterations at the single nucleotide level. However, its clinical application is hindered by low editing efficiency and unintended mutations, necessitating extensive trial-and-error experimentation in the laboratory. To speed up this process, we present an attention-based two-stage machine learning model that learns to predict the likelihood of all possible editing outcomes for a given genomic target sequence. We further propose a multi-task learning schema to jointly learn multiple base editors (i.e. variants) at once. Our model's predictions consistently demonstrated a strong correlation with the actual experimental results on multiple datasets and base editor variants. These results provide further validation for the models' capacity to enhance and accelerate the process of refining base editing designs.
Authors: Kerem Zaman, Leshem Choshen, Shashank Srivastava
Model fusion research aims to aggregate the knowledge of multiple models to enhance performance by combining their weights. In this work, we study the inverse, investigating whether and how can model fusion interfere and reduce unwanted knowledge. We delve into the effects of model fusion on the evolution of learned shortcuts, social biases, and memorization capabilities in fine-tuned language models. Through several experiments covering text classification and generation tasks, our analysis highlights that shared knowledge among models is usually enhanced during model fusion, while unshared knowledge is usually lost or forgotten. Based on this observation, we demonstrate the potential of model fusion as a debiasing tool and showcase its efficacy in addressing privacy concerns associated with language models.
Authors: Arjun Vaithilingam Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran, Sarath Chandar
Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. CALM, a popular approach, leverages linguistic priors of LLMs -- GPT-2 -- for action candidate recommendations to improve the performance in text games in Jericho without environment-provided actions. However, CALM adapts GPT-2 with annotated human gameplays and keeps the LLM fixed during the learning of the text based games. In this work, we explore and evaluate updating LLM used for candidate recommendation during the learning of the text based game as well to mitigate the reliance on the human annotated gameplays, which are costly to acquire. We observe that by updating the LLM during learning using carefully selected in-game transitions, we can reduce the dependency on using human annotated game plays for fine-tuning the LLMs. We conducted further analysis to study the transferability of the updated LLMs and observed that transferring in-game trained models to other games did not result in a consistent transfer.
Authors: Naman Goel
The surprisingly likely criterion in the seminal work of Prelec (the Bayesian Truth Serum) guarantees truthfulness in a game-theoretic multi-agent setting, by rewarding rational agents to maximise the expected information gain with their answers w.r.t. their probabilistic beliefs. We investigate the relevance of a similar criterion for responses of LLMs. We hypothesize that if the surprisingly likely criterion works in LLMs, under certain conditions, the responses that maximize the reward under this criterion should be more accurate than the responses that only maximize the posterior probability. Using benchmarks including the TruthfulQA benchmark and using openly available LLMs: GPT-2 and LLaMA-2, we show that the method indeed improves the accuracy significantly (for example, upto 24 percentage points aggregate improvement on TruthfulQA and upto 70 percentage points improvement on individual categories of questions).
Authors: Surojit Saha, Sarang Joshi, Ross Whitaker
The variational autoencoder (VAE) is a well-studied, deep, latent-variable model (DLVM) that efficiently optimizes the variational lower bound of the log marginal data likelihood and has a strong theoretical foundation. However, the VAE's known failure to match the aggregate posterior often results in \emph{pockets/holes} in the latent distribution (i.e., a failure to match the prior) and/or \emph{posterior collapse}, which is associated with a loss of information in the latent space. This paper addresses these shortcomings in VAEs by reformulating the objective function associated with VAEs in order to match the aggregate/marginal posterior distribution to the prior. We use kernel density estimate (KDE) to model the aggregate posterior in high dimensions. The proposed method is named the \emph{aggregate variational autoencoder} (AVAE) and is built on the theoretical framework of the VAE. Empirical evaluation of the proposed method on multiple benchmark data sets demonstrates the effectiveness of the AVAE relative to state-of-the-art (SOTA) methods.
Authors: Zhen Guo, Shangdi Yu
Large language models (LLMs) have opened up enormous opportunities while simultaneously posing ethical dilemmas. One of the major concerns is their ability to create text that closely mimics human writing, which can lead to potential misuse, such as academic misconduct, disinformation, and fraud. To address this problem, we present AuthentiGPT, an efficient classifier that distinguishes between machine-generated and human-written texts. Under the assumption that human-written text resides outside the distribution of machine-generated text, AuthentiGPT leverages a black-box LLM to denoise input text with artificially added noise, and then semantically compares the denoised text with the original to determine if the content is machine-generated. With only one trainable parameter, AuthentiGPT eliminates the need for a large training dataset, watermarking the LLM's output, or computing the log-likelihood. Importantly, the detection capability of AuthentiGPT can be easily adapted to any generative language model. With a 0.918 AUROC score on a domain-specific dataset, AuthentiGPT demonstrates its effectiveness over other commercial algorithms, highlighting its potential for detecting machine-generated text in academic settings.
Authors: Junyao Wang, Mohammad Abdullah Al Faruque
The Internet of Things (IoT) has facilitated many applications utilizing edge-based machine learning (ML) methods to analyze locally collected data. Unfortunately, popular ML algorithms often require intensive computations beyond the capabilities of today's IoT devices. Brain-inspired hyperdimensional computing (HDC) has been introduced to address this issue. However, existing HDCs use static encoders, requiring extremely high dimensionality and hundreds of training iterations to achieve reasonable accuracy. This results in a huge efficiency loss, severely impeding the application of HDCs in IoT systems. We observed that a main cause is that the encoding module of existing HDCs lacks the capability to utilize and adapt to information learned during training. In contrast, neurons in human brains dynamically regenerate all the time and provide more useful functionalities when learning new information. While the goal of HDC is to exploit the high-dimensionality of randomly generated base hypervectors to represent the information as a pattern of neural activity, it remains challenging for existing HDCs to support a similar behavior as brain neural regeneration. In this work, we present dynamic HDC learning frameworks that identify and regenerate undesired dimensions to provide adequate accuracy with significantly lowered dimensionalities, thereby accelerating both the training and inference.
Authors: Zangir Iklassov, Ikboljon Sobirov, Ruben Solozabal, Martin Takac
This study addresses a gap in the utilization of Reinforcement Learning (RL) and Machine Learning (ML) techniques in solving the Stochastic Vehicle Routing Problem (SVRP) that involves the challenging task of optimizing vehicle routes under uncertain conditions. We propose a novel end-to-end framework that comprehensively addresses the key sources of stochasticity in SVRP and utilizes an RL agent with a simple yet effective architecture and a tailored training method. Through comparative analysis, our proposed model demonstrates superior performance compared to a widely adopted state-of-the-art metaheuristic, achieving a significant 3.43% reduction in travel costs. Furthermore, the model exhibits robustness across diverse SVRP settings, highlighting its adaptability and ability to learn optimal routing strategies in varying environments. The publicly available implementation of our framework serves as a valuable resource for future research endeavors aimed at advancing RL-based solutions for SVRP.
Authors: Jerry Junyang Cheung, Yuchen Zhuang, Yinghao Li, Pranav Shetty, Wantian Zhao, Sanjeev Grampurohit, Rampi Ramprasad, Chao Zhang
Scientific information extraction (SciIE), which aims to automatically extract information from scientific literature, is becoming more important than ever. However, there are no existing SciIE datasets for polymer materials, which is an important class of materials used ubiquitously in our daily lives. To bridge this gap, we introduce POLYIE, a new SciIE dataset for polymer materials. POLYIE is curated from 146 full-length polymer scholarly articles, which are annotated with different named entities (i.e., materials, properties, values, conditions) as well as their N-ary relations by domain experts. POLYIE presents several unique challenges due to diverse lexical formats of entities, ambiguity between entities, and variable-length relations. We evaluate state-of-the-art named entity extraction and relation extraction models on POLYIE, analyze their strengths and weaknesses, and highlight some difficult cases for these models. To the best of our knowledge, POLYIE is the first SciIE benchmark for polymer materials, and we hope it will lead to more research efforts from the community on this challenging task. Our code and data are available on: https://github.com/jerry3027/PolyIE.
Authors: Joshua Clymer, Garrett Baker, Rohan Subramani, Sam Wang
As AI systems become more intelligent and their behavior becomes more challenging to assess, they may learn to game the flaws of human feedback instead of genuinely striving to follow instructions; however, this risk can be mitigated by controlling how LLMs generalize human feedback to situations where it is unreliable. To better understand how reward models generalize, we craft 69 distribution shifts spanning 8 categories. We find that reward models do not learn to evaluate `instruction-following' by default and instead favor personas that resemble internet text. Techniques for interpreting reward models' internal representations achieve better generalization than standard fine-tuning, but still frequently fail to distinguish instruction-following from conflated behaviors. We consolidate the 15 most challenging distribution shifts into the GENaralization analogIES (GENIES) benchmark, which we hope will enable progress toward controlling reward model generalization.
Authors: Ammar Daskin
Blockmodeling of a given problem represented by an $N\times N$ adjacency matrix can be found by swapping rows and columns of the matrix (i.e. multiplying matrix from left and right by a permutation matrix). In general, through performing this task, row and column permutations affect the fitness value in optimization: For an $N\times N$ matrix, it requires $O(N)$ computations to find (or update) the fitness value of a candidate solution.
On quantum computers, permutations can be applied in parallel and efficiently, and their implementations can be as simple as a single qubit operation (a NOT gate on a qubit) which takes an $O(1)$ time algorithmic step. In this paper, using permutation matrices, we describe a quantum blockmodeling for data analysis tasks. In the model, the measurement outcome of a small group of qubits are mapped to indicate the fitness value. Therefore, we show that it is possible to find or update the fitness value in $O(log(N))$ time. This lead us to show that when the number of iterations are less than $log(N)$ time, it may be possible to reach the same solution exponentially faster on quantum computers in comparison to classical computers. In addition, since on quantum circuits the different sequence of permutations can be applied in parallel (superpositon), the machine learning task in this model can be implemented more efficiently on quantum computers.
Authors: Xingyu Chen, Xiaochen Zheng, Amina Mollaysa, Manuel Schürch, Ahmed Allam, Michael Krauthammer
Irregular multivariate time series data is prevalent in the clinical and healthcare domains. It is characterized by time-wise and feature-wise irregularities, making it challenging for machine learning methods to work with. To solve this, we introduce a new model architecture composed of two modules: (1) DLA, a Dynamic Local Attention mechanism that uses learnable queries and feature-specific local windows when computing the self-attention operation. This results in aggregating irregular time steps raw input within each window to a harmonized regular latent space representation while taking into account the different features' sampling rates. (2) A hierarchical MLP mixer that processes the output of DLA through multi-scale patching to leverage information at various scales for the downstream tasks. Our approach outperforms state-of-the-art methods on three real-world datasets, including the latest clinical MIMIC IV dataset.
Authors: S.M. Nabil Ashraf, Md. Adyelullahil Mamun, Hasnat Md. Abdullah, Md. Golam Rabiul Alam
Chest X-rays are widely used to diagnose thoracic diseases, but the lack of detailed information about these abnormalities makes it challenging to develop accurate automated diagnosis systems, which is crucial for early detection and effective treatment. To address this challenge, we employed deep learning techniques to identify patterns in chest X-rays that correspond to different diseases. We conducted experiments on the "ChestX-ray14" dataset using various pre-trained CNNs, transformers, hybrid(CNN+Transformer) models and classical models. The best individual model was the CoAtNet, which achieved an area under the receiver operating characteristic curve (AUROC) of 84.2%. By combining the predictions of all trained models using a weighted average ensemble where the weight of each model was determined using differential evolution, we further improved the AUROC to 85.4%, outperforming other state-of-the-art methods in this field. Our findings demonstrate the potential of deep learning techniques, particularly ensemble deep learning, for improving the accuracy of automatic diagnosis of thoracic diseases from chest X-rays.
Authors: Brian Barr, Noah Fatsi, Leif Hancox-Li, Peter Richter, Daniel Proano, Caleb Mok
The field of explainable artificial intelligence (XAI) aims to explain how black-box machine learning models work. Much of the work centers around the holy grail of providing post-hoc feature attributions to any model architecture. While the pace of innovation around novel methods has slowed down, the question remains of how to choose a method, and how to make it fit for purpose. Recently, efforts around benchmarking XAI methods have suggested metrics for that purpose -- but there are many choices. That bounty of choice still leaves an end user unclear on how to proceed. This paper focuses on comparing metrics with the aim of measuring faithfulness of local explanations on tabular classification problems -- and shows that the current metrics don't agree; leaving users unsure how to choose the most faithful explanations.
Authors: Egemen İşgüder, Özlem Durmaz İncel
Motion sensors integrated into wearable and mobile devices provide valuable information about the device users. Machine learning and, recently, deep learning techniques have been used to characterize sensor data. Mostly, a single task, such as recognition of activities, is targeted, and the data is processed centrally at a server or in a cloud environment. However, the same sensor data can be utilized for multiple tasks and distributed machine-learning techniques can be used without the requirement of the transmission of data to a centre. This paper explores Federated Transfer Learning in a Multi-Task manner for both sensor-based human activity recognition and device position identification tasks. The OpenHAR framework is used to train the models, which contains ten smaller datasets. The aim is to obtain model(s) applicable for both tasks in different datasets, which may include only some label types. Multiple experiments are carried in the Flower federated learning environment using the DeepConvLSTM architecture. Results are presented for federated and centralized versions under different parameters and restrictions. By utilizing transfer learning and training a task-specific and personalized federated model, we obtained a similar accuracy with training each client individually and higher accuracy than a fully centralized approach.
Authors: Dota Tianai Dong, Mariya Toneva
Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn from vision, text, and sound over time have made some progress toward this goal, but the degree to which these models integrate information from modalities still remains unclear. In this work, we present a promising approach for probing a pre-trained multimodal video transformer model by leveraging neuroscientific evidence of multimodal information processing in the brain. Using brain recordings of participants watching a popular TV show, we analyze the effects of multi-modal connections and interactions in a pre-trained multi-modal video transformer on the alignment with uni- and multi-modal brain regions. We find evidence that vision enhances masked prediction performance during language processing, providing support that cross-modal representations in models can benefit individual modalities. However, we don't find evidence of brain-relevant information captured by the joint multi-modal transformer representations beyond that captured by all of the individual modalities. We finally show that the brain alignment of the pre-trained joint representation can be improved by fine-tuning using a task that requires vision-language inferences. Overall, our results paint an optimistic picture of the ability of multi-modal transformers to integrate vision and language in partially brain-relevant ways but also show that improving the brain alignment of these models may require new approaches.
Authors: Tomer Bar Nathan, Gilad Deutch, Nadav Magar, Guy Dar
In-context learning (ICL) has shown impressive results in few-shot learning tasks, yet its underlying mechanism is still not fully understood. Recent works suggest that ICL can be thought of as a gradient descent (GD) based optimization process. While promising, these results mainly focus on simplified settings of ICL and provide only a preliminary evaluation of the similarities between the two methods. In this work, we revisit the comparison between ICL and GD-based finetuning and study what properties of ICL an equivalent process must follow. We highlight a major difference in the flow of information between ICL and standard finetuning. Namely, ICL can only rely on information from lower layers at every point, while finetuning depends on loss gradients from deeper layers. We refer to this discrepancy as Layer Causality and show that a layer causal variant of the finetuning process aligns with ICL on par with vanilla finetuning and is even better in most cases across relevant metrics. To the best of our knowledge, this is the first work to discuss this discrepancy explicitly and suggest a solution that tackles this problem with minimal changes.
Authors: Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user. Many solutions are proposed to resolve this catastrophic forgetting in a centralized setting. However, they do not apply directly to FL because of its unique complexities, such as privacy concerns and resource limitations. To overcome these challenges, this paper presents a framework for \textbf{federated class incremental learning} that utilizes a generative model to synthesize samples from past distributions. This data can be later exploited alongside the training data to mitigate catastrophic forgetting. To preserve privacy, the generative model is trained on the server using data-free methods at the end of each task without requesting data from clients. Moreover, our solution does not demand the users to store old data or models, which gives them the freedom to join/leave the training at any time. Additionally, we introduce SuperImageNet, a new regrouping of the ImageNet dataset specifically tailored for federated continual learning. We demonstrate significant improvements compared to existing baselines through extensive experiments on multiple datasets.
Authors: Anders Vestergaard Nørskov, Alexander Neergaard Zahid, Morten Mørup
Electroencephalography (EEG) is a prominent non-invasive neuroimaging technique providing insights into brain function. Unfortunately, EEG data exhibit a high degree of noise and variability across subjects hampering generalizable signal extraction. Therefore, a key aim in EEG analysis is to extract the underlying neural activation (content) as well as to account for the individual subject variability (style). We hypothesize that the ability to convert EEG signals between tasks and subjects requires the extraction of latent representations accounting for content and style. Inspired by recent advancements in voice conversion technologies, we propose a novel contrastive split-latent permutation autoencoder (CSLP-AE) framework that directly optimizes for EEG conversion. Importantly, the latent representations are guided using contrastive learning to promote the latent splits to explicitly represent subject (style) and task (content). We contrast CSLP-AE to conventional supervised, unsupervised (AE), and self-supervised (contrastive learning) training and find that the proposed approach provides favorable generalizable characterizations of subject and task. Importantly, the procedure also enables zero-shot conversion between unseen subjects. While the present work only considers conversion of EEG, the proposed CSLP-AE provides a general framework for signal conversion and extraction of content (task activation) and style (subject variability) components of general interest for the modeling and analysis of biological signals.
Authors: Paula Chen, Tingwei Meng, Zongren Zou, Jérôme Darbon, George Em Karniadakis
We address two major challenges in scientific machine learning (SciML): interpretability and computational efficiency. We increase the interpretability of certain learning processes by establishing a new theoretical connection between optimization problems arising from SciML and a generalized Hopf formula, which represents the viscosity solution to a Hamilton-Jacobi partial differential equation (HJ PDE) with time-dependent Hamiltonian. Namely, we show that when we solve certain regularized learning problems with integral-type losses, we actually solve an optimal control problem and its associated HJ PDE with time-dependent Hamiltonian. This connection allows us to reinterpret incremental updates to learned models as the evolution of an associated HJ PDE and optimal control problem in time, where all of the previous information is intrinsically encoded in the solution to the HJ PDE. As a result, existing HJ PDE solvers and optimal control algorithms can be reused to design new efficient training approaches for SciML that naturally coincide with the continual learning framework, while avoiding catastrophic forgetting. As a first exploration of this connection, we consider the special case of linear regression and leverage our connection to develop a new Riccati-based methodology for solving these learning problems that is amenable to continual learning applications. We also provide some corresponding numerical examples that demonstrate the potential computational and memory advantages our Riccati-based approach can provide.
Authors: Sishun Liu, Ke Deng, Yan Wang, Xiuzhen Zhang
Explainability of machine learning models is mandatory when researchers introduce these commonly believed black boxes to real-world tasks, especially high-stakes ones. In this paper, we build a machine learning system to automatically generate explanations of happened events from history by \gls{ca} based on the \acrfull{tpp}. Specifically, we propose a new task called \acrfull{ehd}. This task requires a model to distill as few events as possible from observed history. The target is that the event distribution conditioned on left events predicts the observed future noticeably worse. We then regard distilled events as the explanation for the future. To efficiently solve \acrshort{ehd}, we rewrite the task into a \gls{01ip} and directly estimate the solution to the program by a model called \acrfull{model}. This work fills the gap between our task and existing works, which only spot the difference between factual and counterfactual worlds after applying a predefined modification to the environment. Experiment results on Retweet and StackOverflow datasets prove that \acrshort{model} significantly outperforms other \acrshort{ehd} baselines and can reveal the rationale underpinning real-world processes.
Authors: Deepak Akhare, Zeping Chen, Richard Gulotty, Tengfei Luo, Jian-Xun Wang
Chemical vapor infiltration (CVI) is a widely adopted manufacturing technique used in producing carbon-carbon and carbon-silicon carbide composites. These materials are especially valued in the aerospace and automotive industries for their robust strength and lightweight characteristics. The densification process during CVI critically influences the final performance, quality, and consistency of these composite materials. Experimentally optimizing the CVI processes is challenging due to long experimental time and large optimization space. To address these challenges, this work takes a modeling-centric approach. Due to the complexities and limited experimental data of the isothermal CVI densification process, we have developed a data-driven predictive model using the physics-integrated neural differentiable (PiNDiff) modeling framework. An uncertainty quantification feature has been embedded within the PiNDiff method, bolstering the model's reliability and robustness. Through comprehensive numerical experiments involving both synthetic and real-world manufacturing data, the proposed method showcases its capability in modeling densification during the CVI process. This research highlights the potential of the PiNDiff framework as an instrumental tool for advancing our understanding, simulation, and optimization of the CVI manufacturing process, particularly when faced with sparse data and an incomplete description of the underlying physics.
Authors: Yangfan Li, Satyajit Mojumder, Ye Lu, Abdullah Al Amin, Jiachen Guo, Xiaoyu Xie, Wei Chen, Gregory J. Wagner, Jian Cao, Wing Kam Liu
A digital twin (DT) is a virtual representation of physical process, products and/or systems that requires a high-fidelity computational model for continuous update through the integration of sensor data and user input. In the context of laser powder bed fusion (LPBF) additive manufacturing, a digital twin of the manufacturing process can offer predictions for the produced parts, diagnostics for manufacturing defects, as well as control capabilities. This paper introduces a parameterized physics-based digital twin (PPB-DT) for the statistical predictions of LPBF metal additive manufacturing process. We accomplish this by creating a high-fidelity computational model that accurately represents the melt pool phenomena and subsequently calibrating and validating it through controlled experiments. In PPB-DT, a mechanistic reduced-order method-driven stochastic calibration process is introduced, which enables the statistical predictions of the melt pool geometries and the identification of defects such as lack-of-fusion porosity and surface roughness, specifically for diagnostic applications. Leveraging data derived from this physics-based model and experiments, we have trained a machine learning-based digital twin (PPB-ML-DT) model for predicting, monitoring, and controlling melt pool geometries. These proposed digital twin models can be employed for predictions, control, optimization, and quality assurance within the LPBF process, ultimately expediting product development and certification in LPBF-based metal additive manufacturing.
Authors: Jo-Chun Chen, Hung-Hsuan Chen
Spectral clustering is a popular method for effectively clustering nonlinearly separable data. However, computational limitations, memory requirements, and the inability to perform incremental learning challenge its widespread application. To overcome these limitations, this paper introduces a novel approach called parametric spectral clustering (PSC). By extending the capabilities of spectral clustering, PSC addresses the challenges associated with big data and real-time scenarios and enables efficient incremental clustering with new data points. Experimental evaluations conducted on various open datasets demonstrate the superiority of PSC in terms of computational efficiency while achieving clustering quality mostly comparable to standard spectral clustering. The proposed approach has significant potential for incremental and real-time data analysis applications, facilitating timely and accurate clustering in dynamic and evolving datasets. The findings of this research contribute to the advancement of clustering techniques and open new avenues for efficient and effective data analysis. We publish the experimental code at https://github.com/109502518/PSC_BigData.
Authors: Harshavardhan Kamarthi, B. Aditya Prakash
Providing accurate and reliable predictions about the future of an epidemic is an important problem for enabling informed public health decisions. Recent works have shown that leveraging data-driven solutions that utilize advances in deep learning methods to learn from past data of an epidemic often outperform traditional mechanistic models. However, in many cases, the past data is sparse and may not sufficiently capture the underlying dynamics. While there exists a large amount of data from past epidemics, leveraging prior knowledge from time-series data of other diseases is a non-trivial challenge. Motivated by the success of pre-trained models in language and vision tasks, we tackle the problem of pre-training epidemic time-series models to learn from multiple datasets from different diseases and epidemics. We introduce Pre-trained Epidemic Time-Series Models (PEMS) that learn from diverse time-series datasets of a variety of diseases by formulating pre-training as a set of self-supervised learning (SSL) tasks. We tackle various important challenges specific to pre-training for epidemic time-series such as dealing with heterogeneous dynamics and efficiently capturing useful patterns from multiple epidemic datasets by carefully designing the SSL tasks to learn important priors about the epidemic dynamics that can be leveraged for fine-tuning to multiple downstream tasks. The resultant PEM outperforms previous state-of-the-art methods in various downstream time-series tasks across datasets of varying seasonal patterns, geography, and mechanism of contagion including the novel Covid-19 pandemic unseen in pre-trained data with better efficiency using smaller fraction of datasets.
Authors: Dhruv Agarwal, Rajarshi Das, Sopan Khosla, Rashmi Gangadharaiah
We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems. BYOKG draws inspiration from the remarkable ability of humans to comprehend information present in an unseen KG through exploration -- starting at random nodes, inspecting the labels of adjacent nodes and edges, and combining them with their prior world knowledge. In BYOKG, exploration leverages an LLM-backed symbolic agent that generates a diverse set of query-program exemplars, which are then used to ground a retrieval-augmented reasoning procedure to predict programs for arbitrary questions. BYOKG is effective over both small- and large-scale graphs, showing dramatic gains in QA accuracy over a zero-shot baseline of 27.89 and 58.02 F1 on GrailQA and MetaQA, respectively. On GrailQA, we further show that our unsupervised BYOKG outperforms a supervised in-context learning method, demonstrating the effectiveness of exploration. Lastly, we find that performance of BYOKG reliably improves with continued exploration as well as improvements in the base LLM, notably outperforming a state-of-the-art fine-tuned model by 7.08 F1 on a sub-sampled zero-shot split of GrailQA.
Authors: Yilin Wang, Xinyi Hu, Matthew R. Gormley
Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of information. Previous studies have shown that incorporating multiple input granularities improves model generalization, yet very few of them outputs useful representations for each granularity. In this paper, we introduce the entanglement model, aiming to combine character and subword language models. Inspired by vision-language models, our model treats characters and subwords as separate modalities, and it generates mutually informed representations for both granularities as output. We evaluate our model on text classification, named entity recognition, and POS-tagging tasks. Notably, the entanglement model outperforms its backbone language models, particularly in the presence of noisy texts and low-resource languages. Furthermore, the entanglement model even outperforms larger pre-trained models on all English sequence labeling tasks and classification tasks. Our anonymized code is available at https://anonymous.4open.science/r/noisy-IE-A673
Authors: Thao Nguyen, Simon Kornblith
Neural network representations contain structure beyond what was present in the training labels. For instance, representations of images that are visually or semantically similar tend to lie closer to each other than to dissimilar images, regardless of their labels. Clustering these representations can thus provide insights into dataset properties as well as the network internals. In this work, we study how the many design choices involved in neural network training affect the clusters formed in the hidden representations. To do so, we establish an evaluation setup based on the BREEDS hierarchy, for the task of subclass clustering after training models with only superclass information. We isolate the training dataset and architecture as important factors affecting clusterability. Datasets with labeled classes consisting of unrelated subclasses yield much better clusterability than those following a natural hierarchy. When using pretrained models to cluster representations on downstream datasets, models pretrained on subclass labels provide better clusterability than models pretrained on superclass labels, but only when there is a high degree of domain overlap between the pretraining and downstream data. Architecturally, we find that normalization strategies affect which layers yield the best clustering performance, and, surprisingly, Vision Transformers attain lower subclass clusterability than ResNets.
Authors: Onur Poyraz, Pekka Marttinen
Analysis of multivariate healthcare time series data is inherently challenging: irregular sampling, noisy and missing values, and heterogeneous patient groups with different dynamics violating exchangeability. In addition, interpretability and quantification of uncertainty are critically important. Here, we propose a novel class of models, a mixture of coupled hidden Markov models (M-CHMM), and demonstrate how it elegantly overcomes these challenges. To make the model learning feasible, we derive two algorithms to sample the sequences of the latent variables in the CHMM: samplers based on (i) particle filtering and (ii) factorized approximation. Compared to existing inference methods, our algorithms are computationally tractable, improve mixing, and allow for likelihood estimation, which is necessary to learn the mixture model. Experiments on challenging real-world epidemiological and semi-synthetic data demonstrate the advantages of the M-CHMM: improved data fit, capacity to efficiently handle missing and noisy measurements, improved prediction accuracy, and ability to identify interpretable subsets in the data.
Authors: Young-Seok Kweon, Gi-Hwan Shin, Heon-Gyu Kwak, Ha-Na Jo, Seong-Whan Lee
Polysomnography (PSG) is an indispensable diagnostic tool in sleep medicine, essential for identifying various sleep disorders. By capturing physiological signals, including EEG, EOG, EMG, and cardiorespiratory metrics, PSG presents a patient's sleep architecture. However, its dependency on complex equipment and expertise confines its use to specialized clinical settings. Addressing these limitations, our study aims to perform PSG by developing a system that requires only a single EEG measurement. We propose a novel system capable of reconstructing multi-signal PSG from a single-channel EEG based on a masked autoencoder. The masked autoencoder was trained and evaluated using the Sleep-EDF-20 dataset, with mean squared error as the metric for assessing the similarity between original and reconstructed signals. The model demonstrated proficiency in reconstructing multi-signal data. Our results present promise for the development of more accessible and long-term sleep monitoring systems. This suggests the expansion of PSG's applicability, enabling its use beyond the confines of clinics.
Authors: Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Xuezhou Zhang, Shuai Li
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the loss functions may change adversarially but are revealed to the learner at the end of each episode. We propose a policy optimization-based algorithm POLO, and we prove that it attains the $\widetilde{O}(K^{\frac{5}{6}}A^{\frac{1}{2}}d\ln(1+M)/(1-\gamma)^2)$ regret guarantee, where $d$ is rank of the transition kernel (and hence the dimension of the unknown representations), $A$ is the cardinality of the action space, $M$ is the cardinality of the model class, and $\gamma$ is the discounted factor. Notably, our algorithm is oracle-efficient and has a regret guarantee with no dependence on the size of potentially arbitrarily large state space. Furthermore, we also prove an $\Omega(\frac{\gamma^2}{1-\gamma} \sqrt{d A K})$ regret lower bound for this problem, showing that low-rank MDPs are statistically more difficult to learn than linear MDPs in the regret minimization setting. To the best of our knowledge, we present the first algorithm that interleaves representation learning, exploration, and exploitation to achieve the sublinear regret guarantee for RL with nonlinear function approximation and adversarial losses.
Authors: Sudev Kumar Padhi, Mohit Kumar, Debanka Giri, Subidh Ali
Slip and crumple detection is essential for performing robust manipulation tasks with a robotic hand (RH) like remote surgery. It has been one of the challenging problems in the robotics manipulation community. In this work, we propose a technique based on machine learning (ML) based techniques to detect the slip, and crumple as well as the shape of an object that is currently held in the robotic hand. We proposed ML model will detect the slip, crumple, and shape using the force/torque exerted and the angular positions of the actuators present in the RH. The proposed model would be integrated into the loop of a robotic hand(RH) and haptic glove(HG). This would help us to reduce the latency in case of teleoperation
Authors: Han Gao, Xu Han, Xiantao Fan, Luning Sun, Li-Ping Liu, Lian Duan, Jian-Xun Wang
Turbulent flows have historically presented formidable challenges to predictive computational modeling. Traditional numerical simulations often require vast computational resources, making them infeasible for numerous engineering applications. As an alternative, deep learning-based surrogate models have emerged, offering data-drive solutions. However, these are typically constructed within deterministic settings, leading to shortfall in capturing the innate chaotic and stochastic behaviors of turbulent dynamics. We introduce a novel generative framework grounded in probabilistic diffusion models for versatile generation of spatiotemporal turbulence. Our method unifies both unconditional and conditional sampling strategies within a Bayesian framework, which can accommodate diverse conditioning scenarios, including those with a direct differentiable link between specified conditions and generated unsteady flow outcomes, and scenarios lacking such explicit correlations. A notable feature of our approach is the method proposed for long-span flow sequence generation, which is based on autoregressive gradient-based conditional sampling, eliminating the need for cumbersome retraining processes. We showcase the versatile turbulence generation capability of our framework through a suite of numerical experiments, including: 1) the synthesis of LES simulated instantaneous flow sequences from URANS inputs; 2) holistic generation of inhomogeneous, anisotropic wall-bounded turbulence, whether from given initial conditions, prescribed turbulence statistics, or entirely from scratch; 3) super-resolved generation of high-speed turbulent boundary layer flows from low-resolution data across a range of input resolutions. Collectively, our numerical experiments highlight the merit and transformative potential of the proposed methods, making a significant advance in the field of turbulence generation.
Authors: Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, Le Hou
One core capability of Large Language Models (LLMs) is to follow natural language instructions. However, the evaluation of such abilities is not standardized: Human evaluations are expensive, slow, and not objectively reproducible, while LLM-based auto-evaluation is potentially biased or limited by the ability of the evaluator LLM. To overcome these issues, we introduce Instruction-Following Eval (IFEval) for large language models. IFEval is a straightforward and easy-to-reproduce evaluation benchmark. It focuses on a set of "verifiable instructions" such as "write in more than 400 words" and "mention the keyword of AI at least 3 times". We identified 25 types of those verifiable instructions and constructed around 500 prompts, with each prompt containing one or more verifiable instructions. We show evaluation results of two widely available LLMs on the market. Our code and data can be found at https://github.com/google-research/google-research/tree/master/instruction_following_eval
Authors: Garima Agrawal, Tharindu Kumarage, Zeyad Alghami, Huan Liu
The contemporary LLMs are prone to producing hallucinations, stemming mainly from the knowledge gaps within the models. To address this critical limitation, researchers employ diverse strategies to augment the LLMs by incorporating external knowledge, aiming to reduce hallucinations and enhance reasoning accuracy. Among these strategies, leveraging knowledge graphs as a source of external information has demonstrated promising results. In this survey, we conduct a comprehensive review of these knowledge-graph-based knowledge augmentation techniques in LLMs, focusing on their efficacy in mitigating hallucinations. We systematically categorize these methods into three overarching groups, offering both methodological comparisons and empirical evaluations of their performance. Lastly, the paper explores the challenges associated with these techniques and outlines potential avenues for future research in this emerging field.
Authors: Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, Jingren Zhou
Recently, instruction-following audio-language models have received broad attention for audio interaction with humans. However, the absence of pre-trained audio models capable of handling diverse audio types and tasks has hindered progress in this field. Consequently, most existing works have only been able to support a limited range of interaction capabilities. In this paper, we develop the Qwen-Audio model and address this limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types, such as human speech, natural sounds, music, and songs, to facilitate universal audio understanding abilities. However, directly co-training all tasks and datasets can lead to interference issues, as the textual labels associated with different datasets exhibit considerable variations due to differences in task focus, language, granularity of annotation, and text structure. To overcome the one-to-many interference, we carefully design a multi-task training framework by conditioning on a sequence of hierarchical tags to the decoder for encouraging knowledge sharing and avoiding interference through shared and specified tags respectively. Remarkably, Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning, surpassing its counterparts. Building upon the capabilities of Qwen-Audio, we further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.
Authors: Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges, particularly in safety-critical applications like autonomous driving. Current approaches, such as introducing distortions during training, fall short in addressing unforeseen corruptions. This paper proposes an innovative adversarial contrastive learning framework to enhance neural network robustness simultaneously against adversarial attacks and common corruptions. By generating instance-wise adversarial examples and optimizing contrastive loss, our method fosters representations that resist adversarial perturbations and remain robust in real-world scenarios. Subsequent contrastive learning then strengthens the similarity between clean samples and their adversarial counterparts, fostering representations resistant to both adversarial attacks and common distortions. By focusing on improving performance under adversarial and real-world conditions, our approach aims to bolster the robustness of neural networks in safety-critical applications, such as autonomous vehicles navigating unpredictable weather conditions. We anticipate that this framework will contribute to advancing the reliability of neural networks in challenging environments, facilitating their widespread adoption in mission-critical scenarios.
Authors: Yige Zhao, Jianxiang Yu, Yao Cheng, Chengcheng Yu, Yiding Liu, Xiang Li, Shuaiqiang Wang
Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) ignore the problems of missing attributes, inaccurate attributes and scarce labels for nodes, which limits their expressiveness. In this paper, we propose a generative self-supervised model SHAVA to address these issues simultaneously. Specifically, SHAVA first initializes all the nodes in the graph with a low-dimensional representation matrix. After that, based on the variational graph autoencoder framework, SHAVA learns both node-level and attribute-level embeddings in the encoder, which can provide fine-grained semantic information to construct node attributes. In the decoder, SHAVA reconstructs both links and attributes. Instead of directly reconstructing raw features for attributed nodes, SHAVA generates the initial low-dimensional representation matrix for all the nodes, based on which raw features of attributed nodes are further reconstructed to leverage accurate attributes. In this way, SHAVA can not only complete informative features for non-attributed nodes, but rectify inaccurate ones for attributed nodes. Finally, we conduct extensive experiments to show the superiority of SHAVA in tackling HINs with missing and inaccurate attributes.
Authors: Mohammadreza Doostmohammadian, Wei Jiang, Muwahida Liaquat, Alireza Aghasi, Houman Zarrabi
We consider a discrete-time model of continuous-time distributed optimization over dynamic directed-graphs (digraphs) with applications to distributed learning. Our optimization algorithm works over general strongly connected dynamic networks under switching topologies, e.g., in mobile multi-agent systems and volatile networks due to link failures. Compared to many existing lines of work, there is no need for bi-stochastic weight designs on the links. The existing literature mostly needs the link weights to be stochastic using specific weight-design algorithms needed both at the initialization and at all times when the topology of the network changes. This paper eliminates the need for such algorithms and paves the way for distributed optimization over time-varying digraphs. We derive the bound on the gradient-tracking step-size and discrete time-step for convergence and prove dynamic stability using arguments from consensus algorithms, matrix perturbation theory, and Lyapunov theory. This work, particularly, is an improvement over existing stochastic-weight undirected networks in case of link removal or packet drops. This is because the existing literature may need to rerun time-consuming and computationally complex algorithms for stochastic design, while the proposed strategy works as long as the underlying network is weight-symmetric and balanced. The proposed optimization framework finds applications to distributed classification and learning.
Authors: Adharsh Kamath, Aditya Senthilnathan, Saikat Chakraborty, Pantazis Deligiannis, Shuvendu K. Lahiri, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma
Loop invariants are fundamental to reasoning about programs with loops. They establish properties about a given loop's behavior. When they additionally are inductive, they become useful for the task of formal verification that seeks to establish strong mathematical guarantees about program's runtime behavior. The inductiveness ensures that the invariants can be checked locally without consulting the entire program, thus are indispensable artifacts in a formal proof of correctness. Finding inductive loop invariants is an undecidable problem, and despite a long history of research towards practical solutions, it remains far from a solved problem. This paper investigates the capabilities of the Large Language Models (LLMs) in offering a new solution towards this old, yet important problem. To that end, we first curate a dataset of verification problems on programs with loops. Next, we design a prompt for exploiting LLMs, obtaining inductive loop invariants, that are checked for correctness using sound symbolic tools. Finally, we explore the effectiveness of using an efficient combination of a symbolic tool and an LLM on our dataset and compare it against a purely symbolic baseline. Our results demonstrate that LLMs can help improve the state-of-the-art in automated program verification.
Authors: Mahdi Teimouri
Over the last decades, the family of $\alpha$-stale distributions has proven to be useful for modelling in telecommunication systems. Particularly, in the case of radar applications, finding a fast and accurate estimation for the amplitude density function parameters appears to be very important. In this work, the maximum likelihood estimator (MLE) is proposed for parameters of the amplitude distribution. To do this, the amplitude data are \emph{projected} on the horizontal and vertical axes using two simple transformations. It is proved that the \emph{projected} data follow a zero-location symmetric $\alpha$-stale distribution for which the MLE can be computed quite fast. The average of computed MLEs based on two \emph{projections} is considered as estimator for parameters of the amplitude distribution. Performance of the proposed \emph{projection} method is demonstrated through simulation study and analysis of two sets of real radar data.
Authors: Kamel Alrashedy
Large language models (LLMs) such as GPT-3.5 and CodeLlama are powerful models for code generation and understanding. Fine-tuning these models comes with a high computational cost and requires a large labeled dataset. Alternatively, in-context learning techniques allow models to learn downstream tasks with only a few examples. Recently, researchers have shown how in-context learning performs well in bug detection and repair. In this paper, we propose code-pair classification task in which both the buggy and non-buggy versions are given to the model, and the model identifies the buggy ones. We evaluate our task in real-world dataset of bug detection and two most powerful LLMs. Our experiments indicate that an LLM can often pick the buggy from the non-buggy version of the code, and the code-pair classification task is much easier compared to be given a snippet and deciding if and where a bug exists.
Authors: Thomas Christie, Yu He
Graph neural networks operate on graph-structured data via exchanging messages along edges. One limitation of this message passing paradigm is the over-squashing problem. Over-squashing occurs when messages from a node's expanded receptive field are compressed into fixed-size vectors, potentially causing information loss. To address this issue, recent works have explored using expander graphs, which are highly-connected sparse graphs with low diameters, to perform message passing. However, current methods on expander graph propagation only consider pair-wise interactions, ignoring higher-order structures in complex data. To explore the benefits of capturing these higher-order correlations while still leveraging expander graphs, we introduce higher-order expander graph propagation. We propose two methods for constructing bipartite expanders and evaluate their performance on both synthetic and real-world datasets.
Authors: Martin Cubaud (LaSTIG), Arnaud Le Bris (LaSTIG), Laurence Jolivet (LaSTIG), Ana-Maria Olteanu-Raimond (LaSTIG)
Accurate land use maps, describing the territory from an anthropic utilisation point of view, are useful tools for land management and planning. To produce them, the use of optical images alone remains limited. It is therefore necessary to make use of several heterogeneous sources, each carrying complementary or contradictory information due to their imperfections or their different specifications. This study compares two different approaches i.e. a pre-classification and a post-classification fusion approach for combining several sources of spatial data in the context of land use classification. The approaches are applied on authoritative land use data located in the Gers department in the southwest of France. Pre-classification fusion, while not explicitly modeling imperfections, has the best final results, reaching an overall accuracy of 97% and a macro-mean F1 score of 88%.
Authors: Zhilin Zhao, Longbing Cao, Yixuan Zhang
Out-of-distribution (OOD) detection is essential in identifying test samples that deviate from the in-distribution (ID) data upon which a standard network is trained, ensuring network robustness and reliability. This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network. This framework harnesses OOD-sensitive knowledge from the standard network to craft a binary classifier adept at distinguishing between ID and OOD samples. To accomplish this, we introduce Confidence Amendment (CA), an innovative methodology that transforms an OOD sample into an ID one while progressively amending prediction confidence derived from the standard network. This approach enables the simultaneous synthesis of both ID and OOD samples, each accompanied by an adjusted prediction confidence, thereby facilitating the training of a binary classifier sensitive to OOD. Theoretical analysis provides bounds on the generalization error of the binary classifier, demonstrating the pivotal role of confidence amendment in enhancing OOD sensitivity. Extensive experiments spanning various datasets and network architectures confirm the efficacy of the proposed method in detecting OOD samples.
Authors: Jessica Ojo, Kelechi Ogueji, Pontus Stenetorp, David I. Adelani
Recent advancements in natural language processing have led to the proliferation of large language models (LLMs). These models have been shown to yield good performance, using in-context learning, even on unseen tasks and languages. Additionally, they have been widely adopted as language-model-as-a-service commercial APIs like GPT-4 API. However, their performance on African languages is largely unknown. We present an analysis of three popular large language models (mT0, LLaMa 2, and GPT-4) on five tasks (news topic classification, sentiment classification, machine translation, question answering, and named entity recognition) across 30 African languages, spanning different language families and geographical regions. Our results suggest that all LLMs produce below-par performance on African languages, and there is a large gap in performance compared to high-resource languages like English most tasks. We find that GPT-4 has an average or impressive performance on classification tasks but very poor results on generative tasks like machine translation. Surprisingly, we find that mT0 had the best overall on cross-lingual QA, better than the state-of-the-art supervised model (i.e. fine-tuned mT5) and GPT-4 on African languages. Overall, LLaMa 2 records the worst performance due to its limited multilingual capabilities and English-centric pre-training corpus. In general, our findings present a call-to-action to ensure African languages are well represented in large language models, given their growing popularity.
Authors: Cong Guo, Chun Liu, Wei Yang
Many datasets suffer from missing values due to various reasons,which not only increases the processing difficulty of related tasks but also reduces the accuracy of classification. To address this problem, the mainstream approach is to use missing value imputation to complete the dataset. Existing imputation methods estimate the missing parts based on the observed values in the original feature space, and they treat all features as equally important during data completion, while in fact different features have different importance. Therefore, we have designed an imputation method that considers feature importance. This algorithm iteratively performs matrix completion and feature importance learning, and specifically, matrix completion is based on a filling loss that incorporates feature importance. Our experimental analysis involves three types of datasets: synthetic datasets with different noisy features and missing values, real-world datasets with artificially generated missing values, and real-world datasets originally containing missing values. The results on these datasets consistently show that the proposed method outperforms the existing five imputation algorithms.To the best of our knowledge, this is the first work that considers feature importance in the imputation model.
Authors: Maximilian Stahlke, George Yammine, Tobias Feigl, Bjoern M. Eskofier, Christopher Mutschler
Fingerprint-based localization improves the positioning performance in challenging, non-line-of-sight (NLoS) dominated indoor environments. However, fingerprinting models require an expensive life-cycle management including recording and labeling of radio signals for the initial training and regularly at environmental changes. Alternatively, channel-charting avoids this labeling effort as it implicitly associates relative coordinates to the recorded radio signals. Then, with reference real-world coordinates (positions) we can use such charts for positioning tasks. However, current channel-charting approaches lag behind fingerprinting in their positioning accuracy and still require reference samples for localization, regular data recording and labeling to keep the models up to date. Hence, we propose a novel framework that does not require reference positions. We only require information from velocity information, e.g., from pedestrian dead reckoning or odometry to model the channel charts, and topological map information, e.g., a building floor plan, to transform the channel charts into real coordinates. We evaluate our approach on two different real-world datasets using 5G and distributed single-input/multiple-output system (SIMO) radio systems. Our experiments show that even with noisy velocity estimates and coarse map information, we achieve similar position accuracies
Authors: Xinyi Hu, Jasper C.H. Lee, Jimmy H.M. Lee
Consider the setting of constrained optimization, with some parameters unknown at solving time and requiring prediction from relevant features. Predict+Optimize is a recent framework for end-to-end training supervised learning models for such predictions, incorporating information about the optimization problem in the training process in order to yield better predictions in terms of the quality of the predicted solution under the true parameters. Almost all prior works have focused on the special case where the unknowns appear only in the optimization objective and not the constraints. Hu et al.~proposed the first adaptation of Predict+Optimize to handle unknowns appearing in constraints, but the framework has somewhat ad-hoc elements, and they provided a training algorithm only for covering and packing linear programs. In this work, we give a new \emph{simpler} and \emph{more powerful} framework called \emph{Two-Stage Predict+Optimize}, which we believe should be the canonical framework for the Predict+Optimize setting. We also give a training algorithm usable for all mixed integer linear programs, vastly generalizing the applicability of the framework. Experimental results demonstrate the superior prediction performance of our training framework over all classical and state-of-the-art methods.
Authors: Tao Song, Ruizhi Hou, Lisong Dai, Lei Xiang
Image quality assessment (IQA) plays a critical role in optimizing radiation dose and developing novel medical imaging techniques in computed tomography (CT). Traditional IQA methods relying on hand-crafted features have limitations in summarizing the subjective perceptual experience of image quality. Recent deep learning-based approaches have demonstrated strong modeling capabilities and potential for medical IQA, but challenges remain regarding model generalization and perceptual accuracy. In this work, we propose a multi-scale distributions regression approach to predict quality scores by constraining the output distribution, thereby improving model generalization. Furthermore, we design a dual-branch alignment network to enhance feature extraction capabilities. Additionally, semi-supervised learning is introduced by utilizing pseudo-labels for unlabeled data to guide model training. Extensive qualitative experiments demonstrate the effectiveness of our proposed method for advancing the state-of-the-art in deep learning-based medical IQA. Code is available at: https://github.com/zunzhumu/MD-IQA.
Authors: Vasilis Michalakopoulos, Sotiris Pelekis, Giorgos Kormpakis, Vagelis Karakolis, Spiros Mouzakitis, Dimitris Askounis
The analytical prediction of building energy performance in residential buildings based on the heat losses of its individual envelope components is a challenging task. It is worth noting that this field is still in its infancy, with relatively limited research conducted in this specific area to date, especially when it comes for data-driven approaches. In this paper we introduce a novel physics-informed neural network model for addressing this problem. Through the employment of unexposed datasets that encompass general building information, audited characteristics, and heating energy consumption, we feed the deep learning model with general building information, while the model's output consists of the structural components and several thermal properties that are in fact the basic elements of an energy performance certificate (EPC). On top of this neural network, a function, based on physics equations, calculates the energy consumption of the building based on heat losses and enhances the loss function of the deep learning model. This methodology is tested on a real case study for 256 buildings located in Riga, Latvia. Our investigation comes up with promising results in terms of prediction accuracy, paving the way for automated, and data-driven energy efficiency performance prediction based on basic properties of the building, contrary to exhaustive energy efficiency audits led by humans, which are the current status quo.
Authors: Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Nan Du
Human preference alignment is a crucial training step to improve the interaction quality of large language models (LLMs). Existing aligning methods depend on manually annotated preference data to guide the LLM optimization directions. However, in practice, continuously updating LLMs raises a distribution gap between model-generated samples and human-preferred responses, which hinders model fine-tuning efficiency. To mitigate this issue, previous methods require additional preference annotation on generated samples to adapt the shifted distribution, which consumes a large amount of annotation resources. Targeting more efficient human preference optimization, we propose an adversarial preference optimization (APO) framework, where the LLM agent and the preference model update alternatively via a min-max game. Without additional annotation, our APO method can make a self-adaption to the generation distribution gap through the adversarial learning process. In experiments, we empirically verify the effectiveness of APO in improving LLM's helpfulness and harmlessness compared with rejection sampling baselines.
Authors: Victor Croisfelt, Shashi Raj Pandey, Osvaldo Simeone, Petar Popovski
Consider an active learning setting in which a learner has a training set with few labeled examples and a pool set with many unlabeled inputs, while a remote teacher has a pre-trained model that is known to perform well for the learner's task. The learner actively transmits batches of unlabeled inputs to the teacher through a constrained communication channel for labeling. This paper addresses the following key questions: (i) Active batch selection: Which batch of inputs should be sent to the teacher to acquire the most useful information and thus reduce the number of required communication rounds? (ii) Batch encoding: How do we encode the batch of inputs for transmission to the teacher to reduce the communication resources required at each round? We introduce Communication-Constrained Bayesian Active Knowledge Distillation (CC-BAKD), a novel protocol that integrates Bayesian active learning with compression via a linear mix-up mechanism. Bayesian active learning selects the batch of inputs based on their epistemic uncertainty, addressing the "confirmation bias" that is known to increase the number of required communication rounds. Furthermore, the proposed mix-up compression strategy is integrated with the epistemic uncertainty-based active batch selection process to reduce the communication overhead per communication round.
Authors: Anton Simen Albino, Rodrigo Bloot, Otto M. Pires, Erick G. S. Nascimento
Quantum supervised learning, utilizing variational circuits, stands out as a promising technology for NISQ devices due to its efficiency in hardware resource utilization during the creation of quantum feature maps and the implementation of hardware-efficient ansatz with trainable parameters. Despite these advantages, the training of quantum models encounters challenges, notably the barren plateau phenomenon, leading to stagnation in learning during optimization iterations. This study proposes an innovative approach: an evolutionary-enhanced ansatz-free supervised learning model. In contrast to parametrized circuits, our model employs circuits with variable topology that evolves through an elitist method, mitigating the barren plateau issue. Additionally, we introduce a novel concept, the superposition of multi-hot encodings, facilitating the treatment of multi-classification problems. Our framework successfully avoids barren plateaus, resulting in enhanced model accuracy. Comparative analysis with variational quantum classifiers from the technology's state-of-the-art reveal a substantial improvement in training efficiency and precision. Furthermore, we conduct tests on a challenging dataset class, traditionally problematic for conventional kernel machines, demonstrating a potential alternative path for achieving quantum advantage in supervised learning for NISQ era.
Authors: Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch, Claire E. Stevenson
Analogical reasoning derives information from known relations and generalizes this information to similar yet unfamiliar situations. One of the first generalized ways in which deep learning models were able to solve verbal analogies was through vector arithmetic of word embeddings, essentially relating words that were mapped to a vector space (e.g., king - man + woman = __?). In comparison, most attempts to solve visual analogies are still predominantly task-specific and less generalizable. This project focuses on visual analogical reasoning and applies the initial generalized mechanism used to solve verbal analogies to the visual realm. Taking the Abstraction and Reasoning Corpus (ARC) as an example to investigate visual analogy solving, we use a variational autoencoder (VAE) to transform ARC items into low-dimensional latent vectors, analogous to the word embeddings used in the verbal approaches. Through simple vector arithmetic, underlying rules of ARC items are discovered and used to solve them. Results indicate that the approach works well on simple items with fewer dimensions (i.e., few colors used, uniform shapes), similar input-to-output examples, and high reconstruction accuracy on the VAE. Predictions on more complex items showed stronger deviations from expected outputs, although, predictions still often approximated parts of the item's rule set. Error patterns indicated that the model works as intended. On the official ARC paradigm, the model achieved a score of 2% (cf. current world record is 21%) and on ConceptARC it scored 8.8%. Although the methodology proposed involves basic dimensionality reduction techniques and standard vector arithmetic, this approach demonstrates promising outcomes on ARC and can easily be generalized to other abstract visual reasoning tasks.
Authors: Ozge Oztimur Karadag
Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than video frames. With the emergence of deep learning models, it has become very popular to represent the skeleton data in pseudo-image form and apply Convolutional Neural Networks for action recognition. Thereafter, studies concentrated on finding effective methods for forming pseudo-images. Recently, attention networks, more specifically transformers have provided promising results in various vision problems. In this study, the effectiveness of vision transformers for skeleton-based action recognition is examined and its robustness on the pseudo-image representation scheme is investigated. To this end, a three-level architecture, Act-VIT is proposed, which forms a set of pseudo images apply a classifier on each of the representation and combine their results to find the final action class. The classifiers of Act-VIT are first realized by CNNs and then by VITs and their performances are compared. Experimental studies reveal that the vision transformer is less sensitive to the initial pseudo-image representation compared to CNN. Nevertheless, even with the vision transformer, the recognition performance can be further improved by consensus of classifiers.
Authors: Arthur Douillard, Qixuan Feng, Andrei A. Rusu, Rachita Chhaparia, Yani Donchev, Adhiguna Kuncoro, Marc'Aurelio Ranzato, Arthur Szlam, Jiajun Shen
Large language models (LLM) have become a critical component in many applications of machine learning. However, standard approaches to training LLM require a large number of tightly interconnected accelerators, with devices exchanging gradients and other intermediate states at each optimization step. While it is difficult to build and maintain a single computing cluster hosting many accelerators, it might be easier to find several computing clusters each hosting a smaller number of devices. In this work, we propose a distributed optimization algorithm, Distributed Low-Communication (DiLoCo), that enables training of language models on islands of devices that are poorly connected. The approach is a variant of federated averaging, where the number of inner steps is large, the inner optimizer is AdamW, and the outer optimizer is Nesterov momentum. On the widely used C4 dataset, we show that DiLoCo on 8 workers performs as well as fully synchronous optimization while communicating 500 times less. DiLoCo exhibits great robustness to the data distribution of each worker. It is also robust to resources becoming unavailable over time, and vice versa, it can seamlessly leverage resources that become available during training.
Authors: Gabriel Rodrigues Palma, Conor Thornberry, Seán Commins, Rafael de Andrade Moral
Theta oscillations, ranging from 4-8 Hz, play a significant role in spatial learning and memory functions during navigation tasks. Frontal theta oscillations are thought to play an important role in spatial navigation and memory. Electroencephalography (EEG) datasets are very complex, making any changes in the neural signal related to behaviour difficult to interpret. However, multiple analytical methods are available to examine complex data structure, especially machine learning based techniques. These methods have shown high classification performance and the combination with feature engineering enhances the capability of these methods. This paper proposes using hidden Markov and linear mixed effects models to extract features from EEG data. Based on the engineered features obtained from frontal theta EEG data during a spatial navigation task in two key trials (first, last) and between two conditions (learner and non-learner), we analysed the performance of six machine learning methods (Polynomial Support Vector Machines, Non-linear Support Vector Machines, Random Forests, K-Nearest Neighbours, Ridge, and Deep Neural Networks) on classifying learner and non-learner participants. We also analysed how different standardisation methods used to pre-process the EEG data contribute to classification performance. We compared the classification performance of each trial with data gathered from the same subjects, including solely coordinate-based features, such as idle time and average speed. We found that more machine learning methods perform better classification using coordinate-based data. However, only deep neural networks achieved an area under the ROC curve higher than 80% using the theta EEG data alone. Our findings suggest that standardising the theta EEG data and using deep neural networks enhances the classification of learner and non-learner subjects in a spatial learning task.
Authors: Oscar Llorente, Péter Vaderna, Sándor Laki, Roland Kotroczó, Rita Csoma, János Márk Szalai-Gindl
Explainability in Graph Neural Networks (GNNs) is a new field growing in the last few years. In this publication we address the problem of determining how important is each neighbor for the GNN when classifying a node and how to measure the performance for this specific task. To do this, various known explainability methods are reformulated to get the neighbor importance and four new metrics are presented. Our results show that there is almost no difference between the explanations provided by gradient-based techniques in the GNN domain. In addition, many explainability techniques failed to identify important neighbors when GNNs without self-loops are used.
Authors: Vishwajit Kumar Vishnu, C. Chandra Sekhar
Training Memory-based transformers can require a large amount of memory and can be quite inefficient. We propose a novel two-phase training mechanism and a novel regularization technique to improve the training efficiency of memory-based transformers, which are often used for long-range context problems. For our experiments, we consider transformer-XL as our baseline model which is one of memorybased transformer models. We show that our resultant model, Skip Cross-head TransformerXL, outperforms the baseline on character level language modeling task with similar parameters and outperforms the baseline on word level language modelling task with almost 20% fewer parameters. Our proposed methods do not require any additional memory. We also demonstrate the effectiveness of our regularization mechanism on BERT which shows similar performance with reduction in standard deviation of scores of around 30% on multiple GLUE tasks.
Authors: Rui Lin, Jason Chun Lok Li, Jiajun Zhou, Binxiao Huang, Jie Ran, Ngai Wong
Most deep neural networks (DNNs) consist fundamentally of convolutional and/or fully connected layers, wherein the linear transform can be cast as the product between a filter matrix and a data matrix obtained by arranging feature tensors into columns. The lately proposed deformable butterfly (DeBut) decomposes the filter matrix into generalized, butterflylike factors, thus achieving network compression orthogonal to the traditional ways of pruning or low-rank decomposition. This work reveals an intimate link between DeBut and a systematic hierarchy of depthwise and pointwise convolutions, which explains the empirically good performance of DeBut layers. By developing an automated DeBut chain generator, we show for the first time the viability of homogenizing a DNN into all DeBut layers, thus achieving an extreme sparsity and compression. Various examples and hardware benchmarks verify the advantages of All-DeBut networks. In particular, we show it is possible to compress a PointNet to < 5% parameters with < 5% accuracy drop, a record not achievable by other compression schemes.
Authors: Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Vision transformers (ViTs) have recently been used for visual matching beyond object detection and segmentation. However, the original grid dividing strategy of ViTs neglects the spatial information of the keypoints, limiting the sensitivity to local information. Therefore, we propose \textbf{QueryTrans} (Query Transformer), which adopts a cross-attention module and keypoints-based center crop strategy for better spatial information extraction. We further integrate the graph attention module and devise a transformer-based graph matching approach \textbf{GMTR} (Graph Matching TRansformers) whereby the combinatorial nature of GM is addressed by a graph transformer neural GM solver. On standard GM benchmarks, GMTR shows competitive performance against the SOTA frameworks. Specifically, on Pascal VOC, GMTR achieves $\mathbf{83.6\%}$ accuracy, $\mathbf{0.9\%}$ higher than the SOTA framework. On Spair-71k, GMTR shows great potential and outperforms most of the previous works. Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80.1\%$ to $\mathbf{83.3\%}$, and BBGM from $79.0\%$ to $\mathbf{84.5\%}$. On Spair-71k, QueryTrans improves NGMv2 from $80.6\%$ to $\mathbf{82.5\%}$, and BBGM from $82.1\%$ to $\mathbf{83.9\%}$. Source code will be made publicly available.
Authors: G. N. Kimani, P. Oluwadara, P. Fashingabo, M. Busogi, E. Luhanga, K. Sowon, L. Chacha ((1) CyLab-Africa / Upanzi Network, (2) Carnegie Mellon University Africa and (3) Carnegie Mellon University Pittsburgh)
Traditional animal identification methods such as ear-tagging, ear notching, and branding have been effective but pose risks to the animal and have scalability issues. Electrical methods offer better tracking and monitoring but require specialized equipment and are susceptible to attacks. Biometric identification using time-immutable dermatoglyphic features such as muzzle prints and iris patterns is a promising solution. This project explores cattle identification using 4923 muzzle images collected from 268 beef cattle. Two deep learning classification models are implemented - wide ResNet50 and VGG16\_BN and image compression is done to lower the image quality and adapt the models to work for the African context. From the experiments run, a maximum accuracy of 99.5\% is achieved while using the wide ResNet50 model with a compression retaining 25\% of the original image. From the study, it is noted that the time required by the models to train and converge as well as recognition time are dependent on the machine used to run the model.
Authors: Cécile Trottet, Manuel Schürch, Ahmed Allam, Imon Barua, Liubov Petelytska, Oliver Distler, Anna-Maria Hoffmann-Vold, Michael Krauthammer, the EUSTAR collaborators
In this paper, we propose a deep generative time series approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories. We aim to find meaningful temporal latent representations of an underlying generative process that explain the observed disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical concepts. By combining the generative approach with medical knowledge, we leverage the ability to discover novel aspects of the disease while integrating medical concepts into the model. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering the disease into new sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series including uncertainty quantification. We demonstrate the effectiveness of our approach in modeling systemic sclerosis, showcasing the potential of our machine learning model to capture complex disease trajectories and acquire new medical knowledge.
Authors: Pieter Dewulf, Bernard De Baets, Michiel Stock
Hyperdimensional computing (HDC) is an increasingly popular computing paradigm with immense potential for future intelligent applications. Although the main ideas already took form in the 1990s, HDC recently gained significant attention, especially in the field of machine learning and data science. Next to efficiency, interoperability and explainability, HDC offers attractive properties for generalization as it can be seen as an attempt to combine connectionist ideas from neural networks with symbolic aspects. In recent work, we introduced the hyperdimensional transform, revealing deep theoretical foundations for representing functions and distributions as high-dimensional holographic vectors. Here, we present the power of the hyperdimensional transform to a broad data science audience. We use the hyperdimensional transform as a theoretical basis and provide insight into state-of-the-art HDC approaches for machine learning. We show how existing algorithms can be modified and how this transform can lead to a novel, well-founded toolbox. Next to the standard regression and classification tasks of machine learning, our discussion includes various aspects of statistical modelling, such as representation, learning and deconvolving distributions, sampling, Bayesian inference, and uncertainty estimation.
Authors: Bo Ni, Markus J. Buehler
Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus far mainly been reserved for humans. While emerging AI methods can provide effective approaches to solve end-to-end problems, for instance via the use of deep surrogate models or various data analytics strategies, they often lack physical intuition since knowledge is baked into the parametric complement through training, offering less flexibility when it comes to incorporating mathematical or physical insights. By leveraging diverse capabilities of multiple dynamically interacting large language models (LLMs), we can overcome the limitations of conventional approaches and develop a new class of physics-inspired generative machine learning platform, here referred to as MechAgents. A set of AI agents can solve mechanics tasks, here demonstrated for elasticity problems, via autonomous collaborations. A two-agent team can effectively write, execute and self-correct code, in order to apply finite element methods to solve classical elasticity problems in various flavors (different boundary conditions, domain geometries, meshes, small/finite deformation and linear/hyper-elastic constitutive laws, and others). For more complex tasks, we construct a larger group of agents with enhanced division of labor among planning, formulating, coding, executing and criticizing the process and results. The agents mutually correct each other to improve the overall team-work performance in understanding, formulating and validating the solution. Our framework shows the potential of synergizing the intelligence of language models, the reliability of physics-based modeling, and the dynamic collaborations among diverse agents, opening novel avenues for automation of solving engineering problems.
Authors: Giovanni Luca Marchetti, Gabriele Cesa, Kumar Pratik, Arash Behboodi
Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice. In this work, we address lattice reduction via deep learning methods. We design a deep neural model outputting factorized unimodular matrices and train it in a self-supervised manner by penalizing non-orthogonal lattice bases. We incorporate the symmetries of lattice reduction into the model by making it invariant and equivariant with respect to appropriate continuous and discrete groups.
Authors: Shengguang Wu, Keming Lu, Benfeng Xu, Junyang Lin, Qi Su, Chang Zhou
Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To investigate a label-efficient instruction tuning method that allows the model itself to actively sample subsets that are equally or even more effective, we introduce a self-evolving mechanism DiverseEvol. In this process, a model iteratively augments its training subset to refine its own performance, without requiring any intervention from humans or more advanced LLMs. The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets, as the model selects new data points most distinct from any existing ones according to its current embedding space. Extensive experiments across three datasets and benchmarks demonstrate the effectiveness of DiverseEvol. Our models, trained on less than 8% of the original dataset, maintain or improve performance compared with finetuning on full data. We also provide empirical evidence to analyze the importance of diversity in instruction data and the iterative scheme as opposed to one-time sampling. Our code is publicly available at https://github.com/OFA-Sys/DiverseEvol.git.
Authors: Yinuo Wang, Kai Chen, Weimin Yuan, Cai Meng, XiangZhi Bai
Segment Anything Model (SAM), a vision foundation model trained on large-scale annotations, has recently continued raising awareness within medical image segmentation. Despite the impressive capabilities of SAM on natural scenes, it struggles with performance decline when confronted with medical images, especially those involving blurry boundaries and highly irregular regions of low contrast. In this paper, a SAM-based parameter-efficient fine-tuning method, called SAMIHS, is proposed for intracranial hemorrhage segmentation, which is a crucial and challenging step in stroke diagnosis and surgical planning. Distinguished from previous SAM and SAM-based methods, SAMIHS incorporates parameter-refactoring adapters into SAM's image encoder and considers the efficient and flexible utilization of adapters' parameters. Additionally, we employ a combo loss that combines binary cross-entropy loss and boundary-sensitive loss to enhance SAMIHS's ability to recognize the boundary regions. Our experimental results on two public datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/mileswyn/SAMIHS .
Authors: Robert Harb, Thomas Pock, Heimo Müller
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhance the performance of many computational pathology applications. They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations. Or they can facilitate learning representations of WSIs without requiring data annotations. Despite this variety of applications, no existing deep-learning-based method generates WSIs at their typically high resolutions. Mainly due to the high computational complexity. Therefore, we propose a novel coarse-to-fine sampling scheme to tackle image generation of high-resolution WSIs. In this scheme, we increase the resolution of an initial low-resolution image to a high-resolution WSI. Particularly, a diffusion model sequentially adds fine details to images and increases their resolution. In our experiments, we train our method with WSIs from the TCGA-BRCA dataset. Additionally to quantitative evaluations, we also performed a user study with pathologists. The study results suggest that our generated WSIs resemble the structure of real WSIs.
Authors: Yuwei Wang, Runhan Li, Hao Tan, Xuefeng Jiang, Sheng Sun, Min Liu, Bo Gao, Zhiyuan Wu
Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in realistic FL settings, as it causes significant performance deterioration due to discrepancies in optimization among local models. In this work, we focus on label distribution skew, a common scenario in data heterogeneity, where the data label categories are imbalanced on each client. To address this issue, we propose FedBalance, which corrects the optimization bias among local models by calibrating their logits. Specifically, we introduce an extra private weak learner on the client side, which forms an ensemble model with the local model. By fusing the logits of the two models, the private weak learner can capture the variance of different data, regardless of their category. Therefore, the optimization direction of local models can be improved by increasing the penalty for misclassifying minority classes and reducing the attention to majority classes, resulting in a better global model. Extensive experiments show that our method can gain 13\% higher average accuracy compared with state-of-the-art methods.
Authors: Xuan Zhao, Klaus Broelemann, Gjergji Kasneci
Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to guide the user's interaction with AI systems since they represent easy-to-understand explanations. To be applicable, CEs need to be realistic and actionable. In the literature, various methods have been proposed to generate CEs. However, the majority of research on CEs focuses on classification problems where questions like ``What should I do to get my rejected loan approved?" are raised. In practice, answering questions like ``What should I do to increase my salary?" are of a more regressive nature. In this paper, we introduce a novel method to generate CEs for a pre-trained regressor by first disentangling the label-relevant from the label-irrelevant dimensions in the latent space. CEs are then generated by combining the label-irrelevant dimensions and the predefined output. The intuition behind this approach is that the ideal counterfactual search should focus on the label-irrelevant characteristics of the input and suggest changes toward target-relevant characteristics. Searching in the latent space could help achieve this goal. We show that our method maintains the characteristics of the query sample during the counterfactual search. In various experiments, we demonstrate that the proposed method is competitive based on different quality measures on image and tabular datasets in regression problem settings. It efficiently returns results closer to the original data manifold compared to three state-of-the-art methods, which is essential for realistic high-dimensional machine learning applications. Our code will be made available as an open-source package upon the publication of this work.
Authors: Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D Lee, Di He
We introduce Retrieval-Based Speculative Decoding (REST), a novel algorithm designed to speed up language model generation. The key insight driving the development of REST is the observation that the process of text generation often includes certain common phases and patterns. Unlike previous methods that rely on a draft language model for speculative decoding, REST harnesses the power of retrieval to generate draft tokens. This method draws from the reservoir of existing knowledge, retrieving and employing relevant tokens based on the current context. Its plug-and-play nature allows for seamless integration and acceleration of any language models, all without necessitating additional training. When benchmarked on 7B and 13B language models in a single-batch setting, REST achieves a significant speedup of 1.62X to 2.36X on code or text generation. The code of REST is available at https://github.com/FasterDecoding/REST.
Authors: Kyuwon Han, Seung Min Yu, Seong-Lyun Kim, Seung-Woo Ko
A smartphone-based user mobility tracking could be effective in finding his/her location, while the unpredictable error therein due to low specification of built-in inertial measurement units (IMUs) rejects its standalone usage but demands the integration to another positioning technique like WiFi positioning. This paper aims to propose a novel integration technique using a graph neural network called Mobility-INduced Graph LEarning (MINGLE), which is designed based on two types of graphs made by capturing different user mobility features. Specifically, considering sequential measurement points (MPs) as nodes, a user's regular mobility pattern allows us to connect neighbor MPs as edges, called time-driven mobility graph (TMG). Second, a user's relatively straight transition at a constant pace when moving from one position to another can be captured by connecting the nodes on each path, called a direction-driven mobility graph (DMG). Then, we can design graph convolution network (GCN)-based cross-graph learning, where two different GCN models for TMG and DMG are jointly trained by feeding different input features created by WiFi RTTs yet sharing their weights. Besides, the loss function includes a mobility regularization term such that the differences between adjacent location estimates should be less variant due to the user's stable moving pace. Noting that the regularization term does not require ground-truth location, MINGLE can be designed under semi- and self-supervised learning frameworks. The proposed MINGLE's effectiveness is extensively verified through field experiments, showing a better positioning accuracy than benchmarks, say root mean square errors (RMSEs) being 1.398 (m) and 1.073 (m) for self- and semi-supervised learning cases, respectively.
Authors: Guanyu Lin, Chen Gao, Yu Zheng, Jianxin Chang, Yanan Niu, Yang Song, Kun Gai, Zhiheng Li, Depeng Jin, Yong Li, Meng Wang
In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the cross-domain recommendation, which trains models with data across multiple domains to improve the performance in data-scarce domains. Recent proposed cross-domain sequential recommendation models such as PiNet and DASL have a common drawback relying heavily on overlapped users in different domains, which limits their usage in practical recommender systems. In this paper, we propose a Mixed Attention Network (MAN) with local and global attention modules to extract the domain-specific and cross-domain information. Firstly, we propose a local/global encoding layer to capture the domain-specific/cross-domain sequential pattern. Then we propose a mixed attention layer with item similarity attention, sequence-fusion attention, and group-prototype attention to capture the local/global item similarity, fuse the local/global item sequence, and extract the user groups across different domains, respectively. Finally, we propose a local/global prediction layer to further evolve and combine the domain-specific and cross-domain interests. Experimental results on two real-world datasets (each with two domains) demonstrate the superiority of our proposed model. Further study also illustrates that our proposed method and components are model-agnostic and effective, respectively. The code and data are available at https://github.com/Guanyu-Lin/MAN.
Authors: Gabrel Turinici
We give here a proof of the convergence of the Stochastic Gradient Descent (SGD) in a self-contained manner.
Authors: Jason M. Klusowski, Peter M. Tian
This paper shows that decision trees constructed with Classification and Regression Trees (CART) and C4.5 methodology are consistent for regression and classification tasks, even when the number of predictor variables grows sub-exponentially with the sample size, under natural 0-norm and 1-norm sparsity constraints. The theory applies to a wide range of models, including (ordinary or logistic) additive regression models with component functions that are continuous, of bounded variation, or, more generally, Borel measurable. Consistency holds for arbitrary joint distributions of the predictor variables, thereby accommodating continuous, discrete, and/or dependent data. Finally, we show that these qualitative properties of individual trees are inherited by Breiman's random forests. A key step in the analysis is the establishment of an oracle inequality, which allows for a precise characterization of the goodness-of-fit and complexity tradeoff for a mis-specified model.
Authors: Scott Fujimoto, David Meger, Doina Precup
Marginalized importance sampling (MIS), which measures the density ratio between the state-action occupancy of a target policy and that of a sampling distribution, is a promising approach for off-policy evaluation. However, current state-of-the-art MIS methods rely on complex optimization tricks and succeed mostly on simple toy problems. We bridge the gap between MIS and deep reinforcement learning by observing that the density ratio can be computed from the successor representation of the target policy. The successor representation can be trained through deep reinforcement learning methodology and decouples the reward optimization from the dynamics of the environment, making the resulting algorithm stable and applicable to high-dimensional domains. We evaluate the empirical performance of our approach on a variety of challenging Atari and MuJoCo environments.
Authors: Janet van Niekerk, Haavard Rue
Approximate inference methods like the Laplace method, Laplace approximations and variational methods, amongst others, are popular methods when exact inference is not feasible due to the complexity of the model or the abundance of data. In this paper we propose a hybrid approximate method called Low-Rank Variational Bayes correction (VBC), that uses the Laplace method and subsequently a Variational Bayes correction in a lower dimension, to the joint posterior mean. The cost is essentially that of the Laplace method which ensures scalability of the method, in both model complexity and data size. Models with fixed and unknown hyperparameters are considered, for simulated and real examples, for small and large datasets.
Authors: Dennis Grinwald, Kirill Bykov, Shinichi Nakajima, Marina M.-C. Höhne
Explainable Artificial Intelligence (XAI) aims to make learning machines less opaque, and offers researchers and practitioners various tools to reveal the decision-making strategies of neural networks. In this work, we investigate how XAI methods can be used for exploring and visualizing the diversity of feature representations learned by Bayesian Neural Networks (BNNs). Our goal is to provide a global understanding of BNNs by making their decision-making strategies a) visible and tangible through feature visualizations and b) quantitatively measurable with a distance measure learned by contrastive learning. Our work provides new insights into the \emph{posterior} distribution in terms of human-understandable feature information with regard to the underlying decision making strategies. The main findings of our work are the following: 1) global XAI methods can be applied to explain the diversity of decision-making strategies of BNN instances, 2) Monte Carlo dropout with commonly used Dropout rates exhibit increased diversity in feature representations compared to the multimodal posterior approximation of MultiSWAG, 3) the diversity of learned feature representations highly correlates with the uncertainty estimate for the output and 4) the inter-mode diversity of the multimodal posterior decreases as the network width increases, while the intra mode diversity increases. These findings are consistent with the recent Deep Neural Networks theory, providing additional intuitions about what the theory implies in terms of humanly understandable concepts.
Authors: Daniele Ravi (for the Alzheimer's Disease Neuroimaging Initiative), Frederik Barkhof, Daniel C. Alexander, Lemuel Puglisi, Geoffrey JM Parker, Arman Eshaghi
Large medical imaging data sets are becoming increasingly available, but ensuring sample quality without significant artefacts is challenging. Existing methods for identifying imperfections in medical imaging rely on data-intensive approaches, compounded by a scarcity of artefact-rich scans for training machine learning models in clinical research. To tackle this problem, we propose a framework with four main components: 1) artefact generators inspired by magnetic resonance physics to corrupt brain MRI scans and augment a training dataset, 2) abstract and engineered features to represent images compactly, 3) a feature selection process depending on the artefact class to improve classification, and 4) SVM classifiers to identify artefacts. Our contributions are threefold: first, physics-based artefact generators produce synthetic brain MRI scans with controlled artefacts for data augmentation. This will avoid the labour-intensive collection and labelling process of scans with rare artefacts. Second, we propose a pool of abstract and engineered image features to identify 9 different artefacts for structural MRI. Finally, we use an artefact-based feature selection block that, for each class of artefacts, finds the set of features providing the best classification performance. We performed validation experiments on a large data set of scans with artificially-generated artefacts, and in a multiple sclerosis clinical trial where real artefacts were identified by experts, showing that the proposed pipeline outperforms traditional methods. In particular, our data augmentation increases performance by up to 12.5 percentage points on accuracy, precision, and recall. The computational efficiency of our pipeline enables potential real-time deployment, promising high-throughput clinical applications through automated image-processing pipelines driven by quality control systems.
Authors: Bingheng Wang, Zhengtian Ma, Shupeng Lai, Lin Zhao
Estimating and reacting to disturbances is crucial for robust flight control of quadrotors. Existing estimators typically require significant tuning for a specific flight scenario or training with extensive ground-truth disturbance data to achieve satisfactory performance. In this paper, we propose a neural moving horizon estimator (NeuroMHE) that can automatically tune its key parameters modeled by a neural network and adapt to different flight scenarios. We achieve this by deriving the analytical gradients of the MHE estimates with respect to the MHE weighting matrices, which enables a seamless embedding of the MHE as a learnable layer into the neural network for highly effective learning. Interestingly, we show that the gradients can be computed efficiently using a Kalman filter in a recursive form. Moreover, we develop a model-based policy gradient algorithm to train NeuroMHE directly from the quadrotor trajectory tracking error without needing the ground-truth disturbance data. The effectiveness of NeuroMHE is verified extensively via both simulations and physical experiments on quadrotors in various challenging flights. Notably, NeuroMHE outperforms a state-of-the-art neural network-based estimator, reducing force estimation errors by up to 76.7%, while using a portable neural network that has only 7.7% of the learnable parameters of the latter. The proposed method is general and can be applied to robust adaptive control of other robotic systems.
Authors: Siqi Liu, Andreas Lehrmann
Deep learning has shown impressive results in a variety of time series forecasting tasks, where modeling the conditional distribution of the future given the past is the essence. However, when this conditional distribution is non-stationary, it poses challenges for these models to learn consistently and to predict accurately. In this work, we propose a new method to model non-stationary conditional distributions over time by clearly decoupling stationary conditional distribution modeling from non-stationary dynamics modeling. Our method is based on a Bayesian dynamic model that can adapt to conditional distribution changes and a deep conditional distribution model that handles multivariate time series using a factorized output space. Our experimental results on synthetic and real-world datasets show that our model can adapt to non-stationary time series better than state-of-the-art deep learning solutions.
Authors: Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Ukrit Watchareeruetai, Aubin Samacoits
In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural language descriptions of the style. The first model to achieve this, called CLIPstyler, has demonstrated impressive stylisation results. However, its lengthy optimisation procedure at runtime for each query limits its suitability for many practical applications. In this work, we present FastCLIPstyler, a generalised text-based image style transfer model capable of stylising images in a single forward pass for arbitrary text inputs. Furthermore, we introduce EdgeCLIPstyler, a lightweight model designed for compatibility with resource-constrained devices. Through quantitative and qualitative comparisons with state-of-the-art approaches, we demonstrate that our models achieve superior stylisation quality based on measurable metrics while offering significantly improved runtime efficiency, particularly on edge devices.
Authors: Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana, Clément Bonnet, Thomas D. Barrett
Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge or pre-solved instances. However, it is unrealistic to expect an agent to solve these (often NP-)hard problems in a single shot at inference due to their inherent complexity. Thus, leading approaches often implement additional search strategies, from stochastic sampling and beam search to explicit fine-tuning. In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference. To this end, we introduce Poppy, a simple training procedure for populations. Instead of relying on a predefined or hand-crafted notion of diversity, Poppy induces an unsupervised specialization targeted solely at maximizing the performance of the population. We show that Poppy produces a set of complementary policies, and obtains state-of-the-art RL results on four popular NP-hard problems: traveling salesman, capacitated vehicle routing, 0-1 knapsack, and job-shop scheduling.
Authors: Jingang Qu, Thibault Faney, Ze Wang, Patrick Gallinari, Soleiman Yousef, Jean-Charles de Hemptinne
Due to domain shifts, machine learning systems typically struggle to generalize well to new domains that differ from those of training data, which is what domain generalization (DG) aims to address. Although a variety of DG methods have been proposed, most of them fall short in interpretability and require domain labels, which are not available in many real-world scenarios. This paper presents a novel DG method, called HMOE: Hypernetwork-based Mixture of Experts (MoE), which does not rely on domain labels and is more interpretable. MoE proves effective in identifying heterogeneous patterns in data. For the DG problem, heterogeneity arises exactly from domain shifts. HMOE employs hypernetworks taking vectors as input to generate the weights of experts, which promotes knowledge sharing among experts and enables the exploration of their similarities in a low-dimensional vector space. We benchmark HMOE against other DG methods under a fair evaluation framework -- DomainBed. Our extensive experiments show that HMOE can effectively separate mixed-domain data into distinct clusters that are surprisingly more consistent with human intuition than original domain labels. Using self-learned domain information, HMOE achieves state-of-the-art results on most datasets and significantly surpasses other DG methods in average accuracy across all datasets.
Authors: Zhihao Peng, Hui Liu, Yuheng Jia, Junhui Hou
Existing graph clustering networks heavily rely on a predefined yet fixed graph, which can lead to failures when the initial graph fails to accurately capture the data topology structure of the embedding space. In order to address this issue, we propose a novel clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net), which effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. To begin, we leverage both semantic and topological information by employing a vanilla auto-encoder and a graph convolution network, respectively, to learn a latent feature representation. Subsequently, we utilize the local geometric structure within the feature embedding space to construct an adjacency matrix for the graph. This adjacency matrix is dynamically fused with the initial one using our proposed fusion architecture. To train the network in an unsupervised manner, we minimize the Jeffreys divergence between multiple derived distributions. Additionally, we introduce an improved approximate personalized propagation of neural predictions to replace the standard graph convolution network, enabling EGRC-Net to scale effectively. Through extensive experiments conducted on nine widely-used benchmark datasets, we demonstrate that our proposed methods consistently outperform several state-of-the-art approaches. Notably, EGRC-Net achieves an improvement of more than 11.99\% in Adjusted Rand Index (ARI) over the best baseline on the DBLP dataset. Furthermore, our scalable approach exhibits a 10.73% gain in ARI while reducing memory usage by 33.73% and decreasing running time by 19.71%. The code for EGRC-Net will be made publicly available at \url{https://github.com/ZhihaoPENG-CityU/EGRC-Net}.
Authors: Ankit Gupta, Harsh Mehta, Jonathan Berant
Sequence models based on linear state spaces (SSMs) have recently emerged as a promising choice of architecture for modeling long range dependencies across various modalities. However, they invariably rely on discretization of a continuous state space, which complicates their presentation and understanding. In this work, we dispose of the discretization step, and propose a model based on vanilla Diagonal Linear RNNs ($\mathrm{DLR}$). We empirically show that, despite being conceptually much simpler, $\mathrm{DLR}$ is as performant as previously-proposed SSMs on a variety of tasks and benchmarks including Long Range Arena and raw speech classification. Moreover, we characterize the expressivity of SSMs (including $\mathrm{DLR}$) and attention-based models via a suite of $13$ synthetic sequence-to-sequence tasks involving interactions over tens of thousands of tokens, ranging from simple operations, such as shifting an input sequence, to detecting co-dependent visual features over long spatial ranges in flattened images. We find that while SSMs report near-perfect performance on tasks that can be modeled via $\textit{few}$ convolutional kernels, they struggle on tasks requiring $\textit{many}$ such kernels and especially when the desired sequence manipulation is $\textit{context-dependent}$. Despite these limitations, $\mathrm{DLR}$ reaches high performance on two higher-order reasoning tasks $\mathrm{ListOpsSubTrees}$ and $\mathrm{PathfinderSegmentation}\text{-}\mathrm{256}$ with input lengths $8K$ and $65K$ respectively, and gives encouraging performance on $\mathrm{PathfinderSegmentation}\text{-}\mathrm{512}$ with input length $262K$ for which attention is not a viable choice.
Authors: Arvind Krishna Sridhar, Erik Visser
Advancement in large pretrained language models has significantly improved their performance for conditional language generation tasks including summarization albeit with hallucinations. To reduce hallucinations, conventional methods proposed improving beam search or using a fact checker as a postprocessing step. In this paper, we investigate the use of the Natural Language Inference (NLI) entailment metric to detect and prevent hallucinations in summary generation. We propose an NLI-assisted beam re-ranking mechanism by computing entailment probability scores between the input context and summarization model-generated beams during saliency-enhanced greedy decoding. Moreover, a diversity metric is introduced to compare its effectiveness against vanilla beam search. Our proposed algorithm significantly outperforms vanilla beam decoding on XSum and CNN/DM datasets.
Authors: Jialiang Lin, Jiaxin Song, Zhangping Zhou, Yidong Chen, Xiaodong Shi
Open peer review is a growing trend in academic publications. Public access to peer review data can benefit both the academic and publishing communities. It also serves as a great support to studies on review comment generation and further to the realization of automated scholarly paper review. However, most of the existing peer review datasets do not provide data that cover the whole peer review process. Apart from this, their data are not diversified enough as the data are mainly collected from the field of computer science. These two drawbacks of the currently available peer review datasets need to be addressed to unlock more opportunities for related studies. In response, we construct MOPRD, a multidisciplinary open peer review dataset. This dataset consists of paper metadata, multiple version manuscripts, review comments, meta-reviews, author's rebuttal letters, and editorial decisions. Moreover, we propose a modular guided review comment generation method based on MOPRD. Experiments show that our method delivers better performance as indicated by both automatic metrics and human evaluation. We also explore other potential applications of MOPRD, including meta-review generation, editorial decision prediction, author rebuttal generation, and scientometric analysis. MOPRD is a strong endorsement for further studies in peer review-related research and other applications.
Authors: Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang
Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{O}(\sqrt{T}\zeta)$ regret bound, where $T$ is the number of rounds and $\zeta$ is the total amount of corruption. In this paper, we consider the contextual bandit with general function approximation and propose a computationally efficient algorithm to achieve a regret of $\tilde{O}(\sqrt{T}+\zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandit and a new weighted estimator of uncertainty for the general function class. In contrast to the existing analysis that heavily relies on the linear structure, we develop a novel technique to control the sum of weighted uncertainty, thus establishing the final regret bounds. We then generalize our algorithm to the episodic MDP setting and first achieve an additive dependence on the corruption level $\zeta$ in the scenario of general function approximation. Notably, our algorithms achieve regret bounds either nearly match the performance lower bound or improve the existing methods for all the corruption levels and in both known and unknown $\zeta$ cases.
Authors: Junfan Li, Shizhong Liao
In this paper, we improve the kernel alignment regret bound for online kernel learning in the regime of the Hinge loss function. Previous algorithm achieves a regret of $O((\mathcal{A}_TT\ln{T})^{\frac{1}{4}})$ at a computational complexity (space and per-round time) of $O(\sqrt{\mathcal{A}_TT\ln{T}})$, where $\mathcal{A}_T$ is called \textit{kernel alignment}. We propose an algorithm whose regret bound and computational complexity are better than previous results. Our results depend on the decay rate of eigenvalues of the kernel matrix. If the eigenvalues of the kernel matrix decay exponentially, then our algorithm enjoys a regret of $O(\sqrt{\mathcal{A}_T})$ at a computational complexity of $O(\ln^2{T})$. Otherwise, our algorithm enjoys a regret of $O((\mathcal{A}_TT)^{\frac{1}{4}})$ at a computational complexity of $O(\sqrt{\mathcal{A}_TT})$. We extend our algorithm to batch learning and obtain a $O(\frac{1}{T}\sqrt{\mathbb{E}[\mathcal{A}_T]})$ excess risk bound which improves the previous $O(1/\sqrt{T})$ bound.
Authors: Felix Lanfermann, Sebastian Schmitt, Patricia Wollstadt
Identifying meaningful concepts in large data sets can provide valuable insights into engineering design problems. Concept identification aims at identifying non-overlapping groups of design instances that are similar in a joint space of all features, but which are also similar when considering only subsets of features. These subsets usually comprise features that characterize a design with respect to one specific context, for example, constructive design parameters, performance values, or operation modes. It is desirable to evaluate the quality of design concepts by considering several of these feature subsets in isolation. In particular, meaningful concepts should not only identify dense, well separated groups of data instances, but also provide non-overlapping groups of data that persist when considering pre-defined feature subsets separately. In this work, we propose to view concept identification as a special form of clustering algorithm with a broad range of potential applications beyond engineering design. To illustrate the differences between concept identification and classical clustering algorithms, we apply a recently proposed concept identification algorithm to two synthetic data sets and show the differences in identified solutions. In addition, we introduce the mutual information measure as a metric to evaluate whether solutions return consistent clusters across relevant subsets. To support the novel understanding of concept identification, we consider a simulated data set from a decision-making problem in the energy management domain and show that the identified clusters are more interpretable with respect to relevant feature subsets than clusters found by common clustering algorithms and are thus more suitable to support a decision maker.
Authors: Jiaqi Guo, Amy R. Reibman, Edward J. Delp
Unsupervised domain adaptive (UDA) person re-identification (re-ID) aims to learn identity information from labeled images in source domains and apply it to unlabeled images in a target domain. One major issue with many unsupervised re-identification methods is that they do not perform well relative to large domain variations such as illumination, viewpoint, and occlusions. In this paper, we propose a Synthesis Model Bank (SMB) to deal with illumination variation in unsupervised person re-ID. The proposed SMB consists of several convolutional neural networks (CNN) for feature extraction and Mahalanobis matrices for distance metrics. They are trained using synthetic data with different illumination conditions such that their synergistic effect makes the SMB robust against illumination variation. To better quantify the illumination intensity and improve the quality of synthetic images, we introduce a new 3D virtual-human dataset for GAN-based image synthesis. From our experiments, the proposed SMB outperforms other synthesis methods on several re-ID benchmarks.
Authors: Matteo Gamba, Hossein Azizpour, Mårten Björkman
Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms controlling such factors in practice. In this work, we present an extensive experimental study of the empirical Lipschitz constant of deep networks undergoing double descent, and highlight non-monotonic trends strongly correlating with the test error. Building a connection between parameter-space and input-space gradients for SGD around a critical point, we isolate two important factors -- namely loss landscape curvature and distance of parameters from initialization -- respectively controlling optimization dynamics around a critical point and bounding model function complexity, even beyond the training data. Our study presents novels insights on implicit regularization via overparameterization, and effective model complexity for networks trained in practice.
Authors: Lingxiao Li, Samuel Hurault, Justin Solomon
We present a discretization-free scalable framework for solving a large class of mass-conserving partial differential equations (PDEs), including the time-dependent Fokker-Planck equation and the Wasserstein gradient flow. The main observation is that the time-varying velocity field of the PDE solution needs to be self-consistent: it must satisfy a fixed-point equation involving the probability flow characterized by the same velocity field. Instead of directly minimizing the residual of the fixed-point equation with neural parameterization, we use an iterative formulation with a biased gradient estimator that bypasses significant computational obstacles with strong empirical performance. Compared to existing approaches, our method does not suffer from temporal or spatial discretization, covers a wider range of PDEs, and scales to high dimensions. Experimentally, our method recovers analytical solutions accurately when they are available and achieves superior performance in high dimensions with less training time compared to alternatives.
Authors: Johannes Kirschner, Tor Lattimore, Andreas Krause
Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey and extend recent results on the linear formulation of partial monitoring that naturally generalizes the standard linear bandit setting. The main result is that a single algorithm, information-directed sampling (IDS), is (nearly) worst-case rate optimal in all finite-action games. We present a simple and unified analysis of stochastic partial monitoring, and further extend the model to the contextual and kernelized setting.
Authors: Hongkang Li, Meng Wang, Sijia Liu, Pin-yu Chen
Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly elusive. Based on a data model characterizing both label-relevant and label-irrelevant tokens, this paper provides the first theoretical analysis of training a shallow ViT, i.e., one self-attention layer followed by a two-layer perceptron, for a classification task. We characterize the sample complexity to achieve a zero generalization error. Our sample complexity bound is positively correlated with the inverse of the fraction of label-relevant tokens, the token noise level, and the initial model error. We also prove that a training process using stochastic gradient descent (SGD) leads to a sparse attention map, which is a formal verification of the general intuition about the success of attention. Moreover, this paper indicates that a proper token sparsification can improve the test performance by removing label-irrelevant and/or noisy tokens, including spurious correlations. Empirical experiments on synthetic data and CIFAR-10 dataset justify our theoretical results and generalize to deeper ViTs.
Authors: Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain
We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the instance space is bounded, while our second result takes advantage of dimensionality reduction. Our results naturally apply to Wasserstein GANs and Energy-Based GANs, and our bounds provide new training objectives for these two. Although our work is mainly theoretical, we perform numerical experiments showing non-vacuous generalization bounds for Wasserstein GANs on synthetic datasets.
Authors: Qi Zhao, Bai Yan, Taiwei Hu, Xianglong Chen, Qiqi Duan, Jian Yang, Yuhui Shi
Metaheuristics are prominent gradient-free optimizers for solving hard problems that do not meet the rigorous mathematical assumptions of analytical solvers. The canonical manual optimizer design could be laborious, untraceable and error-prone, let alone human experts are not always available. This arises increasing interest and demand in automating the optimizer design process. In response, this paper proposes AutoOptLib, the first platform for accessible automated design of metaheuristic optimizers. AutoOptLib leverages computing resources to conceive, build up, and verify the design choices of the optimizers. It requires much less labor resources and expertise than manual design, democratizing satisfactory metaheuristic optimizers to a much broader range of researchers and practitioners. Furthermore, by fully exploring the design choices with computing resources, AutoOptLib has the potential to surpass human experience, subsequently gaining enhanced performance compared with human problem-solving. To realize the automated design, AutoOptLib provides 1) a rich library of metaheuristic components for continuous, discrete, and permutation problems; 2) a flexible algorithm representation for evolving diverse algorithm structures; 3) different design objectives and techniques for different optimization scenarios; and 4) a graphic user interface for accessibility and practicability. AutoOptLib is fully written in Matlab/Octave; its source code and documentation are available at https://github.com/qz89/AutoOpt and https://AutoOpt.readthedocs.io/, respectively.
Authors: Kenneth S. Berenhaut, John D. Foley, Liangdongsheng Lyu
In this paper we provide a generalization of the concept of cohesion as introduced recently by Berenhaut, Moore and Melvin [Proceedings of the National Academy of Sciences, 119 (4) (2022)]. The formulation presented builds on the technique of partitioned local depth by distilling two key probabilistic concepts: local relevance and support division. Earlier results are extended within the new context, and examples of applications to revealing communities in data with uncertainty are included. The work sheds light on the foundations of partitioned local depth, and extends the original ideas to enable probabilistic consideration of uncertain, variable and potentially conflicting information.
Authors: Chao Wang
Multi-turn compositional image generation (M-CIG) is a challenging task that aims to iteratively manipulate a reference image given a modification text. While most of the existing methods for M-CIG are based on generative adversarial networks (GANs), recent advances in image generation have demonstrated the superiority of diffusion models over GANs. In this paper, we propose a diffusion-based method for M-CIG named conditional denoising diffusion with image compositional matching (CDD-ICM). We leverage CLIP as the backbone of image and text encoders, and incorporate a gated fusion mechanism, originally proposed for question answering, to compositionally fuse the reference image and the modification text at each turn of M-CIG. We introduce a conditioning scheme to generate the target image based on the fusion results. To prioritize the semantic quality of the generated target image, we learn an auxiliary image compositional match (ICM) objective, along with the conditional denoising diffusion (CDD) objective in a multi-task learning framework. Additionally, we also perform ICM guidance and classifier-free guidance to improve performance. Experimental results show that CDD-ICM achieves state-of-the-art results on two benchmark datasets for M-CIG, i.e., CoDraw and i-CLEVR.
Authors: Nicholas H. Barbara, Ruigang Wang, Ian R. Manchester
This paper presents a policy parameterization for learning-based control on nonlinear, partially-observed dynamical systems. The parameterization is based on a nonlinear version of the Youla parameterization and the recently proposed Recurrent Equilibrium Network (REN) class of models. We prove that the resulting Youla-REN parameterization automatically satisfies stability (contraction) and user-tunable robustness (Lipschitz) conditions on the closed-loop system. This means it can be used for safe learning-based control with no additional constraints or projections required to enforce stability or robustness. We test the new policy class in simulation on two reinforcement learning tasks: 1) magnetic suspension, and 2) inverting a rotary-arm pendulum. We find that the Youla-REN performs similarly to existing learning-based and optimal control methods while also ensuring stability and exhibiting improved robustness to adversarial disturbances.
Authors: Jason Blocklove, Siddharth Garg, Ramesh Karri, Hammond Pearce
Modern hardware design starts with specifications provided in natural language. These are then translated by hardware engineers into appropriate Hardware Description Languages (HDLs) such as Verilog before synthesizing circuit elements. Automating this translation could reduce sources of human error from the engineering process. But, it is only recently that artificial intelligence (AI) has demonstrated capabilities for machine-based end-to-end design translations. Commercially-available instruction-tuned Large Language Models (LLMs) such as OpenAI's ChatGPT and Google's Bard claim to be able to produce code in a variety of programming languages; but studies examining them for hardware are still lacking. In this work, we thus explore the challenges faced and opportunities presented when leveraging these recent advances in LLMs for hardware design. Given that these `conversational' LLMs perform best when used interactively, we perform a case study where a hardware engineer co-architects a novel 8-bit accumulator-based microprocessor architecture with the LLM according to real-world hardware constraints. We then sent the processor to tapeout in a Skywater 130nm shuttle, meaning that this `Chip-Chat' resulted in what we believe to be the world's first wholly-AI-written HDL for tapeout.
Authors: Shishir Adhikari, Elena Zheleva
Causal inference in networks should account for interference, which occurs when a unit's outcome is influenced by treatments or outcomes of peers. Heterogeneous peer influence (HPI) occurs when a unit's outcome is influenced differently by different peers based on their attributes and relationships, or when each unit has a different susceptibility to peer influence. Existing solutions to estimating direct causal effects under interference consider either homogeneous influence from peers or specific heterogeneous influence mechanisms (e.g., based on local neighborhood structure). This paper presents a methodology for estimating individual direct causal effects in the presence of HPI where the mechanism of influence is not known a priori. We propose a structural causal model for networks that can capture different possible assumptions about network structure, interference conditions, and causal dependence and enables reasoning about identifiability in the presence of HPI. We find potential heterogeneous contexts using the causal model and propose a novel graph neural network-based estimator to estimate individual direct causal effects. We show that state-of-the-art methods for individual direct effect estimation produce biased results in the presence of HPI, and that our proposed estimator is robust.
Authors: Wenting Ye, Chen Li, Yang Xie, Wen Zhang, Hong-Yu Zhang, Bowen Wang, Debo Cheng, Zaiwen Feng
Identifying and discovering drug-target interactions(DTIs) are vital steps in drug discovery and development. They play a crucial role in assisting scientists in finding new drugs and accelerating the drug development process. Recently, knowledge graph and knowledge graph embedding (KGE) models have made rapid advancements and demonstrated impressive performance in drug discovery. However, such models lack authenticity and accuracy in drug target identification, leading to an increased misjudgment rate and reduced drug development efficiency. To address these issues, we focus on the problem of drug-target interactions, with knowledge mapping as the core technology. Specifically, a causal intervention-based confidence measure is employed to assess the triplet score to improve the accuracy of the drug-target interaction prediction model. Experimental results demonstrate that the developed confidence measurement method based on causal intervention can significantly enhance the accuracy of DTI link prediction, particularly for high-precision models. The predicted results are more valuable in guiding the design and development of subsequent drug development experiments, thereby significantly improving the efficiency of drug development.
Authors: Vedant Nanda, Till Speicher, John P. Dickerson, Soheil Feizi, Krishna P. Gummadi, Adrian Weller
Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a given layer exhibit a degree of diffuse redundancy, ie, any randomly chosen subset of neurons in the layer that is larger than a threshold size shares a large degree of similarity with the full layer and is able to perform similarly as the whole layer on a variety of downstream tasks. For example, a linear probe trained on $20\%$ of randomly picked neurons from the penultimate layer of a ResNet50 pre-trained on ImageNet1k achieves an accuracy within $5\%$ of a linear probe trained on the full layer of neurons for downstream CIFAR10 classification. We conduct experiments on different neural architectures (including CNNs and Transformers) pre-trained on both ImageNet1k and ImageNet21k and evaluate a variety of downstream tasks taken from the VTAB benchmark. We find that the loss and dataset used during pre-training largely govern the degree of diffuse redundancy and the "critical mass" of neurons needed often depends on the downstream task, suggesting that there is a task-inherent redundancy-performance Pareto frontier. Our findings shed light on the nature of representations learned by pre-trained deep neural networks and suggest that entire layers might not be necessary to perform many downstream tasks. We investigate the potential for exploiting this redundancy to achieve efficient generalization for downstream tasks and also draw caution to certain possible unintended consequences. Our code is available at \url{https://github.com/nvedant07/diffused-redundancy}.
Authors: Haobo Chen, Yuheng Bu, Gregory W. Wornell
Double-descent refers to the unexpected drop in test loss of a learning algorithm beyond an interpolating threshold with over-parameterization, which is not predicted by information criteria in their classical forms due to the limitations in the standard asymptotic approach. We update these analyses using the information risk minimization framework and provide Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) for models learned by the Gibbs algorithm. Notably, the penalty terms for the Gibbs-based AIC and BIC correspond to specific information measures, i.e., symmetrized KL information and KL divergence. We extend this information-theoretic analysis to over-parameterized models by providing two different Gibbs-based BICs to compute the marginal likelihood of random feature models in the regime where the number of parameters $p$ and the number of samples $n$ tend to infinity, with $p/n$ fixed. Our experiments demonstrate that the Gibbs-based BIC can select the high-dimensional model and reveal the mismatch between marginal likelihood and population risk in the over-parameterized regime, providing new insights to understand double-descent.
Authors: Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.
Authors: Harry Bendekgey, Gabriel Hope, Erik B. Sudderth
By composing graphical models with deep learning architectures, we learn generative models with the strengths of both frameworks. The structured variational autoencoder (SVAE) inherits structure and interpretability from graphical models, and flexible likelihoods for high-dimensional data from deep learning, but poses substantial optimization challenges. We propose novel algorithms for learning SVAEs, and are the first to demonstrate the SVAE's ability to handle multimodal uncertainty when data is missing by incorporating discrete latent variables. Our memory-efficient implicit differentiation scheme makes the SVAE tractable to learn via gradient descent, while demonstrating robustness to incomplete optimization. To more rapidly learn accurate graphical model parameters, we derive a method for computing natural gradients without manual derivations, which avoids biases found in prior work. These optimization innovations enable the first comparisons of the SVAE to state-of-the-art time series models, where the SVAE performs competitively while learning interpretable and structured discrete data representations.
Authors: Dan Braha
Phase transitions, characterized by abrupt shifts between macroscopic patterns of organization, are ubiquitous in complex systems. Despite considerable research in the physical and natural sciences, the empirical study of this phenomenon in societal systems is relatively underdeveloped. The goal of this study is to explore whether the dynamics of collective civil unrest can be plausibly characterized as a sequence of recurrent phase shifts, with each phase having measurable and identifiable latent characteristics. Building on previous efforts to characterize civil unrest as a self-organized critical system, we introduce a macro-level statistical model of civil unrest and evaluate its plausibility using a comprehensive dataset of civil unrest events in 170 countries from 1946 to 2017. Our findings demonstrate that the macro-level phase model effectively captures the characteristics of civil unrest data from diverse countries globally and that universal mechanisms may underlie certain aspects of the dynamics of civil unrest. We also introduce a scale to quantify a country's long-term unrest per unit of time and show that civil unrest events tend to cluster geographically, with the magnitude of civil unrest concentrated in specific regions. Our approach has the potential to identify and measure phase transitions in various collective human phenomena beyond civil unrest, contributing to a better understanding of complex social systems.
Authors: Swarnadeep Saha, Peter Hase, Mohit Bansal
A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex reasoning by generating explanations for their predictions, it is unclear whether they also make good teachers for weaker agents. To address this, we consider a student-teacher framework between two LLM agents and study if, when, and how the teacher should intervene with natural language explanations to improve the student's performance. Since communication is expensive, we define a budget such that the teacher only communicates explanations for a fraction of the data, after which the student should perform well on its own. We decompose the teaching problem along four axes: (1) if teacher's test time intervention improve student predictions, (2) when it is worth explaining a data point, (3) how the teacher should personalize explanations to better teach the student, and (4) if teacher explanations also improve students on future unexplained data. We first show that teacher LLMs can indeed intervene on student reasoning to improve their performance. Next, inspired by the Theory of Mind abilities of effective teachers, we propose building two few-shot mental models of the student. The first model defines an Intervention Function that simulates the utility of an intervention, allowing the teacher to intervene when this utility is the highest and improving student performance at lower budgets. The second model enables the teacher to personalize explanations for a particular student and outperform unpersonalized teachers. We also demonstrate that in multi-turn interactions, teacher explanations generalize and learning from explained data improves student performance on future unexplained data. Finally, we verify that misaligned teachers can lower student performance to random chance by intentionally misleading them.
Authors: Shreejit Jadhav, Mihir Shrivastava, Sanjit Mitra
The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of speed, parameter space coverage, and search sensitivity. However, the opaque nature of DL models severely harms their reliability. In this work, we meticulously develop a DL model stage-wise and work towards improving its robustness and reliability. First, we address the problems in maintaining the purity of training data by deriving a new metric that better reflects the visual strength of the 'chirp' signal features in the data. Using a reduced, smooth representation obtained through a variational auto-encoder (VAE), we build a classifier to search for compact binary coalescence (CBC) signals. Our tests on real LIGO data show an impressive performance of the model. However, upon probing the robustness of the model through adversarial attacks, its simple failure modes were identified, underlining how such models can still be highly fragile. As a first step towards bringing robustness, we retrain the model in a novel framework involving a generative adversarial network (GAN). Over the course of training, the model learns to eliminate the primary modes of failure identified by the adversaries. Although absolute robustness is practically impossible to achieve, we demonstrate some fundamental improvements earned through such training, like sparseness and reduced degeneracy in the extracted features at different layers inside the model. We show that these gains are achieved at practically zero loss in terms of model performance on real LIGO data before and after GAN training. Through a direct search on 8.8 days of LIGO data, we recover two significant CBC events from GWTC-2.1, GW190519_153544 and GW190521_074359. We also report the search sensitivity obtained from an injection study.
Authors: Tamas Hajgato
We review the literature on trainable, compressed embedding layers and discuss their applicability for compressing gigantic neural recommender systems. We also report the results we measured with our compressed embedding layers.
Authors: Austin Tripp, Sergio Bacallado, Sukriti Singh, José Miguel Hernández-Lobato
The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kernel. While many kernel methods can be accelerated using random feature approximations, at present there is a lack of such approximations for the Tanimoto kernel. In this paper we propose two kinds of novel random features to allow this kernel to scale to large datasets, and in the process discover a novel extension of the kernel to real-valued vectors. We theoretically characterize these random features, and provide error bounds on the spectral norm of the Gram matrix. Experimentally, we show that these random features are effective at approximating the Tanimoto coefficient of real-world datasets and are useful for molecular property prediction and optimization tasks.
Authors: Eric Nguyen, Michael Poli, Marjan Faizi, Armin Thomas, Callum Birch-Sykes, Michael Wornow, Aman Patel, Clayton Rabideau, Stefano Massaroli, Yoshua Bengio, Stefano Ermon, Stephen A. Baccus, Chris Ré
Genomic (DNA) sequences encode an enormous amount of information for gene regulation and protein synthesis. Similar to natural language models, researchers have proposed foundation models in genomics to learn generalizable features from unlabeled genome data that can then be fine-tuned for downstream tasks such as identifying regulatory elements. Due to the quadratic scaling of attention, previous Transformer-based genomic models have used 512 to 4k tokens as context (<0.001% of the human genome), significantly limiting the modeling of long-range interactions in DNA. In addition, these methods rely on tokenizers or fixed k-mers to aggregate meaningful DNA units, losing single nucleotide resolution where subtle genetic variations can completely alter protein function via single nucleotide polymorphisms (SNPs). Recently, Hyena, a large language model based on implicit convolutions was shown to match attention in quality while allowing longer context lengths and lower time complexity. Leveraging Hyena's new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 1 million tokens at the single nucleotide-level - an up to 500x increase over previous dense attention-based models. HyenaDNA scales sub-quadratically in sequence length (training up to 160x faster than Transformer), uses single nucleotide tokens, and has full global context at each layer. We explore what longer context enables - including the first use of in-context learning in genomics. On fine-tuned benchmarks from the Nucleotide Transformer, HyenaDNA reaches state-of-the-art (SotA) on 12 of 18 datasets using a model with orders of magnitude less parameters and pretraining data. On the GenomicBenchmarks, HyenaDNA surpasses SotA on 7 of 8 datasets on average by +10 accuracy points. Code at https://github.com/HazyResearch/hyena-dna.
Authors: Yuhang Chen, Chaoyun Zhang, Minghua Ma, Yudong Liu, Ruomeng Ding, Bowen Li, Shilin He, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang
Anomaly detection in multivariate time series data is of paramount importance for ensuring the efficient operation of large-scale systems across diverse domains. However, accurately detecting anomalies in such data poses significant challenges. Existing approaches, including forecasting and reconstruction-based methods, struggle to address these challenges effectively. To overcome these limitations, we propose a novel anomaly detection framework named ImDiffusion, which combines time series imputation and diffusion models to achieve accurate and robust anomaly detection. The imputation-based approach employed by ImDiffusion leverages the information from neighboring values in the time series, enabling precise modeling of temporal and inter-correlated dependencies, reducing uncertainty in the data, thereby enhancing the robustness of the anomaly detection process. ImDiffusion further leverages diffusion models as time series imputers to accurately capturing complex dependencies. We leverage the step-by-step denoised outputs generated during the inference process to serve as valuable signals for anomaly prediction, resulting in improved accuracy and robustness of the detection process.
We evaluate the performance of ImDiffusion via extensive experiments on benchmark datasets. The results demonstrate that our proposed framework significantly outperforms state-of-the-art approaches in terms of detection accuracy and timeliness. ImDiffusion is further integrated into the real production system in Microsoft and observe a remarkable 11.4% increase in detection F1 score compared to the legacy approach. To the best of our knowledge, ImDiffusion represents a pioneering approach that combines imputation-based techniques with time series anomaly detection, while introducing the novel use of diffusion models to the field.
Authors: Jean Kaddour, Oscar Key, Piotr Nawrot, Pasquale Minervini, Matt J. Kusner
The computation necessary for training Transformer-based language models has skyrocketed in recent years. This trend has motivated research on efficient training algorithms designed to improve training, validation, and downstream performance faster than standard training. In this work, we revisit three categories of such algorithms: dynamic architectures (layer stacking, layer dropping), batch selection (selective backprop, RHO loss), and efficient optimizers (Lion, Sophia). When pre-training BERT and T5 with a fixed computation budget using such methods, we find that their training, validation, and downstream gains vanish compared to a baseline with a fully-decayed learning rate. We define an evaluation protocol that enables computation to be done on arbitrary machines by mapping all computation time to a reference machine which we call reference system time. We discuss the limitations of our proposed protocol and release our code to encourage rigorous research in efficient training procedures: https://github.com/JeanKaddour/NoTrainNoGain.
Authors: Ning Bao, Gavin S. Hartnett
The problem of decomposing an arbitrary Clifford element into a sequence of Clifford gates is known as Clifford synthesis. Drawing inspiration from similarities between this and the famous Rubik's Cube problem, we develop a machine learning approach for Clifford synthesis based on learning an approximation to the distance to the identity. This approach is probabilistic and computationally intensive. However, when a decomposition is successfully found, it often involves fewer gates than existing synthesis algorithms. Additionally, our approach is much more flexible than existing algorithms in that arbitrary gate sets, device topologies, and gate fidelities may incorporated, thus allowing for the approach to be tailored to a specific device.
Authors: Xiao-Yang Liu, Guoxuan Wang, Hongyang Yang, Daochen Zha
Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating human-like texts, which may potentially revolutionize the finance industry. However, existing LLMs often fall short in the financial field, which is mainly attributed to the disparities between general text data and financial text data. Unfortunately, there is only a limited number of financial text datasets available, and BloombergGPT, the first financial LLM (FinLLM), is close-sourced (only the training logs were released). In light of this, we aim to democratize Internet-scale financial data for LLMs, which is an open challenge due to diverse data sources, low signal-to-noise ratio, and high time-validity. To address the challenges, we introduce an open-sourced and data-centric framework, Financial Generative Pre-trained Transformer (FinGPT), that automates the collection and curation of real-time financial data from 34 diverse sources on the Internet, providing researchers and practitioners with accessible and transparent resources to develop their FinLLMs. Additionally, we propose a simple yet effective strategy for fine-tuning FinLLM using the inherent feedback from the market, dubbed Reinforcement Learning with Stock Prices (RLSP). We also adopt the Low-rank Adaptation (LoRA, QLoRA) method that enables users to customize their own FinLLMs from general-purpose LLMs at a low cost. Finally, we showcase several FinGPT applications, including robo-advisor, sentiment analysis for algorithmic trading, and low-code development. FinGPT aims to democratize FinLLMs, stimulate innovation, and unlock new opportunities in open finance. The codes have been open-sourced.
Authors: Sérgio F. Chevtchenko, Elisson da Silva Rocha, Monalisa Cristina Moura Dos Santos, Ricardo Lins Mota, Diego Moura Vieira, Ermeson Carneiro de Andrade, Danilo Ricardo Barbosa de Araújo
Anomaly detection is critical in the smart industry for preventing equipment failure, reducing downtime, and improving safety. Internet of Things (IoT) has enabled the collection of large volumes of data from industrial machinery, providing a rich source of information for Anomaly Detection. However, the volume and complexity of data generated by the Internet of Things ecosystems make it difficult for humans to detect anomalies manually. Machine learning (ML) algorithms can automate anomaly detection in industrial machinery by analyzing generated data. Besides, each technique has specific strengths and weaknesses based on the data nature and its corresponding systems. However, the current systematic mapping studies on Anomaly Detection primarily focus on addressing network and cybersecurity-related problems, with limited attention given to the industrial sector. Additionally, these studies do not cover the challenges involved in using ML for Anomaly Detection in industrial machinery within the context of the IoT ecosystems. This paper presents a systematic mapping study on Anomaly Detection for industrial machinery using IoT devices and ML algorithms to address this gap. The study comprehensively evaluates 84 relevant studies spanning from 2016 to 2023, providing an extensive review of Anomaly Detection research. Our findings identify the most commonly used algorithms, preprocessing techniques, and sensor types. Additionally, this review identifies application areas and points to future challenges and research opportunities.
Authors: Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa
We study a synthetic corpus based approach for language models (LMs) to acquire logical deductive reasoning ability. The previous studies generated deduction examples using specific sets of deduction rules. However, these rules were limited or otherwise arbitrary, limiting the generalizability of acquired reasoning ability. We rethink this and adopt a well-grounded set of deduction rules based on formal logic theory, which can derive any other deduction rules when combined in a multistep way. Then, using the proposed corpora, which we name FLD (Formal Logic Deduction), we first evaluate and analyze the logical reasoning ability of the latest LLMs. Even GPT-4 can solve only half of the problems, suggesting that pure logical reasoning isolated from knowledge is still challenging for the LLMs, and additional training specialized in logical reasoning is indeed essential. We next empirically verify that LMs trained on FLD corpora acquire more generalizable reasoning ability. Furthermore, we identify the aspects of reasoning ability on which deduction corpora can enhance LMs and those on which they cannot, and discuss future directions on each aspect. The released corpora serve both as learning resources and as challenging benchmarks.
Authors: Robert Graf, Joachim Schmitt, Sarah Schlaeger, Hendrik Kristian Möller, Vasiliki Sideri-Lampretsa, Anjany Sekuboyina, Sandro Manuel Krieg, Benedikt Wiestler, Bjoern Menze, Daniel Rueckert, Jan Stefan Kirschke
Background: Automated segmentation of spinal MR images plays a vital role both scientifically and clinically. However, accurately delineating posterior spine structures presents challenges.
Methods: This retrospective study, approved by the ethical committee, involved translating T1w and T2w MR image series into CT images in a total of n=263 pairs of CT/MR series. Landmark-based registration was performed to align image pairs. We compared 2D paired (Pix2Pix, denoising diffusion implicit models (DDIM) image mode, DDIM noise mode) and unpaired (contrastive unpaired translation, SynDiff) image-to-image translation using "peak signal to noise ratio" (PSNR) as quality measure. A publicly available segmentation network segmented the synthesized CT datasets, and Dice scores were evaluated on in-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings were extended to 3D Pix2Pix and DDIM.
Results: 2D paired methods and SynDiff exhibited similar translation performance and Dice scores on paired data. DDIM image mode achieved the highest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstrated similar Dice scores (0.77). For craniocaudal axis rotations, at least two landmarks per vertebra were required for registration. The 3D translation outperformed the 2D approach, resulting in improved Dice scores (0.80) and anatomically accurate segmentations in a higher resolution than the original MR image.
Conclusion: Two landmarks per vertebra registration enabled paired image-to-image translation from MR to CT and outperformed all unpaired approaches. The 3D techniques provided anatomically correct segmentations, avoiding underprediction of small structures like the spinous process.
Authors: Sumeet S. Singh
Transformer based language models exhibit intelligent behaviors such as understanding natural language, recognizing patterns, acquiring knowledge, reasoning, planning, reflecting and using tools. This paper explores how their underlying mechanics give rise to intelligent behaviors. Towards that end, we propose framing Transformer dynamics as movement through embedding space. Examining Transformers through this perspective reveals key insights, establishing a Theory of Transformers: 1) Intelligent behaviours map to paths in Embedding Space which, the Transformer random-walks through during inferencing. 2) LM training learns a probability distribution over all possible paths. `Intelligence' is learnt by assigning higher probabilities to paths representing intelligent behaviors. No learning can take place in-context; context only narrows the subset of paths sampled during decoding. 5) The Transformer is a self-mapping composition function, folding a context sequence into a context-vector such that it's proximity to a token-vector reflects its co-occurrence and conditioned probability. Thus, the physical arrangement of vectors in Embedding Space determines path probabilities. 6) Context vectors are composed by aggregating features of the sequence's tokens via a process we call the encoding walk. Attention contributes a - potentially redundant - association-bias to this process. 7) This process is comprised of two principal operation types: filtering (data independent) and aggregation (data dependent). This generalization unifies Transformers with other sequence models. Building upon this foundation, we formalize a popular semantic interpretation of embeddings into a ``concept-space theory'' and find some evidence of it's validity.
Authors: Antonio Briola, Yuanrong Wang, Silvia Bartolucci, Tomaso Aste
Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with classic machine learning approaches being often computationally cheaper and equally effective than increasingly complex deep learning architectures. The challenge arises from the fact that, in tabular data, the correlation among features is weaker than the one from spatial or semantic relationships in images or natural language, and the dependency structures need to be modeled without any prior information. In this work, we propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations to gain relational information from sparse tabular inputs. The resulting model leverages the power of convolution and is centered on a limited number of concepts from network topology to guarantee: (i) a data-centric and deterministic building pipeline; (ii) a high level of interpretability over the inference process; and (iii) an adequate room for scalability. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models, demonstrating that our approach reaches state-of-the-art performances on these challenging datasets. The code to reproduce all our experiments is provided at https://github.com/FinancialComputingUCL/HomologicalCNN.
Authors: Binh Duong Nguyen, Pavlo Potapenko, Aytekin Dermici, Kishan Govind, Sébastien Bompas, Stefan Sandfeld
Determining, understanding, and predicting the so-called structure-property relation is an important task in many scientific disciplines, such as chemistry, biology, meteorology, physics, engineering, and materials science. Structure refers to the spatial distribution of, e.g., substances, material, or matter in general, while property is a resulting characteristic that usually depends in a non-trivial way on spatial details of the structure. Traditionally, forward simulations models have been used for such tasks. Recently, several machine learning algorithms have been applied in these scientific fields to enhance and accelerate simulation models or as surrogate models. In this work, we develop and investigate the applications of six machine learning techniques based on two different datasets from the domain of materials science: data from a two-dimensional Ising model for predicting the formation of magnetic domains and data representing the evolution of dual-phase microstructures from the Cahn-Hilliard model. We analyze the accuracy and robustness of all models and elucidate the reasons for the differences in their performances. The impact of including domain knowledge through tailored features is studied, and general recommendations based on the availability and quality of training data are derived from this.
Authors: Sergio Caprioli, Emanuele Cagliero, Riccardo Crupi
In this research, we propose a novel approach for the quantification of credit portfolio Value-at-Risk (VaR) sensitivity to asset correlations with the use of synthetic financial correlation matrices generated with deep learning models. In previous work Generative Adversarial Networks (GANs) were employed to demonstrate the generation of plausible correlation matrices, that capture the essential characteristics observed in empirical correlation matrices estimated on asset returns. Instead of GANs, we employ Variational Autoencoders (VAE) to achieve a more interpretable latent space representation. Through our analysis, we reveal that the VAE latent space can be a useful tool to capture the crucial factors impacting portfolio diversification, particularly in relation to credit portfolio sensitivity to asset correlations changes.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Kai Yin, Ali Mostafavi
Urban flood risk emerges from complex and nonlinear interactions among multiple features related to flood hazard, flood exposure, and social and physical vulnerabilities, along with the complex spatial flood dependence relationships. Existing approaches for characterizing urban flood risk, however, are primarily based on flood plain maps, focusing on a limited number of features, primarily hazard and exposure features, without consideration of feature interactions or the dependence relationships among spatial areas. To address this gap, this study presents an integrated urban flood-risk rating model based on a novel unsupervised graph deep learning model (called FloodRisk-Net). FloodRisk-Net is capable of capturing spatial dependence among areas and complex and nonlinear interactions among flood hazards and urban features for specifying emergent flood risk. Using data from multiple metropolitan statistical areas (MSAs) in the United States, the model characterizes their flood risk into six distinct city-specific levels. The model is interpretable and enables feature analysis of areas within each flood-risk level, allowing for the identification of the three archetypes shaping the highest flood risk within each MSA. Flood risk is found to be spatially distributed in a hierarchical structure within each MSA, where the core city disproportionately bears the highest flood risk. Multiple cities are found to have high overall flood-risk levels and low spatial inequality, indicating limited options for balancing urban development and flood-risk reduction. Relevant flood-risk reduction strategies are discussed considering ways that the highest flood risk and uneven spatial distribution of flood risk are formed.
Authors: Duanyu Feng, Yongfu Dai, Jimin Huang, Yifang Zhang, Qianqian Xie, Weiguang Han, Alejandro Lopez-Lira, Hao Wang
In the financial industry, credit scoring is a fundamental element, shaping access to credit and determining the terms of loans for individuals and businesses alike. Traditional credit scoring methods, however, often grapple with challenges such as narrow knowledge scope and isolated evaluation of credit tasks. Our work posits that Large Language Models (LLMs) have great potential for credit scoring tasks, with strong generalization ability across multiple tasks. To systematically explore LLMs for credit scoring, we propose the first open-source comprehensive framework. We curate a novel benchmark covering 9 datasets with 14K samples, tailored for credit assessment and a critical examination of potential biases within LLMs, and the novel instruction tuning data with over 45k samples. We then propose the first Credit and Risk Assessment Large Language Model (CALM) by instruction tuning, tailored to the nuanced demands of various financial risk assessment tasks. We evaluate CALM, and existing state-of-art (SOTA) open source and close source LLMs on the build benchmark. Our empirical results illuminate the capability of LLMs to not only match but surpass conventional models, pointing towards a future where credit scoring can be more inclusive, comprehensive, and unbiased. We contribute to the industry's transformation by sharing our pioneering instruction-tuning datasets, credit and risk assessment LLM, and benchmarks with the research community and the financial industry.
Authors: Han Zhou, Xingchen Ma, Matthew B Blaschko
Sequential maximization of expected improvement (EI) is one of the most widely used policies in Bayesian optimization because of its simplicity and ability to handle noisy observations. In particular, the improvement function often uses the best posterior mean as the best incumbent in noisy settings. However, the uncertainty associated with the incumbent solution is often neglected in many analytic EI-type methods: a closed-form acquisition function is derived in the noise-free setting, but then applied to the setting with noisy observations. To address this limitation, we propose a modification of EI that corrects its closed-form expression by incorporating the covariance information provided by the Gaussian Process (GP) model. This acquisition function specializes to the classical noise-free result, and we argue should replace that formula in Bayesian optimization software packages, tutorials, and textbooks. This enhanced acquisition provides good generality for noisy and noiseless settings. We show that our method achieves a sublinear convergence rate on the cumulative regret bound under heteroscedastic observation noise. Our empirical results demonstrate that our proposed acquisition function can outperform EI in the presence of noisy observations on benchmark functions for black-box optimization, as well as on parameter search for neural network model compression.
Authors: Ruotong Liao, Xu Jia, Yunpu Ma, Volker Tresp
The rapid advancements in large language models (LLMs) have ignited interest in the temporal knowledge graph (tKG) domain, where conventional carefully designed embedding-based and rule-based models dominate. The question remains open of whether pre-trained LLMs can understand structured temporal relational data and replace them as the foundation model for temporal relational forecasting. Therefore, we bring temporal knowledge forecasting into the generative setting. However, challenges occur in the huge chasms between complex temporal graph data structure and sequential natural expressions LLMs can handle, and between the enormous data sizes of tKGs and heavy computation costs of finetuning LLMs. To address these challenges, we propose a novel retrieval augmented generation framework that performs generative forecasting on tKGs named GenTKG, which combines a temporal logical rule-based retrieval strategy and lightweight parameter-efficient instruction tuning. Extensive experiments have shown that GenTKG outperforms conventional methods of temporal relational forecasting under low computation resources. GenTKG also highlights remarkable transferability with exceeding performance on unseen datasets without re-training. Our work reveals the huge potential of LLMs in the tKG domain and opens a new frontier for generative forecasting on tKGs.
Authors: Qingyue Zhao, Banghua Zhu
We characterize the statistical efficiency of knowledge transfer through $n$ samples from a teacher to a probabilistic student classifier with input space $\mathcal S$ over labels $\mathcal A$. We show that privileged information at three progressive levels accelerates the transfer. At the first level, only samples with hard labels are known, via which the maximum likelihood estimator attains the minimax rate $\sqrt{{|{\mathcal S}||{\mathcal A}|}/{n}}$. The second level has the teacher probabilities of sampled labels available in addition, which turns out to boost the convergence rate lower bound to ${{|{\mathcal S}||{\mathcal A}|}/{n}}$. However, under this second data acquisition protocol, minimizing a naive adaptation of the cross-entropy loss results in an asymptotically biased student. We overcome this limitation and achieve the fundamental limit by using a novel empirical variant of the squared error logit loss. The third level further equips the student with the soft labels (complete logits) on ${\mathcal A}$ given every sampled input, thereby provably enables the student to enjoy a rate ${|{\mathcal S}|}/{n}$ free of $|{\mathcal A}|$. We find any Kullback-Leibler divergence minimizer to be optimal in the last case. Numerical simulations distinguish the four learners and corroborate our theory.
Authors: Jianfei Ma
Future sequence represents the outcome after executing the action into the environment (i.e. the trajectory onwards). When driven by the information-theoretic concept of mutual information, it seeks maximally informative consequences. Explicit outcomes may vary across state, return, or trajectory serving different purposes such as credit assignment or imitation learning. However, the inherent nature of incorporating intrinsic motivation with reward maximization is often neglected. In this work, we propose a policy iteration scheme that seamlessly incorporates the mutual information, ensuring convergence to the optimal policy. Concurrently, a variational approach is introduced, which jointly learns the necessary quantity for estimating the mutual information and the dynamics model, providing a general framework for incorporating different forms of outcomes of interest. While we mainly focus on theoretical analysis, our approach opens the possibilities of leveraging intrinsic control with model learning to enhance sample efficiency and incorporate uncertainty of the environment into decision-making.
Authors: Guanqun Sun, Yizhi Pan, Weikun Kong, Zichang Xu, Jianhua Ma, Teeradaj Racharak, Le-Minh Nguyen, Junyi Xin
Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional Unet architectures and their transformer-integrated variants excel in automated segmentation tasks. However, they lack the ability to harness the intrinsic position and channel features of image. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block(DA-Block) into the traditional U-shaped architecture. Unlike earlier transformer-based U-net models, DA-TransUNet utilizes Transformers and DA-Block to integrate not only global and local features, but also image-specific positional and channel features, improving the performance of medical image segmentation. By incorporating a DA-Block at the embedding layer and within each skip connection layer, we substantially enhance feature extraction capabilities and improve the efficiency of the encoder-decoder structure. DA-TransUNet demonstrates superior performance in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across multiple datasets. In summary, DA-TransUNet offers a significant advancement in medical image segmentation, providing an effective and powerful alternative to existing techniques. Our architecture stands out for its ability to improve segmentation accuracy, thereby advancing the field of automated medical image diagnostics. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.
Authors: Xabi Azagirre, Akshay Balwally, Guillaume Candeli, Nicholas Chamandy, Benjamin Han, Alona King, Hyungjun Lee, Martin Loncaric, Sebastien Martin, Vijay Narasiman, Zhiwei (Tony)Qin, Baptiste Richard, Sara Smoot, Sean Taylor, Garrett van Ryzin, Di Wu, Fei Yu, Alex Zamoshchin
To better match drivers to riders in our ridesharing application, we revised Lyft's core matching algorithm. We use a novel online reinforcement learning approach that estimates the future earnings of drivers in real time and use this information to find more efficient matches. This change was the first documented implementation of a ridesharing matching algorithm that can learn and improve in real time. We evaluated the new approach during weeks of switchback experimentation in most Lyft markets, and estimated how it benefited drivers, riders, and the platform. In particular, it enabled our drivers to serve millions of additional riders each year, leading to more than $30 million per year in incremental revenue. Lyft rolled out the algorithm globally in 2021.
Authors: Illia Horenko
Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computation of minimal adversarial paths (MAP) and minimal adversarial distances (MAD) for (locally) uniquely-invertible classifiers, for generalized linear models (GLM), and for entropic AI (EAI) are formulated and proven. Practical computation of MAP and MAD, their comparison and interpretations for various classes of AI tools (for neuronal networks, boosted random forests, GLM and EAI) are demonstrated on the common synthetic benchmarks: on a double Swiss roll spiral and its extensions, as well as on the two biomedical data problems (for the health insurance claim predictions, and for the heart attack lethality classification). On biomedical applications it is demonstrated how MAP provides unique minimal patient-specific risk-mitigating interventions in the predefined subsets of accessible control variables.
Authors: Chenlu Ye, Rui Yang, Quanquan Gu, Tong Zhang
We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\zeta\geq0$ quantifies the cumulative corruption amount over $n$ episodes and $H$ steps. Our goal is to find a policy that is robust to such corruption and minimizes the suboptimality gap with respect to the optimal policy for the uncorrupted Markov decision processes (MDPs). Drawing inspiration from the uncertainty-weighting technique from the robust online RL setting \citep{he2022nearly,ye2022corruptionrobust}, we design a new uncertainty weight iteration procedure to efficiently compute on batched samples and propose a corruption-robust algorithm for offline RL. Notably, under the assumption of single policy coverage and the knowledge of $\zeta$, our proposed algorithm achieves a suboptimality bound that is worsened by an additive factor of $\mathcal O(\zeta \cdot (\text{CC}(\lambda,\hat{\mathcal F},\mathcal Z_n^H))^{1/2} (C(\hat{\mathcal F},\mu))^{-1/2} n^{-1})$ due to the corruption. Here $\text{CC}(\lambda,\hat{\mathcal F},\mathcal Z_n^H)$ is the coverage coefficient that depends on the regularization parameter $\lambda$, the confidence set $\hat{\mathcal F}$, and the dataset $\mathcal Z_n^H$, and $C(\hat{\mathcal F},\mu)$ is a coefficient that depends on $\hat{\mathcal F}$ and the underlying data distribution $\mu$. When specialized to linear MDPs, the corruption-dependent error term reduces to $\mathcal O(\zeta d n^{-1})$ with $d$ being the dimension of the feature map, which matches the existing lower bound for corrupted linear MDPs. This suggests that our analysis is tight in terms of the corruption-dependent term.
Authors: Alexander Jenkins, Zehua Chen, Fu Siong Ng, Danilo Mandic
Pulsative signals such as the electrocardiogram (ECG) are extensively collected as part of routine clinical care. However, noisy and poor-quality recordings are a major issue for signals collected using mobile health systems, decreasing the signal quality, leading to missing values, and affecting automated downstream tasks. Recent studies have explored the imputation of missing values in ECG with probabilistic time-series models. Nevertheless, in comparison with the deterministic models, their performance is still limited, as the variations across subjects and heart-beat relationships are not explicitly considered in the training objective. In this work, to improve the imputation and forecasting accuracy for ECG with probabilistic models, we present a template-guided denoising diffusion probabilistic model (DDPM), PulseDiff, which is conditioned on an informative prior for a range of health conditions. Specifically, 1) we first extract a subject-level pulsative template from the observed values to use as an informative prior of the missing values, which personalises the prior; 2) we then add beat-level stochastic shift terms to augment the prior, which considers variations in the position and amplitude of the prior at each beat; 3) we finally design a confidence score to consider the health condition of the subject, which ensures our prior is provided safely. Experiments with the PTBXL dataset reveal that PulseDiff improves the performance of two strong DDPM baseline models, CSDI and SSSD$^{S4}$, verifying that our method guides the generation of DDPMs while managing the uncertainty. When combined with SSSD$^{S4}$, PulseDiff outperforms the leading deterministic model for short-interval missing data and is comparable for long-interval data loss.
Authors: Chris Salahub, Wayne Oldford
A common approach to evaluating the significance of a collection of $p$-values combines them with a pooling function, in particular when the original data are not available. These pooled $p$-values convert a sample of $p$-values into a single number which behaves like a univariate $p$-value. To clarify discussion of these functions, a telescoping series of alternative hypotheses are introduced that communicate the strength and prevalence of non-null evidence in the $p$-values before general pooling formulae are discussed. A pattern noticed in the UMP pooled $p$-value for a particular alternative motivates the definition and discussion of central and marginal rejection levels at $\alpha$. It is proven that central rejection is always greater than or equal to marginal rejection, motivating a quotient to measure the balance between the two for pooled $p$-values. A combining function based on the $\chi^2_{\kappa}$ quantile transformation is proposed to control this quotient and shown to be robust to mis-specified parameters relative to the UMP. Different powers for different parameter settings motivate a map of plausible alternatives based on where this pooled $p$-value is minimized.
Authors: Zhixuan Chu, Huaiyu Guo, Xinyuan Zhou, Yijia Wang, Fei Yu, Hong Chen, Wanqing Xu, Xin Lu, Qing Cui, Longfei Li, Jun Zhou, Sheng Li
Large language models (LLMs) show promise for natural language tasks but struggle when applied directly to complex domains like finance. LLMs have difficulty reasoning about and integrating all relevant information. We propose a data-centric approach to enable LLMs to better handle financial tasks. Our key insight is that rather than overloading the LLM with everything at once, it is more effective to preprocess and pre-understand the data. We create a financial LLM (FLLM) using multitask prompt-based finetuning to achieve data pre-processing and pre-understanding. However, labeled data is scarce for each task. To overcome manual annotation costs, we employ abductive augmentation reasoning (AAR) to automatically generate training data by modifying the pseudo labels from FLLM's own outputs. Experiments show our data-centric FLLM with AAR substantially outperforms baseline financial LLMs designed for raw text, achieving state-of-the-art on financial analysis and interpretation tasks. We also open source a new benchmark for financial analysis and interpretation. Our methodology provides a promising path to unlock LLMs' potential for complex real-world domains.
Authors: Aleksandar Armacki, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar
Several recent works have studied the convergence \textit{in high probability} of stochastic gradient descent (SGD) and its clipped variant. Compared to vanilla SGD, clipped SGD is practically more stable and has the additional theoretical benefit of logarithmic dependence on the failure probability. However, the convergence of other practical nonlinear variants of SGD, e.g., sign SGD, quantized SGD and normalized SGD, that achieve improved communication efficiency or accelerated convergence is much less understood. In this work, we study the convergence bounds \textit{in high probability} of a broad class of nonlinear SGD methods. For strongly convex loss functions with Lipschitz continuous gradients, we prove a logarithmic dependence on the failure probability, even when the noise is heavy-tailed. Strictly more general than the results for clipped SGD, our results hold for any nonlinearity with bounded (component-wise or joint) outputs, such as clipping, normalization, and quantization. Further, existing results with heavy-tailed noise assume bounded $\eta$-th central moments, with $\eta \in (1,2]$. In contrast, our refined analysis works even for $\eta=1$, strictly relaxing the noise moment assumptions in the literature.
Authors: Binghui Peng, Aviad Rubinstein
We give a simple and computationally efficient algorithm that, for any constant $\varepsilon>0$, obtains $\varepsilon T$-swap regret within only $T = \mathsf{polylog}(n)$ rounds; this is an exponential improvement compared to the super-linear number of rounds required by the state-of-the-art algorithm, and resolves the main open problem of [Blum and Mansour 2007]. Our algorithm has an exponential dependence on $\varepsilon$, but we prove a new, matching lower bound.
Our algorithm for swap regret implies faster convergence to $\varepsilon$-Correlated Equilibrium ($\varepsilon$-CE) in several regimes: For normal form two-player games with $n$ actions, it implies the first uncoupled dynamics that converges to the set of $\varepsilon$-CE in polylogarithmic rounds; a $\mathsf{polylog}(n)$-bit communication protocol for $\varepsilon$-CE in two-player games (resolving an open problem mentioned by [Babichenko-Rubinstein'2017, Goos-Rubinstein'2018, Ganor-CS'2018]); and an $\tilde{O}(n)$-query algorithm for $\varepsilon$-CE (resolving an open problem of [Babichenko'2020] and obtaining the first separation between $\varepsilon$-CE and $\varepsilon$-Nash equilibrium in the query complexity model).
For extensive-form games, our algorithm implies a PTAS for $\mathit{normal}$ $\mathit{form}$ $\mathit{correlated}$ $\mathit{equilibria}$, a solution concept often conjectured to be computationally intractable (e.g. [Stengel-Forges'08, Fujii'23]).
Authors: Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
Diffusion models are a class of generative models that serve to establish a stochastic transport map between an empirically observed, yet unknown, target distribution and a known prior. Despite their remarkable success in real-world applications, a theoretical understanding of their generalization capabilities remains underdeveloped. This work embarks on a comprehensive theoretical exploration of the generalization attributes of diffusion models. We establish theoretical estimates of the generalization gap that evolves in tandem with the training dynamics of score-based diffusion models, suggesting a polynomially small generalization error ($O(n^{-2/5}+m^{-4/5})$) on both the sample size $n$ and the model capacity $m$, evading the curse of dimensionality (i.e., not exponentially large in the data dimension) when early-stopped. Furthermore, we extend our quantitative analysis to a data-dependent scenario, wherein target distributions are portrayed as a succession of densities with progressively increasing distances between modes. This precisely elucidates the adverse effect of "modes shift" in ground truths on the model generalization. Moreover, these estimates are not solely theoretical constructs but have also been confirmed through numerical simulations. Our findings contribute to the rigorous understanding of diffusion models' generalization properties and provide insights that may guide practical applications.
Authors: Chuncheng Zhang, Yingjie Shi, Zheyi Yao, Xiubao Sui, Qian Chen
Imaging through perturbed multimode fibres based on deep learning has been widely researched. However, existing methods mainly use target-speckle pairs in different configurations. It is challenging to reconstruct targets without trained networks. In this paper, we propose a physics-assisted, unsupervised, learning-based fibre imaging scheme. The role of the physical prior is to simplify the mapping relationship between the speckle pattern and the target image, thereby reducing the computational complexity. The unsupervised network learns target features according to the optimized direction provided by the physical prior. Therefore, the reconstruction process of the online learning only requires a few speckle patterns and unpaired targets. The proposed scheme also increases the generalization ability of the learning-based method in perturbed multimode fibres. Our scheme has the potential to extend the application of multimode fibre imaging.
Authors: Arghya Datta, Sayak Chakrabarty
Probabilistic principal component analysis (PPCA) is currently one of the most used statistical tools to reduce the ambient dimension of the data. From multidimensional scaling to the imputation of missing data, PPCA has a broad spectrum of applications ranging from science and engineering to quantitative finance.
Despite this wide applicability in various fields, hardly any theoretical guarantees exist to justify the soundness of the maximal likelihood (ML) solution for this model. In fact, it is well known that the maximum likelihood estimation (MLE) can only recover the true model parameters up to a rotation. The main obstruction is posed by the inherent identifiability nature of the PPCA model resulting from the rotational symmetry of the parameterization. To resolve this ambiguity, we propose a novel approach using quotient topological spaces and in particular, we show that the maximum likelihood solution is consistent in an appropriate quotient Euclidean space. Furthermore, our consistency results encompass a more general class of estimators beyond the MLE. Strong consistency of the ML estimate and consequently strong covariance estimation of the PPCA model have also been established under a compactness assumption.
Authors: Jeremy McMahan, Xiaojin Zhu
We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no longer sufficient, we show that there exist optimal deterministic policies augmented with cumulative costs. In fact, we present a fixed-parameter tractable reduction from anytime-constrained cMDPs to unconstrained MDPs. Our reduction yields planning and learning algorithms that are time and sample-efficient for tabular cMDPs so long as the precision of the costs is logarithmic in the size of the cMDP. However, we also show that computing non-trivial approximately optimal policies is NP-hard in general. To circumvent this bottleneck, we design provable approximation algorithms that efficiently compute or learn an arbitrarily accurate approximately feasible policy with optimal value so long as the maximum supported cost is bounded by a polynomial in the cMDP or the absolute budget. Given our hardness results, our approximation guarantees are the best possible under worst-case analysis.
Authors: Shanghao Shi, Ning Wang, Yang Xiao, Chaoyu Zhang, Yi Shi, Y.Thomas Hou, Wenjing Lou
Federated learning is known for its capability to safeguard participants' data privacy. However, recently emerged model inversion attacks (MIAs) have shown that a malicious parameter server can reconstruct individual users' local data samples through model updates. The state-of-the-art attacks either rely on computation-intensive search-based optimization processes to recover each input batch, making scaling difficult, or they involve the malicious parameter server adding extra modules before the global model architecture, rendering the attacks too conspicuous and easily detectable.
To overcome these limitations, we propose Scale-MIA, a novel MIA capable of efficiently and accurately recovering training samples of clients from the aggregated updates, even when the system is under the protection of a robust secure aggregation protocol. Unlike existing approaches treating models as black boxes, Scale-MIA recognizes the importance of the intricate architecture and inner workings of machine learning models. It identifies the latent space as the critical layer for breaching privacy and decomposes the complex recovery task into an innovative two-step process to reduce computation complexity. The first step involves reconstructing the latent space representations (LSRs) from the aggregated model updates using a closed-form inversion mechanism, leveraging specially crafted adversarial linear layers. In the second step, the whole input batches are recovered from the LSRs by feeding them into a fine-tuned generative decoder.
We implemented Scale-MIA on multiple commonly used machine learning models and conducted comprehensive experiments across various settings. The results demonstrate that Scale-MIA achieves excellent recovery performance on different datasets, exhibiting high reconstruction rates, accuracy, and attack efficiency on a larger scale compared to state-of-the-art MIAs.
Authors: Noah J. Bagazinski, Faez Ahmed
Ship design is a years-long process that requires balancing complex design trade-offs to create a ship that is efficient and effective. Finding new ways to improve the ship design process can lead to significant cost savings for ship building and operation. One promising technology is generative artificial intelligence, which has been shown to reduce design cycle time and create novel, high-performing designs. In literature review, generative artificial intelligence has been shown to generate ship hulls; however, ship design is particularly difficult as the hull of a ship requires the consideration of many objectives. This paper presents a study on the generation of parametric ship hull designs using a parametric diffusion model that considers multiple objectives and constraints for the hulls. This denoising diffusion probabilistic model (DDPM) generates the tabular parametric design vectors of a ship hull for evaluation. In addition to a tabular DDPM, this paper details adding guidance to improve the quality of generated ship hull designs. By leveraging classifier guidance, the DDPM produced feasible parametric ship hulls that maintain the coverage of the initial training dataset of ship hulls with a 99.5% rate, a 149x improvement over random sampling of the design vector parameters across the design space. Parametric ship hulls produced with performance guidance saw an average of 91.4% reduction in wave drag coefficients and an average of a 47.9x relative increase in the total displaced volume of the hulls compared to the mean performance of the hulls in the training dataset. The use of a DDPM to generate parametric ship hulls can reduce design time by generating high-performing hull designs for future analysis. These generated hulls have low drag and high volume, which can reduce the cost of operating a ship and increase its potential to generate revenue.
Authors: Johannes Kopp, Dominik Kellner, Aldi Piroli, Vinzenz Dallabetta, Klaus Dietmayer
The unique properties of radar sensors, such as their robustness to adverse weather conditions, make them an important part of the environment perception system of autonomous vehicles. One of the first steps during the processing of radar point clouds is often the detection of clutter, i.e. erroneous points that do not correspond to real objects. Another common objective is the semantic segmentation of moving road users. These two problems are handled strictly separate from each other in literature. The employed neural networks are always focused entirely on only one of the tasks. In contrast to this, we examine ways to solve both tasks at the same time with a single jointly used model. In addition to a new augmented multi-head architecture, we also devise a method to represent a network's predictions for the two tasks with only one output value. This novel approach allows us to solve the tasks simultaneously with the same inference time as a conventional task-specific model. In an extensive evaluation, we show that our setup is highly effective and outperforms every existing network for semantic segmentation on the RadarScenes dataset.
Authors: Xiao Li, Huan Li, Hua Lu, Christian S. Jensen, Varun Pandey, Volker Markl
Sensor data streams occur widely in various real-time applications in the context of the Internet of Things (IoT). However, sensor data streams feature missing values due to factors such as sensor failures, communication errors, or depleted batteries. Missing values can compromise the quality of real-time analytics tasks and downstream applications. Existing imputation methods either make strong assumptions about streams or have low efficiency. In this study, we aim to accurately and efficiently impute missing values in data streams that satisfy only general characteristics in order to benefit real-time applications more widely. First, we propose a message propagation imputation network (MPIN) that is able to recover the missing values of data instances in a time window. We give a theoretical analysis of why MPIN is effective. Second, we present a continuous imputation framework that consists of data update and model update mechanisms to enable MPIN to perform continuous imputation both effectively and efficiently. Extensive experiments on multiple real datasets show that MPIN can outperform the existing data imputers by wide margins and that the continuous imputation framework is efficient and accurate.
Authors: Alireza Mohammadshahi, Jannis Vamvas, Rico Sennrich
Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions. Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. Previous work has used a simple averaging of probability distributions from multiple paths, but we find that this performs worse than using a single pivot, and exacerbates the hallucination problem because the same hallucinations can be probable across different paths. As an alternative, we propose MaxEns, a combination strategy that is biased towards the most confident predictions, hypothesising that confident predictions are less prone to be hallucinations. We evaluate different strategies on the FLORES benchmark for 20 low-resource language directions, demonstrating that MaxEns improves translation quality for low-resource languages while reducing hallucination in translations, compared to both direct translation and an averaging approach. On average, multi-pivot strategies still lag behind using English as a single pivot language, raising the question of how to identify the best pivoting strategy for a given translation direction.
Authors: Joonsu Gha, Vincent Herrmann, Benjamin Grewe, Jürgen Schmidhuber, Anand Gopalakrishnan
Current object-centric learning models such as the popular SlotAttention architecture allow for unsupervised visual scene decomposition. Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition. Since concepts of opacity and occlusion in vision have no auditory analogues, the softmax normalization of alpha masks in the decoders of visual object-centric models is not well-suited for decomposing audio objects. MusicSlots overcomes this problem. We introduce a spectrogram-based multi-object music dataset tailored to evaluate object-centric learning on western tonal music. MusicSlots achieves good performance on unsupervised note discovery and outperforms several established baselines on supervised note property prediction tasks.
Authors: Brian Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel
This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPMs) and Discrete Wavelet Transformation (DWT). By enabling DDPMs to operate in the DWT domain, our DDPM models effectively hallucinate high-frequency information for super-resolved images on the wavelet spectrum, resulting in high-quality and detailed reconstructions in image space. Quantitatively, we outperform state-of-the-art diffusion-based SISR methods, namely SR3 and SRDiff, regarding PSNR, SSIM, and LPIPS on both face (8x scaling) and general (4x scaling) SR benchmarks. Meanwhile, using DWT enabled us to use fewer parameters than the compared models: 92M parameters instead of 550M compared to SR3 and 9.3M instead of 12M compared to SRDiff. Additionally, our method outperforms other state-of-the-art generative methods on classical general SR datasets while saving inference time. Finally, our work highlights its potential for various applications.
Authors: Shunfeng Wang, Yueyang Li, Haichi Luo, Chenyang Bi
In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook the crucial prior information embedded within anomalous samples. Moreover, among numerous deep learning methods, supervised methods generally exhibit superior performance compared to unsupervised methods. Considering the reasons mentioned above, we propose a self-supervised anomaly detection approach that combines contrastive learning with 2D-Flow to achieve more precise detection outcomes and expedited inference processes. On one hand, we introduce a novel approach to anomaly synthesis, yielding anomalous samples in accordance with authentic industrial scenarios, alongside their surrogate annotations. On the other hand, having obtained a substantial number of anomalous samples, we enhance the 2D-Flow framework by incorporating contrastive learning, leveraging diverse proxy tasks to fine-tune the network. Our approach enables the network to learn more precise mapping relationships from self-generated labels while retaining the lightweight characteristics of the 2D-Flow. Compared to mainstream unsupervised approaches, our self-supervised method demonstrates superior detection accuracy, fewer additional model parameters, and faster inference speed. Furthermore, the entire training and inference process is end-to-end. Our approach showcases new state-of-the-art results, achieving a performance of 99.6\% in image-level AUROC on the MVTecAD dataset and 96.8\% in image-level AUROC on the BTAD dataset.