Search

The rapid expansion of foundation models (FMs), such as large language models (LLMs), has given rise to FMware--software systems that integrate FMs as core components. While building demonstration-level FMware is relatively straightforward, transitioning to production-ready systems presents numerous challenges, including reliability, high implementation costs, scalability, and compliance with privacy regulations. This paper provides a thematic analysis of the key obstacles in productionizing FMware, synthesized from industry experience and diverse data sources, including hands-on involvement in the Open Platform for Enterprise AI (OPEA) and FMware lifecycle engineering. We identify critical issues in FM selection, data and model alignment, prompt engineering, agent orchestration, system testing, and deployment, alongside cross-cutting concerns such as memory management, observability, and feedback integration. We discuss needed technologies and strategies to address these challenges and offer guidance on how to enable the transition from demonstration systems to scalable, production-ready FMware solutions. Our findings underscore the importance of continued research and multi-industry collaboration to advance the development of production-ready FMware.

Large Language Models excel in tasks like natural language understanding and text generation. Prompt engineering plays a critical role in leveraging LLM effectively. However, LLMs black-box nature hinders its interpretability and effective prompting engineering. A wide range of model explanation approaches have been developed for deep learning models, However, these local explanations are designed for single-output tasks like classification and regression,and cannot be directly applied to LLMs, which generate sequences of tokens. Recent efforts in LLM explanation focus on natural language explanations, but they are prone to hallucinations and inaccuracies. To address this, we introduce PromptExp , a framework for multi-granularity prompt explanations by aggregating token-level insights. PromptExp introduces two token-level explanation approaches: 1. an aggregation-based approach combining local explanation techniques, and 2. a perturbation-based approach with novel techniques to evaluate token masking impact. PromptExp supports both white-box and black-box explanations and extends explanations to higher granularity levels, enabling flexible analysis. We evaluate PromptExp in case studies such as sentiment analysis, showing the perturbation-based approach performs best using semantic similarity to assess perturbation impact. Furthermore, we conducted a user study to confirm PromptExp's accuracy and practical value, and demonstrate its potential to enhance LLM interpretability., Comment: 11 pages

Underwater mine detection with deep learning suffers from limitations due to the scarcity of real-world data. This scarcity leads to overfitting, where models perform well on training data but poorly on unseen data. This paper proposes a Syn2Real (Synthetic to Real) domain generalization approach using diffusion models to address this challenge. We demonstrate that synthetic data generated with noise by DDPM and DDIM models, even if not perfectly realistic, can effectively augment real-world samples for training. The residual noise in the final sampled images improves the model's ability to generalize to real-world data with inherent noise and high variation. The baseline Mask-RCNN model when trained on a combination of synthetic and original training datasets, exhibited approximately a 60% increase in Average Precision (AP) compared to being trained solely on the original training data. This significant improvement highlights the potential of Syn2Real domain generalization for underwater mine detection tasks., Comment: 7 pages, 4 figures and 3 tables

In search and advertisement ranking, it is often required to simultaneously maximize multiple objectives. For example, the objectives can correspond to multiple intents of a search query, or in the context of advertising, they can be relevance and revenue. It is important to efficiently find rankings which strike a good balance between such objectives. Motivated by such applications, we formulate a general class of problems where - each result gets a different score corresponding to each objective, - the results of a ranking are aggregated by taking, for each objective, a weighted sum of the scores in the order of the ranking, and - an arbitrary concave function of the aggregates is maximized. Combining the aggregates using a concave function will naturally lead to more balanced outcomes. We give an approximation algorithm in a bicriteria/resource augmentation setting: the algorithm with a slight advantage does as well as the optimum. In particular, if the aggregation step is just the sum of the top k results, then the algorithm outputs k + 1 results which do as well the as the optimal top k results. We show how this approach helps with balancing different objectives via simulations on synthetic data as well as on real data from LinkedIn.

Background: Data quality is vital in software analytics, particularly for machine learning (ML) applications like software defect prediction (SDP). Despite the widespread use of ML in software engineering, the effect of data quality antipatterns on these models remains underexplored. Objective: This study develops a taxonomy of ML-specific data quality antipatterns and assesses their impact on software analytics models' performance and interpretation. Methods: We identified eight types and 14 sub-types of ML-specific data quality antipatterns through a literature review. We conducted experiments to determine the prevalence of these antipatterns in SDP data (RQ1), assess how cleaning order affects model performance (RQ2), evaluate the impact of antipattern removal on performance (RQ3), and examine the consistency of interpretation from models built with different antipatterns (RQ4). Results: In our SDP case study, we identified nine antipatterns. Over 90% of these overlapped at both row and column levels, complicating cleaning prioritization and risking excessive data removal. The order of cleaning significantly impacts ML model performance, with neural networks being more resilient to cleaning order changes than simpler models like logistic regression. Antipatterns such as Tailed Distributions and Class Overlap show a statistically significant correlation with performance metrics when other antipatterns are cleaned. Models built with different antipatterns showed moderate consistency in interpretation results. Conclusion: The cleaning order of different antipatterns impacts ML model performance. Five antipatterns have a statistically significant correlation with model performance when others are cleaned. Additionally, model interpretation is moderately affected by different data quality antipatterns.

Bindings for machine learning frameworks (such as TensorFlow and PyTorch) allow developers to integrate a framework's functionality using a programming language different from the framework's default language (usually Python). In this paper, we study the impact of using TensorFlow and PyTorch bindings in C#, Rust, Python and JavaScript on the software quality in terms of correctness (training and test accuracy) and time cost (training and inference time) when training and performing inference on five widely used deep learning models. Our experiments show that a model can be trained in one binding and used for inference in another binding for the same framework without losing accuracy. Our study is the first to show that using a non-default binding can help improve machine learning software quality from the time cost perspective compared to the default Python binding while still achieving the same level of correctness.

We present logistic dark energy model (LDEM), where the dark energy density follows a logistic function for the scale factor. The equation of state parameter of dark energy ($w_D$) transitioned from $-1$ in the distant past to its current value of $-0.76$, closely resembling the $\Lambda$CDM model in the early epoch and showing significant deviation in the late phase. The evolution of the deceleration parameter in the LDEM signifies its success in explaining the late-time cosmic acceleration. Model selection based on the Bayesian Information Criterion (BIC), incorporating observations from Type Ia Supernovae (SNe Ia), Observational Hubble data (OHD), and Baryon Acoustic Oscillation (BAO) strongly favors the LDEM over the conventional $\Lambda$CDM model, where BIC is estimated to be $\sim -20$. Incorporating the shift parameter derived from the Cosmic Microwave Background (CMB) data shows competing evidence of the LDEM over the standard $\Lambda$CDM. Remarkably, the Hubble constant ($H_0$) value computed using any of the datasets tends to align closely with the predictions from the Cosmic Microwave Background (CMB), suggesting a need to reconsider the local measurement.

Data clones are defined as multiple copies of the same data among datasets. Presence of data clones between datasets can cause issues such as difficulties in managing data assets and data license violations when using datasets with clones to build AI software. However, detecting data clones is not trivial. Majority of the prior studies in this area rely on structural information to detect data clones (e.g., font size, column header). However, tabular datasets used to build AI software are typically stored without any structural information. In this paper, we propose a novel method called SimClone for data clone detection in tabular datasets without relying on structural information. SimClone method utilizes value similarities for data clone detection. We also propose a visualization approach as a part of our SimClone method to help locate the exact position of the cloned data between a dataset pair. Our results show that our SimClone outperforms the current state-of-the-art method by at least 20\% in terms of both F1-score and AUC. In addition, SimClone's visualization component helps identify the exact location of the data clone in a dataset with a Precision@10 value of 0.80 in the top 20 true positive predictions., Comment: 24 pages, 9 figures

In the international development community, the term "digital public goods" is used to describe open-source digital products (e.g., software, datasets) that aim to address the United Nations (UN) Sustainable Development Goals. DPGs are increasingly being used to deliver government services around the world (e.g., ID management, healthcare registration). Because DPGs may handle sensitive data, the UN has established user privacy as a first-order requirement for DPGs. The privacy risks of DPGs are currently managed in part by the DPG standard, which includes a prerequisite questionnaire with questions designed to evaluate a DPG's privacy posture. This study examines the effectiveness of the current DPG standard for ensuring adequate privacy protections. We present a systematic assessment of responses from DPGs regarding their protections of users' privacy. We also present in-depth case studies from three widely-used DPGs to identify privacy threats and compare this to their responses to the DPG standard. Our findings reveal limitations in the current DPG standard's evaluation approach. We conclude by presenting preliminary recommendations and suggestions for strengthening the DPG standard as it relates to privacy. Additionally, we hope this study encourages more usable privacy research on communicating privacy, not only to end users but also third-party adopters of user-facing technologies.

We establish a connection between problems studied in rigidity theory and matroids arising from linear algebraic constructions like tensor products and symmetric products. A special case of this correspondence identifies the problem of giving a description of the correctable erasure patterns in a maximally recoverable tensor code with the problem of describing bipartite rigid graphs or low-rank completable matrix patterns. Additionally, we relate dependencies among symmetric products of generic vectors to graph rigidity and symmetric matrix completion. With an eye toward applications to computer science, we study the dependency of these matroids on the characteristic by giving new combinatorial descriptions in several cases, including the first description of the correctable patterns in an (m, n, a=2, b=2) maximally recoverable tensor code.

Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is private and therefore cannot be shared or used freely due to privacy concerns. Generating synthetic replicas of private text data with a formal privacy guarantee, i.e., differential privacy (DP), offers a promising and scalable solution. However, existing methods necessitate DP finetuning of large language models (LLMs) on private data to generate DP synthetic data. This approach is not viable for proprietary LLMs (e.g., GPT-3.5) and also demands considerable computational resources for open-source LLMs. Lin et al. (2024) recently introduced the Private Evolution (PE) algorithm to generate DP synthetic images with only API access to diffusion models. In this work, we propose an augmented PE algorithm, named Aug-PE, that applies to the complex setting of text. We use API access to an LLM and generate DP synthetic text without any model training. We conduct comprehensive experiments on three benchmark datasets. Our results demonstrate that Aug-PE produces DP synthetic text that yields competitive utility with the SOTA DP finetuning baselines. This underscores the feasibility of relying solely on API access of LLMs to produce high-quality DP synthetic texts, thereby facilitating more accessible routes to privacy-preserving LLM applications. Our code and data are available at https://github.com/AI-secure/aug-pe., Comment: ICML'24 Spotlight

Recent advances in van der Waals (vdW) materials have sparked renewed interest in the impact of dimensionality on magnetic phase transitions. While ordered magnetic phases have been demonstrated to survive in the two-dimensional (2D) limit, the quest for a spin-glass with quenched magnetic disorder in lower dimensions has proven elusive. Here we show evidence of a spin-glass emerging from randomly distributed Fe atoms in Fe3GeTe2, the first time such a state has been reported in a vdW material. AC magnetic susceptibility displays a strong frequency dependence indicative of slow spin dynamics. Additional distinctive phenomena, including ageing, chaos, and memory effects, further substantiate the existence of a glassy state. Remarkably, we find that this state persists even in single-unit-cell thick Fe3GeTe2, thereby confirming the existence of a 2D spin-glass. The formation of spin-glass states via intercalation in vdW systems allows for highly tunable spin-glass states that are otherwise difficult to realize.

Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built using FMs as FMware. The unique properties of FMware (e.g., prompts, agents, and the need for orchestration), coupled with the intrinsic limitations of FMs (e.g., hallucination) lead to a completely new set of software engineering challenges. Based on our industrial experience, we identified 10 key SE4FMware challenges that have caused enterprise FMware development to be unproductive, costly, and risky. In this paper, we discuss these challenges in detail and state the path for innovation that we envision. Next, we present FMArts, which is our long-term effort towards creating a cradle-to-grave platform for the engineering of trustworthy FMware. Finally, we (i) show how the unique properties of FMArts enabled us to design and develop a complex FMware for a large customer in a timely manner and (ii) discuss the lessons that we learned in doing so. We hope that the disclosure of the aforementioned challenges and our associated efforts to tackle them will not only raise awareness but also promote deeper and further discussions, knowledge sharing, and innovative solutions across the software engineering discipline.

As Graph Neural Networks (GNNs) become popular, libraries like PyTorch-Geometric (PyG) and Deep Graph Library (DGL) are proposed; these libraries have emerged as the de facto standard for implementing GNNs because they provide graph-oriented APIs and are purposefully designed to manage the inherent sparsity and irregularity in graph structures. However, these libraries show poor scalability on multi-core processors, which under-utilizes the available platform resources and limits the performance. This is because GNN training is a resource-intensive workload with high volume of irregular data accessing, and existing libraries fail to utilize the memory bandwidth efficiently. To address this challenge, we propose ARGO, a novel runtime system for GNN training that offers scalable performance. ARGO exploits multi-processing and core-binding techniques to improve platform resource utilization. We further develop an auto-tuner that searches for the optimal configuration for multi-processing and core-binding. The auto-tuner works automatically, making it completely transparent from the user. Furthermore, the auto-tuner allows ARGO to adapt to various platforms, GNN models, datasets, etc. We evaluate ARGO on two representative GNN models and four widely-used datasets on two platforms. With the proposed autotuner, ARGO is able to select a near-optimal configuration by exploring only 5% of the design space. ARGO speeds up state-of-the-art GNN libraries by up to 5.06x and 4.54x on a four-socket Ice Lake machine with 112 cores and a two-socket Sapphire Rapids machine with 64 cores, respectively. Finally, ARGO can seamlessly integrate into widely-used GNN libraries (e.g., DGL, PyG) with few lines of code and speed up GNN training., Comment: To appear in IEEE International Parallel and Distributed Processing Symposium (IPDPS) 2024

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. Overfitting can be (1) prevented (e.g., using dropout or early stopping) or (2) detected in a trained model (e.g., using correlation-based approaches). Both overfitting detection and prevention approaches that are currently used have constraints (e.g., requiring modification of the model structure, and high computing resources). In this paper, we propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history (i.e., validation losses). Our approach first trains a time series classifier on training histories of overfit models. This classifier is then used to detect if a trained model is overfit. In addition, our trained classifier can be used to prevent overfitting by identifying the optimal point to stop a model's training. We evaluate our approach on its ability to identify and prevent overfitting in real-world samples. We compare our approach against correlation-based detection approaches and the most commonly used prevention approach (i.e., early stopping). Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach. Furthermore, our approach can stop training to avoid overfitting at least 32% of the times earlier than early stopping and has the same or a better rate of returning the best model.

The possible existence of a family of $uudc\overline{c}$ pentaquark system was explored through the application of Thomas Fermi Quark Model on the system. Considering a pocket of pentaquark contains $5$ quarks, the density functions, and energies of $10$ different pockets of pentaquarks were studied. Out of these $10$ different pockets, a single pocket of pentaquark was found to be more stable as its total energy was lowest compared to others. The kinetic, potential, and volume energies of all pockets of pentaquarks were calculated and the nature of the plots was investigated. The plots displayed an increasing trend for all energies except for kinetic energy, which exhibited a decreasing pattern., Comment: 60 pages, 21 figures, Master's thesis submitted to the Central Department of Physics, Tribhuvan University