Recent advances in machine learning have significantly improved prediction accuracy in various applications. However, ensuring the calibration of probabilistic predictions remains a significant challenge. Despite efforts to enhance model calibration, the rigorous statistical evaluation of model calibration remains less explored. In this work, we develop confidence intervals the $\ell_2$ Expected Calibration Error (ECE). We consider top-1-to-$k$ calibration, which includes both the popular notion of confidence calibration as well as full calibration. For a debiased estimator of the ECE, we show asymptotic normality, but with different convergence rates and asymptotic variances for calibrated and miscalibrated models. We develop methods to construct asymptotically valid confidence intervals for the ECE, accounting for this behavior as well as non-negativity. Our theoretical findings are supported through extensive experiments, showing that our methods produce valid confidence intervals with shorter lengths compared to those obtained by resampling-based methods.
Combinatorial assembly uses standardized unit primitives to build objects that satisfy user specifications. This paper studies assembly sequence planning (ASP) for physical combinatorial assembly. Given the shape of the desired object, the goal is to find a sequence of actions for placing unit primitives to build the target object. In particular, we aim to ensure the planned assembly sequence is physically executable. However, ASP for combinatorial assembly is particularly challenging due to its combinatorial nature. To address the challenge, we employ deep reinforcement learning to learn a construction policy for placing unit primitives sequentially to build the desired object. Specifically, we design an online physics-aware action mask that filters out invalid actions, which effectively guides policy learning and ensures violation-free deployment. In the end, we apply the proposed method to Lego assembly with more than 250 3D structures. The experiment results demonstrate that the proposed method plans physically valid assembly sequences to build all structures, achieving a $100\%$ success rate, whereas the best comparable baseline fails more than $40$ structures. Our implementation is available at \url{https://github.com/intelligent-control-lab/PhysicsAwareCombinatorialASP}.
Morphing Attack Detection (MAD) is a relevant topic that aims to detect attempts by unauthorised individuals to access a "valid" identity. One of the main scenarios is printing morphed images and submitting the respective print in a passport application process. Today, small datasets are available to train the MAD algorithm because of privacy concerns and the limitations resulting from the effort associated with the printing and scanning of images at large numbers. In order to improve the detection capabilities and spot such morphing attacks, it will be necessary to have a larger and more realistic dataset representing the passport application scenario with the diversity of devices and the resulting printed scanned or compressed images. Creating training data representing the diversity of attacks is a very demanding task because the training material is developed manually. This paper proposes two different methods based on transfer-transfer for automatically creating digital print/scan face images and using such images in the training of a Morphing Attack Detection algorithm. Our proposed method can reach an Equal Error Rate (EER) of 3.84% and 1.92% on the FRGC/FERET database when including our synthetic and texture-transfer print/scan with 600 dpi to handcrafted images, respectively.
Data-driven surrogate models have shown immense potential as quick, inexpensive approximations to complex numerical and experimental modelling tasks. However, most surrogate models of physical systems do not quantify their uncertainty, rendering their predictions unreliable, requiring further validation. Though Bayesian approximations offer some solace in estimating the error associated with these models, they cannot provide guarantees, and the quality of their inferences depends on the availability of prior information and good approximations to posteriors for complex problems. This is particularly pertinent to multi-variable or spatio-temporal problems. Our work constructs and formalises a conformal prediction framework that satisfies marginal coverage for spatio-temporal predictions in a model-agnostic manner, requiring near-zero computational costs. We provide an extensive empirical study of the application of the framework to ascertain valid error bars that provide guaranteed coverage across the surrogate model's domain of operation. The application scope of our work extends across a large range of spatio-temporal models, from solving partial differential equations to weather forecasting. Through the applications, the paper looks at providing statistically valid error bars for deterministic models, as well as crafting guarantees to the error bars of probabilistic models. Our conformal prediction formalisation provides guaranteed coverage of the surrogate model, regardless of model architecture, and its training regime and is unbothered by the curse of dimensionality.
Large language models (LLMs) have shown remarkable capability in numerous tasks and applications. However, fine-tuning LLMs using high-quality datasets under external supervision remains prohibitively expensive. In response, LLM self-improvement approaches have been vibrantly developed recently. The typical paradigm of LLM self-improvement involves training LLM on self-generated data, part of which may be detrimental and should be filtered out due to the unstable data quality. While current works primarily employs filtering strategies based on answer correctness, in this paper, we demonstrate that filtering out correct but with high distribution shift extent (DSE) samples could also benefit the results of self-improvement. Given that the actual sample distribution is usually inaccessible, we propose a new metric called DS weight to approximate DSE, inspired by the Importance Weighting methods. Consequently, we integrate DS weight with self-consistency to comprehensively filter the self-generated samples and fine-tune the language model. Experiments show that with only a tiny valid set (up to 5\% size of the training set) to compute DS weight, our approach can notably promote the reasoning ability of current LLM self-improvement methods. The resulting performance is on par with methods that rely on external supervision from pre-trained reward models.
Deep generative models have recently made a remarkable progress in capturing complex probability distributions over graphs. However, they are intractable and thus unable to answer even the most basic probabilistic inference queries without resorting to approximations. Therefore, we propose graph sum-product networks (GraphSPNs), a tractable deep generative model which provides exact and efficient inference over (arbitrary parts of) graphs. We investigate different principles to make SPNs permutation invariant. We demonstrate that GraphSPNs are able to (conditionally) generate novel and chemically valid molecular graphs, being competitive to, and sometimes even better than, existing intractable models. We find out that (Graph)SPNs benefit from ensuring the permutation invariance via canonical ordering.
The Maximum Minimal Cut Problem (MMCP), a NP-hard combinatorial optimization (CO) problem, has not received much attention due to the demanding and challenging bi-connectivity constraint. Moreover, as a CO problem, it is also a daunting task for machine learning, especially without labeled instances. To deal with these problems, this work proposes an unsupervised learning framework combined with heuristics for MMCP that can provide valid and high-quality solutions. As far as we know, this is the first work that explores machine learning and heuristics to solve MMCP. The unsupervised solver is inspired by a relaxation-plus-rounding approach, the relaxed solution is parameterized by graph neural networks, and the cost and penalty of MMCP are explicitly written out, which can train the model end-to-end. A crucial observation is that each solution corresponds to at least one spanning tree. Based on this finding, a heuristic solver that implements tree transformations by adding vertices is utilized to repair and improve the solution quality of the unsupervised solver. Alternatively, the graph is simplified while guaranteeing solution consistency, which reduces the running time. We conduct extensive experiments to evaluate our framework and give a specific application. The results demonstrate the superiority of our method against two techniques designed.
Pre-trained LLMs have demonstrated substantial capabilities across a range of conventional natural language processing (NLP) tasks, such as summarization and entity recognition. In this paper, we explore the application of LLMs in the generation of high-quality protein sequences. Specifically, we adopt a suite of pre-trained LLMs, including Mistral-7B1, Llama-2-7B2, Llama-3-8B3, and gemma-7B4, to produce valid protein sequences. All of these models are publicly available.5 Unlike previous work in this field, our approach utilizes a relatively small dataset comprising 42,000 distinct human protein sequences. We retrain these models to process protein-related data, ensuring the generation of biologically feasible protein structures. Our findings demonstrate that even with limited data, the adapted models exhibit efficiency comparable to established protein-focused models such as ProGen varieties, ProtGPT2, and ProLLaMA, which were trained on millions of protein sequences. To validate and quantify the performance of our models, we conduct comparative analyses employing standard metrics such as pLDDT, RMSD, TM-score, and REU. Furthermore, we commit to making the trained versions of all four models publicly available, fostering greater transparency and collaboration in the field of computational biology.
Current research on trajectory prediction primarily relies on data collected by onboard sensors of an ego vehicle. With the rapid advancement in connected technologies, such as vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, valuable information from alternate views becomes accessible via wireless networks. The integration of information from alternative views has the potential to overcome the inherent limitations associated with a single viewpoint, such as occlusions and limited field of view. In this work, we introduce V2INet, a novel trajectory prediction framework designed to model multi-view data by extending existing single-view models. Unlike previous approaches where the multi-view data is manually fused or formulated as a separate training stage, our model supports end-to-end training, enhancing both flexibility and performance. Moreover, the predicted multimodal trajectories are calibrated by a post-hoc conformal prediction module to get valid and efficient confidence regions. We evaluated the entire framework using the real-world V2I dataset V2X-Seq. Our results demonstrate superior performance in terms of Final Displacement Error (FDE) and Miss Rate (MR) using a single GPU. The code is publicly available at: \url{https://github.com/xichennn/V2I_trajectory_prediction}.
In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by professional human interpreters, we utilize a novel data-driven read-write strategy to balance the translation quality and latency. To address the challenge of translating in-domain terminologies, CLASI employs a multi-modal retrieving module to obtain relevant information to augment the translation. Supported by LLMs, our approach can generate error-tolerated translation by considering the input audio, historical context, and retrieved information. Experimental results show that our system outperforms other systems by significant margins. Aligned with professional human interpreters, we evaluate CLASI with a better human evaluation metric, valid information proportion (VIP), which measures the amount of information that can be successfully conveyed to the listeners. In the real-world scenarios, where the speeches are often disfluent, informal, and unclear, CLASI achieves VIP of 81.3% and 78.0% for Chinese-to-English and English-to-Chinese translation directions, respectively. In contrast, state-of-the-art commercial or open-source systems only achieve 35.4% and 41.6%. On the extremely hard dataset, where other systems achieve under 13% VIP, CLASI can still achieve 70% VIP.
Game Description Language (GDL) provides a standardized way to express diverse games in a machine-readable format, enabling automated game simulation, and evaluation. While previous research has explored game description generation using search-based methods, generating GDL descriptions from natural language remains a challenging task. This paper presents a novel framework that leverages Large Language Models (LLMs) to generate grammatically accurate game descriptions from natural language. Our approach consists of two stages: first, we gradually generate a minimal grammar based on GDL specifications; second, we iteratively improve the game description through grammar-guided generation. Our framework employs a specialized parser that identifies valid subsequences and candidate symbols from LLM responses, enabling gradual refinement of the output to ensure grammatical correctness. Experimental results demonstrate that our iterative improvement approach significantly outperforms baseline methods that directly use LLM outputs. Our code is available at https://github.com/tsunehiko/ggdg
We propose a novel regression adjustment method designed for estimating distributional treatment effect parameters in randomized experiments. Randomized experiments have been extensively used to estimate treatment effects in various scientific fields. However, to gain deeper insights, it is essential to estimate distributional treatment effects rather than relying solely on average effects. Our approach incorporates pre-treatment covariates into a distributional regression framework, utilizing machine learning techniques to improve the precision of distributional treatment effect estimators. The proposed approach can be readily implemented with off-the-shelf machine learning methods and remains valid as long as the nuisance components are reasonably well estimated. Also, we establish the asymptotic properties of the proposed estimator and present a uniformly valid inference method. Through simulation results and real data analysis, we demonstrate the effectiveness of integrating machine learning techniques in reducing the variance of distributional treatment effect estimators in finite samples.
Latent space Energy-Based Models (EBMs), also known as energy-based priors, have drawn growing interests in the field of generative modeling due to its flexibility in the formulation and strong modeling power of the latent space. However, the common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress; the degenerate MCMC sampling quality in practice often leads to degraded generation quality and instability in training, especially with highly multi-modal and/or high-dimensional target distributions. To remedy this sampling issue, in this paper we introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it. We provide theoretical evidence that the learned amortization of MCMC is a valid long-run MCMC sampler. Experiments on several image modeling benchmark datasets demonstrate the superior performance of our method compared with strong counterparts
Petri nets are a promising modeling framework for epidemiology, including the spread of disease across populations or within an individual. In particular, the Susceptible-Infectious-Recovered (SIR) compartment model is foundational for population epidemiological modeling and has been implemented in several prior Petri net studies. However, the SIR model is generally stated as a system of ordinary differential equations (ODEs) with continuous time and variables, while Petri nets are discrete event simulations. To our knowledge, no prior study has investigated the numerical equivalence of Petri net SIR models to the classical ODE formulation. We introduce crucial numerical techniques for implementing SIR models in the GPenSim package for Petri net simulations. We show that these techniques are critical for Petri net SIR models and show a relative root mean squared error of less than 1% compared to ODE simulations for biologically relevant parameter ranges. We conclude that Petri nets provide a valid framework for modeling SIR-type dynamics using biologically relevant parameter values provided that the other PN structures we outline are also implemented.
Interrogation of biological pathways is an integral part of omics data analysis. Large language models (LLMs) enable the generation of custom pathways and gene sets tailored to specific scientific questions. These targeted sets are significantly smaller than traditional pathway enrichment analysis libraries, reducing multiple hypothesis testing and potentially enhancing statistical power. Lomics (Large Language Models for Omics Studies) v1.0 is a python-based bioinformatics toolkit that streamlines the generation of pathways and gene sets for transcriptomic analysis. It operates in three steps: 1) deriving relevant pathways based on the researcher's scientific question, 2) generating valid gene sets for each pathway, and 3) outputting the results as .GMX files. Lomics also provides explanations for pathway selections. Consistency and accuracy are ensured through iterative processes, JSON format validation, and HUGO Gene Nomenclature Committee (HGNC) gene symbol verification. Lomics serves as a foundation for integrating LLMs into omics research, potentially improving the specificity and efficiency of pathway analysis.
Instruction-tuned Large Language Models (LLMs) can perform a wide range of tasks given natural language instructions to do so, but they are sensitive to how such instructions are phrased. This issue is especially concerning in healthcare, as clinicians are unlikely to be experienced prompt engineers and the potential consequences of inaccurate outputs are heightened in this domain. This raises a practical question: How robust are instruction-tuned LLMs to natural variations in the instructions provided for clinical NLP tasks? We collect prompts from medical doctors across a range of tasks and quantify the sensitivity of seven LLMs -- some general, others specialized -- to natural (i.e., non-adversarial) instruction phrasings. We find that performance varies substantially across all models, and that -- perhaps surprisingly -- domain-specific models explicitly trained on clinical data are especially brittle, compared to their general domain counterparts. Further, arbitrary phrasing differences can affect fairness, e.g., valid but distinct instructions for mortality prediction yield a range both in overall performance, and in terms of differences between demographic groups.
Generating novel molecules is challenging, with most representations leading to generative models producing many invalid molecules. Spanning Tree-based Graph Generation (STGG) is a promising approach to ensure the generation of valid molecules, outperforming state-of-the-art SMILES and graph diffusion models for unconditional generation. In the real world, we want to be able to generate molecules conditional on one or multiple desired properties rather than unconditionally. Thus, in this work, we extend STGG to multi-property-conditional generation. Our approach, STGG+, incorporates a modern Transformer architecture, random masking of properties during training (enabling conditioning on any subset of properties and classifier-free guidance), an auxiliary property-prediction loss (allowing the model to self-criticize molecules and select the best ones), and other improvements. We show that STGG+ achieves state-of-the-art performance on in-distribution and out-of-distribution conditional generation, and reward maximization.
There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.
Three-dimensional (3D) deep molecular generative models offer the advantage of goal-directed generation based on 3D-dependent properties, such as binding affinity for structure-based design within binding pockets. Traditional benchmarks created to evaluate SMILES or molecular graphs generators, such as GuacaMol or MOSES, are limited to evaluate 3D generators as they do not assess the quality of the generated molecular conformation. In this work, we hence developed GenBench3D, which implements a new benchmark for models producing molecules within a binding pocket. Our main contribution is the Validity3D metric, evaluating the conformation quality using the likelihood of bond lengths and valence angles based on reference values observed in the Cambridge Structural Database. The LiGAN, 3D-SBDD, Pocket2Mol, TargetDiff, DiffSBDD and ResGen models were benchmarked. We show that only between 0% and 11% of generated molecules have valid conformations. Performing local relaxation of generated molecules in the pocket considerably improved the Validity3D for all models by a minimum increase of 40%. For LiGAN, 3D-SBDD, or TargetDiff, the set of valid relaxed molecules shows on average higher Vina score (i.e. worse) than the set of raw generated molecules, indicating that the binding affinity of raw generated molecules might be overestimated. Using the other scoring functions, that give higher importance to ligand strain, only yield improved scores when using valid relaxed molecules. Using valid relaxed molecules, TargetDiff and Pocket2Mol show better median Vina, Glide and Gold PLP scores than other models. We have publicly released GenBench3D on GitHub for broader use: https://github.com/bbaillif/genbench3d
Computer-aided synthesis planning (CASP) algorithms have demonstrated expert-level abilities in planning retrosynthetic routes to molecules of low to moderate complexity. However, current search methods assume the sufficiency of reaching arbitrary building blocks, failing to address the common real-world constraint where using specific molecules is desired. To this end, we present a formulation of synthesis planning with starting material constraints. Under this formulation, we propose Double-Ended Synthesis Planning (DESP), a novel CASP algorithm under a bidirectional graph search scheme that interleaves expansions from the target and from the goal starting materials to ensure constraint satisfiability. The search algorithm is guided by a goal-conditioned cost network learned offline from a partially observed hypergraph of valid chemical reactions. We demonstrate the utility of DESP in improving solve rates and reducing the number of search expansions by biasing synthesis planning towards expert goals on multiple new benchmarks. DESP can make use of existing one-step retrosynthesis models, and we anticipate its performance to scale as these one-step model capabilities improve.