Author name cluster

Dino Oglic

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

11 papers

2 author rows

ICLR Conference 2025 Conference Paper

Balancing Act: Diversity and Consistency in Large Language Model Ensembles

Ahmed Abdulaal
Chen Jin
Nina Montaña Brown
Aryo Pradipta Gema
Daniel Coelho de Castro
Daniel C. Alexander
Philip Alexander Teare
Tom Diethe

Ensembling strategies for Large Language Models (LLMs) have demonstrated significant potential in improving performance across various tasks by combining the strengths of individual models. However, identifying the most effective ensembling method remains an open challenge, as neither maximizing output consistency through self-consistency decoding nor enhancing model diversity via frameworks like "Mixture of Agents" has proven universally optimal. Motivated by this, we propose a unified framework to examine the trade-offs between task performance, model diversity, and output consistency in ensembles. More specifically, we introduce a consistency score that defines a gating mechanism for mixtures of agents and an algorithm for mixture refinement to investigate these trade-offs at the semantic and model levels, respectively. We incorporate our insights into a novel inference-time LLM ensembling strategy called the Dynamic Mixture of Agents (DMoA) and demonstrate that it achieves a new state-of-the-art result in the challenging Big Bench Hard mixed evaluations benchmark. Our analysis reveals that cross-validation bias can enhance performance, contingent on the expertise of the constituent models. We further demonstrate that distinct reasoning tasks—such as arithmetic reasoning, commonsense reasoning, and instruction following—require different model capabilities, leading to inherent task-dependent trade-offs that DMoA balances effectively.

Details

ICML Conference 2025 Conference Paper

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation

Zhihua Liu
Amrutha Saseendran
Lei Tong
Xilin He
Fariba Yousefi
Nikolay Burlutskiy
Dino Oglic
Tom Diethe

Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies on token-level cross-attention maps from a frozen diffusion model to produce segmentation surrogates or mask prompts, which are then refined into targeted object masks. Initial prompts typically lack coherence and consistency as the complexity of the image-text increases, resulting in suboptimal mask fragments. To tackle this issue, we further introduce a novel linguistic-guided visual prompt regularization that binds and clusters visual prompts based on sentence dependency and syntactic structural information, enabling the extraction of robust, noise-tolerant mask prompts, and significant improvements in segmentation accuracy. The proposed approach is effective, generalizes across different open-set segmentation tasks, and achieves state-of-the-art results of 52. 5 (+6. 8 relative) mIoU on Pascal Context 59, 67. 73 (+25. 73 relative) cIoU on gRefCOCO, and 67. 4 (+1. 1 relative to fine-tuned methods) mIoU on GranDf, which is the most complex open-set grounded segmentation task in the field.

Details

ICML Conference 2024 Conference Paper

Improving Antibody Humanness Prediction using Patent Data

Talip Ucar
Aubin Ramon
Dino Oglic
Rebecca Croasdale-Wood
Tom Diethe
Pietro Sormanni

We investigate the potential of patent data for improving the antibody humanness prediction using a multi-stage, multi-loss training process. Humanness serves as a proxy for the immunogenic response to antibody therapeutics, one of the major causes of attrition in drug discovery and a challenging obstacle for their use in clinical settings. We pose the initial learning stage as a weakly-supervised contrastive-learning problem, where each antibody sequence is associated with possibly multiple identifiers of function and the objective is to learn an encoder that groups them according to their patented properties. We then freeze a part of the contrastive encoder and continue training it on the patent data using the cross-entropy loss to predict the humanness score of a given antibody sequence. We illustrate the utility of the patent data and our approach by performing inference on three different immunogenicity datasets, unseen during training. Our empirical results demonstrate that the learned model consistently outperforms the alternative baselines and establishes new state-of-the-art on five out of six inference tasks, irrespective of the used metric.

Details

NeurIPS Conference 2022 Conference Paper

Graph Neural Networks with Adaptive Readouts

David Buterez
Jon Paul Janet
Steven J Kiddle
Dino Oglic
Pietro Liò

An effective aggregation of node features into a graph-level representation via readout functions is an essential step in numerous learning tasks involving graph neural networks. Typically, readouts are simple and non-adaptive functions designed such that the resulting hypothesis space is permutation invariant. Prior work on deep sets indicates that such readouts might require complex node embeddings that can be difficult to learn via standard neighborhood aggregation schemes. Motivated by this, we investigate the potential of adaptive readouts given by neural networks that do not necessarily give rise to permutation invariant hypothesis spaces. We argue that in some problems such as binding affinity prediction where molecules are typically presented in a canonical form it might be possible to relax the constraints on permutation invariance of the hypothesis space and learn a more effective model of the affinity by employing an adaptive readout function. Our empirical results demonstrate the effectiveness of neural readouts on more than 40 datasets spanning different domains and graph characteristics. Moreover, we observe a consistent improvement over standard readouts (i. e. , sum, max, and mean) relative to the number of neighborhood aggregation iterations and different convolutional operators.

PDF Details

JMLR Journal 2021 Journal Article

Towards a Unified Analysis of Random Fourier Features

Zhu Li
Jean-Francois Ton
Dino Oglic
Dino Sejdinovic

Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused on specific learning tasks and typically gives pessimistic bounds which are at odds with the empirical results. We tackle these problems and provide the first unified risk analysis of learning with random Fourier features using the squared error and Lipschitz continuous loss functions. In our bounds, the trade-off between the computational cost and the learning risk convergence rate is problem specific and expressed in terms of the regularization parameter and the number of effective degrees of freedom. We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to ridge leverage scores and further reduces the required number of features. As ridge leverage scores are expensive to compute, we devise a simple approximation scheme which provably reduces the computational cost without loss of statistical efficiency. Our empirical results illustrate the effectiveness of the proposed scheme relative to the standard random Fourier features method. [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details

ICML Conference 2019 Conference Paper

Scalable Learning in Reproducing Kernel Krein Spaces

Dino Oglic
Thomas Gärtner 0001

We provide the first mathematically complete derivation of the Nystr{ö}m method for low-rank approximation of indefinite kernels and propose an efficient method for finding an approximate eigendecomposition of such kernel matrices. Building on this result, we devise highly scalable methods for learning in reproducing kernel Krein spaces. The devised approaches provide a principled and theoretically well-founded means to tackle large scale learning problems with indefinite kernels. The main motivation for our work comes from problems with structured representations (e. g. , graphs, strings, time-series), where it is relatively easy to devise a pairwise (dis)similarity function based on intuition and/or knowledge of domain experts. Such functions are typically not positive definite and it is often well beyond the expertise of practitioners to verify this condition. The effectiveness of the devised approaches is evaluated empirically using indefinite kernels defined on structured and vectorial data representations.

Details

ICML Conference 2019 Conference Paper

Towards a Unified Analysis of Random Fourier Features

Zhu Li
Jean-Francois Ton
Dino Oglic
Dino Sejdinovic

Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused on specific learning tasks and typically gives pessimistic bounds which are at odds with the empirical results. We tackle these problems and provide the first unified risk analysis of learning with random Fourier features using the squared error and Lipschitz continuous loss functions. In our bounds, the trade-off between the computational cost and the expected risk convergence rate is problem specific and expressed in terms of the regularization parameter and the number of effective degrees of freedom. We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to ridge leverage scores and further reduces the required number of features. As ridge leverage scores are expensive to compute, we devise a simple approximation scheme which provably reduces the computational cost without loss of statistical efficiency.

Details

ICML Conference 2018 Conference Paper

Learning in Reproducing Kernel Krein Spaces

Dino Oglic
Thomas Gärtner 0001

We formulate a novel regularized risk minimization problem for learning in reproducing kernel Kre{ı̆}n spaces and show that the strong representer theorem applies to it. As a result of the latter, the learning problem can be expressed as the minimization of a quadratic form over a hypersphere of constant radius. We present an algorithm that can find a globally optimal solution to this non-convex optimization problem in time cubic in the number of instances. Moreover, we derive the gradient of the solution with respect to its hyperparameters and, in this way, provide means for efficient hyperparameter tuning. The approach comes with a generalization bound expressed in terms of the Rademacher complexity of the corresponding hypothesis space. The major advantage over standard kernel methods is the ability to learn with various domain specific similarity measures for which positive definiteness does not hold or is difficult to establish. The approach is evaluated empirically using indefinite kernels defined on structured as well as vectorial data. The empirical results demonstrate a superior performance of our approach over the state-of-the-art baselines.

Details

AAAI Conference 2017 Conference Paper

Active Search in Intensionally Specified Structured Spaces

Dino Oglic
Roman Garnett
Thomas Gaertner

We consider an active search problem in intensionally speci- ﬁed structured spaces. The ultimate goal in this setting is to discover structures from structurally different partitions of a ﬁxed but unknown target class. An example of such a process is that of computer-aided de novo drug design. In the past 20 years several Monte Carlo search heuristics have been developed for this process. Motivated by these hand-crafted search heuristics, we devise a Metropolis–Hastings sampling scheme where the acceptance probability is given by a probabilistic surrogate of the target property, modeled with a max entropy conditional model. The surrogate model is updated in each iteration upon the evaluation of a selected structure. The proposed approach is consistent and the empirical evidence indicates that it achieves a large structural variety of discovered targets.

PDF Details

ICML Conference 2017 Conference Paper

Nyström Method with Kernel K-means++ Samples as Landmarks

Dino Oglic
Thomas Gärtner 0001

We investigate, theoretically and empirically, the effectiveness of kernel K-means++ samples as landmarks in the Nyström method for low-rank approximation of kernel matrices. Previous empirical studies (Zhang et al. , 2008; Kumar et al. ,2012) observe that the landmarks obtained using (kernel) K-means clustering define a good low-rank approximation of kernel matrices. However, the existing work does not provide a theoretical guarantee on the approximation error for this approach to landmark selection. We close this gap and provide the first bound on the approximation error of the Nyström method with kernel K-means++ samples as landmarks. Moreover, for the frequently used Gaussian kernel we provide a theoretically sound motivation for performing Lloyd refinements of kernel K-means++ landmarks in the instance space. We substantiate our theoretical results empirically by comparing the approach to several state-of-the-art algorithms.

Details

NeurIPS Conference 2016 Conference Paper

Greedy Feature Construction

Dino Oglic
Thomas Gärtner

We present an effective method for supervised feature construction. The main goal of the approach is to construct a feature representation for which a set of linear hypotheses is of sufficient capacity -- large enough to contain a satisfactory solution to the considered problem and small enough to allow good generalization from a small number of training examples. We achieve this goal with a greedy procedure that constructs features by empirically fitting squared error residuals. The proposed constructive procedure is consistent and can output a rich set of features. The effectiveness of the approach is evaluated empirically by fitting a linear ridge regression model in the constructed feature space and our empirical results indicate a superior performance of our approach over competing methods.

PDF Details