This paper studies the property of permutation invariance in the context of structured prediction. The paper argues that in many applications permutation invariance is a desirable property of a solution and it makes sense to design the model such that it is satisfied by construction rather than to rely on learning to get this property. The paper proposes a model to represent permutation invariant functions and claims that this model is a universal approximator within this family. The proposed method is evaluated on a synthetic and a real task (labelling of scene graphs). 1) Most importantly, I think that in the current form the proof of the main theoretical result (Theorem 1) is wrong. The problem is with the reverse direction proving that any permutation invariant function can be represented in the form of Theorem 1. Specifically, Lines 142-159 construct matrix M which aggregates information about the graph edges.

The model consists of a novel covariance function, which considers nodes in the 1-hop neighbourhood.

Accurately modeling the relationships between skills is a crucial part of human resources processes such as recruitment and employee development. Yet, no benchmarks exist to evaluate such methods directly. We construct and release SkillMatch, a benchmark for the task of skill relatedness, based on expert knowledge mining from millions of job ads. Additionally, we propose a scalable self-supervised learning technique to adapt a Sentence-BERT model based on skill co-occurrence in job ads. This new method greatly surpasses traditional models for skill relatedness as measured on SkillMatch. By releasing SkillMatch publicly, we aim to contribute a foundation for research towards increased accuracy and transparency of skill-based recommendation systems.

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing overall load balancing and collaborative efficacy. Extensive experiments verify the effectiveness and versatility of CNF in defending against various attacks across different neural VRP methods. Notably, our approach also achieves impressive out-of-distribution generalization on benchmark instances.

We present an approach for the analysis of hybrid visual compositions in animation in the domain of ephemeral film. We combine ideas from semi-supervised and weakly supervised learning to train a model that can segment hybrid compositions without requiring pre-labeled segmentation masks. We evaluate our approach on a set of ephemeral films from 13 film archives. Results demonstrate that the proposed learning strategy yields a performance close to a fully supervised baseline. On a qualitative level the performed analysis provides interesting insights on hybrid compositions in animation film.

We introduce Functional Group-Aware Representations for Small Molecules (FARM), a novel foundation model designed to bridge the gap between SMILES, natural language, and molecular graphs. The key innovation of FARM lies in its functional group-aware tokenization, which directly incorporates functional group information into the representations. This strategic reduction in tokenization granularity is intentionally aligned with key drivers of functional properties (i.e., functional groups), enhancing the model's understanding of chemical language. By expanding the chemical lexicon, FARM more effectively bridges SMILES and natural language, ultimately advancing the model's capacity to predict molecular properties. FARM also represents molecules from two perspectives: by using masked language modeling to capture atom-level features and by employing graph neural networks to encode the whole molecule topology. We rigorously evaluate FARM on the MoleculeNet dataset, where it achieves state-of-the-art performance on 10 out of 12 tasks. These results highlight FARM's potential to improve molecular representation learning, with promising applications in drug discovery and pharmaceutical research. Artificial intelligence (AI) has emerged as a transformative tool in accelerating scientific discovery, particularly in drug development. However, one of the central challenges in this field is the scarcity of large labeled datasets required for traditional supervised learning methods. This has shifted the focus towards self-supervised pre-trained models that can extract meaningful patterns from vast amounts of unlabeled molecular data (Shen & Nicolaou, 2019). As a result, the development of robust foundation models for molecular representations is now more critical than ever. Despite significant advancements in other domains, such as natural language processing (NLP) and computer vision, there is still no dominant foundation model tailored to molecular representation in drug discovery (Zhang et al., 2023b). This paper begins to address this pressing gap by introducing an innovative approach that leverages functional group (FG)-aware tokenization in the context of both sequence-based and graph-based molecular representations.

Neural Information Processing Systems http://nips.cc/

Adversarial machines, where a learner competes against an adversary, have regained much recent interest in machine learning. They are naturally in the form of saddle-point optimization, often with separable structure but sometimes also with unmanageably large dimension. In this work we show that adversarial prediction under multivariate losses can be solved much faster than they used to be. We first reduce the problem size exponentially by using appropriate sufficient statistics, and then we adapt the new stochastic variance-reduced algorithm of Balamurugan & Bach (2016) to allow any Bregman divergence. We prove that the same linear rate of convergence is retained and we show that for adversarial prediction using KL-divergence we can further achieve a speedup of #example times compared with the Euclidean alternative. We verify the theoretical findings through extensive experiments on two example applications: adversarial prediction and LPboosting.

Key to multitask learning is exploiting the relationships between different tasks in order to improve prediction performance. Most previous methods have focused on the case where tasks relations can be modeled as linear operators and regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related is often restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to satisfy. We show that our algorithm can be efficiently implemented and study its generalization properties, proving universal consistency and learning rates. Our theoretical analysis highlights the benefits of non-linear multitask learning over learning the tasks independently. Encouraging experimental results show the benefits of the proposed method in practice.

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g.