arXiv research

Low-rank framework for task-specific LLM ranking from sparse comparisons.

Hierarchical framework for model evaluation on leaderboards

Boosting for label ranking outperforms existing methods.

A ranking network improves neural architecture search efficiency.

This paper protects rankings from differential privacy breaches.

The two main tasks in the Recommender Systems domain are the ranking and rating prediction tasks. The rating prediction task aims at predicting to what extent a user would like any given item, which would enable to recommend the items with the highest predicted scores. The ranking task on the other hand directly aims a…

Owing to the advancement of deep learning, artificial systems are now rival to humans in several pattern recognition tasks, such as visual recognition of object categories. However, this is only the case with the tasks for which correct answers exist independent of human perception. There is another type of tasks for w…

Improved unsupervised probing for ranking tasks using Contrast-Consistent Ranking.

Study multi-task learning with low-rank representation in stochastic linear bandits.

Scorio.jl ranks systems from repeated tasks using various methods.

Low-rank structure emerges in neural networks during learning.

BoRA finetunes multi-task LLMs by sharing information through hierarchical priors.

This paper presents our system details and results of participation in the RDoC Tasks of BioNLP-OST 2019. Research Domain Criteria (RDoC) construct is a multi-dimensional and broad framework to describe mental health disorders by combining knowledge from genomics to behaviour. Non-availability of RDoC labelled dataset …

Proposes GTTN for discovering all low-rank structures in deep multi-task learning.

Paper introduces GAMs for interpretable learning-to-rank models.

New method learns shared structures in non-linear tasks.

TA-VAAL improves active learning by better utilizing task structures and overall data distribution.

The paper ranks experts based on task performance with noisy evaluations.

Bayesian framework for sequential learning tasks with low-rank approximations.

Multitask learning, i.e. taking advantage of the relatedness of individual tasks in order to improve performance on all of them, is a core challenge in the field of machine learning. We focus on matrix regression tasks where the rank of the weight matrix is constrained to reduce sample complexity. We introduce the comm…

Unsupervised ranking faces one critical challenge in evaluation applications, that is, no ground truth is available. When PageRank and its variants show a good solution in related subjects, they are applicable only for ranking from link-structure data. In this work, we focus on unsupervised ranking from multi-attribute…

Parallel deep learning architectures like fine-tuned BERT and MT-DNN, have quickly become the state of the art, bypassing previous deep and shallow learning methods by a large margin. More recently, pre-trained models from large related datasets have been able to perform well on many downstream tasks by just fine-tunin…

RNNs solve modular addition tasks using low rank and sparse Fourier structures.

In this paper, we propose a novel multi-task learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multi-task learning problem, we propose to learn a low-rank deep…

Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items are scored independently by their similarity to the query in the latent embedding…

Framework learns sentence order from paragraphs using attention and transformer networks.

Ranking is a key aspect of many applications, such as information retrieval, question answering, ad placement and recommender systems. Learning to rank has the goal of estimating a ranking model automatically from training data. In practical settings, the task often reduces to estimating a rank functional of an object …

FLoE adapts LLMs by selectively deploying LoRA adapters based on layer importance and task requirements.

Develops a new fairness learning approach for multi-task regression models.

Proposes semi-supervised feature ranking for handling high-dimensional, unlabeled data.

Ranking data arises in a wide variety of application areas but remains difficult to model, learn from, and predict. Datasets often exhibit multimodality, intransitivity, or incomplete rankings---particularly when generated by humans---yet popular probabilistic models are often too rigid to capture such complexities. In…

Research characterizes learnability of multilabel ranking problems.

Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorizatio…

Factorization machines (FM) are a popular model class to learn pairwise interactions by a low-rank approximation. Different from existing FM-based approaches which use a fixed rank for all features, this paper proposes a Rank-Aware FM (RaFM) model which adopts pairwise interactions from embeddings with different ranks.…

New method solves nonsmooth low-rank matrix optimization problems efficiently.

Flora uses random projections to achieve high-rank updates with low memory usage.

We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP). WMRB uses a new rank estimator and an efficient batch training algorithm. The approach allows more accurate item rank approximation and explicit utilization of…

MiM-StocR combines momentum indicators and adaptive ranking loss for better stock recommendation.

Improved ranking method for scarce data with feature info.

VLM judges rank well but score poorly; task difficulty and annotation quality affect interval width.

Modern navigation services often provide multiple paths connecting the same source and destination for users to select. Hence, ranking such paths becomes increasingly important, which directly affects the service quality. We present PathRank, a data-driven framework for ranking paths based on historical trajectories us…

The paper analyzes how forgetting in LLMs is linked to simple task-upstream example associations.

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints bet…

MARS automatically selects tensor decomposition ranks, improving performance in neural network tasks.

AdaRL improves robust RL by adaptively adjusting policy complexity.

Proposes a new method for rank-consistent ordinal regression without weight-sharing constraints.

The paper introduces a framework to select efficient datasets for preserving model rankings.

This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.