Search Results for author:
Found 115 papers, 52 papers with code
BECEL: Benchmark for Consistency Evaluation of Language Models
Behavioural consistency is a critical condition for a language model (LM) to become trustworthy like humans.
Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction
The goal of open information extraction (OIE) is to extract facts from natural language text, and to represent them as structured triples of the form {\textless}subject, predicate, object{\textgreater}.
PiShield: A NeSy Framework for Learning with Requirements
Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains.
Exploiting T-norms for Deep Learning in Autonomous Driving
Deep learning has been at the core of the autonomous driving field development, due to the neural networks' success in finding patterns in raw data and turning them into accurate predictions.
Associative Memories in the Feature Space
This problem can be easily solved by computing \emph{similarities} in an embedding space instead of the pixel space.
How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
Further, we show how our CL does not necessarily need to be integrated at training time, as it can be also used as a guardrail at inference time, still producing some improvements in the overall performance of the models.
Pre-training and Diagnosing Knowledge Base Completion Models
The method works for both canonicalized knowledge bases and uncanonicalized or open knowledge bases, i. e., knowledge bases where more than one copy of a real-world entity or relation may exist.
Large Language Models for Mathematicians
Large language models (LLMs) such as ChatGPT have received immense interest for their general-purpose language understanding and, in particular, their ability to generate high-quality text or computer code.
Text Attribute Control via Closed-Loop Disentanglement
In this approach, we use a semi-supervised contrastive learning method to encourage the disentanglement of attributes in latent spaces.
Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary
Next, we propose an efficient parameter integration technique that updates only a few additional parameters to combine the learned interrelationship with PLMs' pre-trained knowledge.
C^2M-DoT: Cross-modal consistent multi-view medical report generation with domain transfer network
In addition, word-level optimization based on numbers ignores the semantics of reports and medical images, and the generated reports often cannot achieve good performance.
AMLP:Adaptive Masking Lesion Patches for Self-supervised Medical Image Segmentation
The proposed strategies effectively address limitations in applying masked modeling to medical images, tailored to capturing fine lesion details vital for segmentation tasks.
Brain-Inspired Computational Intelligence via Predictive Coding
Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century.
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation
This is useful in a wide range of real-world applications where collecting pixel-wise labels is not feasible in time or cost.
Causal Inference via Predictive Coding
Bayesian inference models observations: what can be inferred about y if we observe a related variable x?
Minimum Description Length Clustering to Measure Meaningful Image Complexity
We conduct experiments on seven different sets of images, which show that our method assigns the most accurate scores to all images considered.
An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models
The increasingly large size of modern pretrained language models not only makes them inherit more human-like biases from the training corpora, but also makes it computationally expensive to mitigate such biases.
KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations
While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs.
Evaluating Language Models for Mathematics through Interactions
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants.
Faithfulness Tests for Natural Language Explanations
Explanations of neural models aim to reveal a model's decision-making process for its predictions.
MvCo-DoT:Multi-View Contrastive Domain Transfer Network for Medical Report Generation
In clinical scenarios, multiple medical images with different views are usually generated at the same time, and they have high semantic consistency.
Machine Learning with Requirements: a Manifesto
In the recent years, machine learning has made great advancements that have been at the root of many breakthroughs in different application domains.
Correcting Flaws in Common Disentanglement Metrics
Recent years have seen growing interest in learning disentangled representations, in which distinct features, such as size or shape, are represented by distinct neurons.
Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation
We propose a method that does not require data augmentation, and that, differently from existing methods, regularizes the hard assignments.
MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation
We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further.
Multi-Head Feature Pyramid Networks for Breast Mass Detection
Analysis of X-ray images is one of the main tools to diagnose breast cancer.
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods.
NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning
In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match.
Mathematical Capabilities of ChatGPT
We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available datasets, as well as hand-crafted ones, using a novel methodology.
Rationalizing Predictions by Adversarial Information Calibration
One form of explanation for a prediction is an extractive rationale, i. e., a subset of features of an instance that lead the model to give its prediction on that instance.
Robust Graph Representation Learning via Predictive Coding
Predictive coding is a message-passing framework initially developed to model information processing in the brain, and now also topic of research in machine learning due to some interesting properties.
Graph Representation Learning
Out-of-Distribution Generalization
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience.
Learning to Model Multimodal Semantic Alignment for Story Visualization
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story, where the images should be realistic and keep global consistency across dynamic scenes and characters.
Predictive Coding beyond Gaussian Distributions
A large amount of recent research has the far-reaching goal of finding training methods for deep neural networks that can serve as alternatives to backpropagation (BP).
Hybrid Reinforced Medical Report Generation with M-Linear Attention and Repetition Penalty
In this article, we propose a hybrid reinforced medical report generation method with m-linear attention and repetition penalty mechanism (HReMRG-MR) to overcome these problems.
Bird-Eye Transformers for Text Generation Models
Transformers have become an indispensable module for text generation models since their great success in machine translation.
ROAD-R: The Autonomous Driving Dataset with Logical Requirements
Neural networks have proven to be very powerful at computer vision tasks.
Efficient Deep Clustering of Human Activities and How to Improve Evaluation
Progress is starting to be made in the unsupervised setting, in the form of deep HAR clustering models, which can assign labels to data without having been given any labels to train on, but there are problems with evaluating deep HAR clustering models, which makes assessing the field and devising new methods difficult.
Ranked #1 on
Human Activity Recognition
on PAMAP2
Lightweight Long-Range Generative Adversarial Networks
In this paper, we introduce novel lightweight generative adversarial networks, which can effectively capture long-range dependencies in the image generation process, and produce high-quality results with a much simpler architecture.
Memory-Driven Text-to-Image Generation
We introduce a memory-driven semi-parametric approach to text-to-image generation, which is based on both parametric and non-parametric techniques.
Word-Level Fine-Grained Story Visualization
Story visualization aims to generate a sequence of images to narrate each sentence in a multi-sentence story with a global consistency across dynamic scenes and characters.
PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training
Unlike most existing semi-supervised learning methods, adversarial training based methods distinguish samples from different sources by learning the data distribution of the segmentation map, leading the segmenter to generate more accurate predictions.
A Theoretical Framework for Inference and Learning in Predictive Coding Networks
In this paper, we provide a comprehensive theoretical analysis of the properties of PCNs trained with prospective configuration.
Explaining Chest X-ray Pathologies in Natural Language
Most deep learning algorithms lack explanations for their predictions, which limits their deployment in clinical practice.
NP-Match: When Neural Processes meet Semi-Supervised Learning
Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data.
Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation
Secondly, in fact, they are only partially based on Bayesian deep learning, as their overall architectures are not designed under the Bayesian framework.
Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning
How the brain performs credit assignment is a fundamental unsolved problem in neuroscience.
Clinical outcome prediction under hypothetical interventions -- a representation learning framework for counterfactual reasoning
Most machine learning (ML) models are developed for prediction only; offering no option for causal interpretation of their predictions or parameters/properties.
Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence
To alleviate the issue, we propose a novel intermediate training task, names meaning-matching, designed to directly learn a meaning-text correspondence, instead of relying on the distributional hypothesis.
Deep Learning with Logical Constraints
In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e. g., for safety-critical applications.
Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?
The backpropagation of error algorithm used to train deep neural networks has been fundamental to the successes of deep learning.
Universal Hopfield Networks: A General Framework for Single-Shot Associative Memory Models
A large number of neural network models of associative memory have been proposed in the literature.
Learning on Arbitrary Graph Topologies via Predictive Coding
Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network.
The Defeat of the Winograd Schema Challenge
The Winograd Schema Challenge - a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge - was proposed by Hector Levesque in 2011.
Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
A potential solution is the few-shot out-of-domain transfer of NLEs from a parent task with many NLEs to a child task.
Imposing Hard Logical Constraints on Multi-label Classification Neural Networks
In this paper, we thus propose to enhance deep learning models by incorporating background knowledge as hard logical constraints.
Rationale production to support clinical decision-making
In this work, we apply InfoCal, the current state-of-the-art model that produces extractive rationales for its predictions, to the task of predicting hospital readmission using hospital discharge notes.
Unifying Categorical Models by Explicit Disentanglement of the Labels' Generative Factors
By doing so, it is possible to merge multiple datasets based on different categorical models by projecting the data points into a unified latent space.
Associative Memories via Predictive Coding
We conclude by discussing the possible impact of this work in the neuroscience community, by showing that our model provides a plausible framework to study learning and retrieval of memories in the brain, as it closely mimics the behavior of the hippocampus as a memory index and generative model.
Knowledge Base Completion Meets Transfer Learning
The aim of knowledge base completion is to predict unseen facts from existing facts in knowledge bases.
NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models
The recent development in pretrained language models trained in a self-supervised fashion, such as BERT, is driving rapid progress in the field of NLP.
Are Training Resources Insufficient? Predict First Then Explain!
The most predominant form of these models is the explain-then-predict (EtP) structure, which first generates explanations and uses them for making decisions.
Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models
Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model.
Selective Pseudo-label Clustering
The most accurate existing approaches combine the training of the DNN with the clustering objective, so that information from the clustering process can be used to update the DNN to produce better features for clustering.
Ranked #1 on
Image Clustering
on USPS
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations.
Hi-BEHRT: Hierarchical Transformer-based model for accurate prediction of clinical events using multimodal longitudinal electronic health records
Capturing the whole history of medical encounters is expected to lead to more accurate predictions, but the inclusion of records collected for decades and from multiple resources can inevitably exceed the receptive field of the existing deep learning architectures.
RSG: A Simple but Effective Module for Learning Imbalanced Datasets
Imbalanced datasets widely exist in practice and area great challenge for training deep neural models with agood generalization on infrequent classes.
Ranked #17 on
Long-tail Learning
on Places-LT
Controlling Text Edition by Changing Answers of Specific Questions
Experimental results on the test set show that our proposed method is a good fit for this novel NLP task.
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks.
Multi-Label Classification Neural Networks with Hard Logical Constraints
Multi-label classification (MC) is a standard machine learning problem in which a data point can be associated with a set of classes.
Reverse Differentiation via Predictive Coding
Recent works prove that these methods can approximate BP up to a certain margin on multilayer perceptrons (MLPs), and asymptotically on any other complex model, and that zero-divergence inference learning (Z-IL), a variant of PC, is able to exactly implement BP on MLPs.
Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks
Predictive coding networks (PCNs) are an influential model for information processing in the brain.
Risk factor identification for incident heart failure using neural network distillation and variable selection
In this study, we propose two methods, namely, model distillation and variable selection, to untangle hidden patterns learned by an established deep learning model (BEHRT) for risk association identification.
An explainable Transformer-based deep learning model for the prediction of incident heart failure
Predicting the incidence of complex chronic conditions such as heart failure is challenging.
Orthogonal Subspace Decomposition: A New Perspective of Learning Discriminative Features for Face Clustering
Learning discriminative node features is the key to further improve the performance of graph-based face clustering.
Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration
We use an adversarial-based technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
Multi-type Disentanglement without Adversarial Training
After the latent space is disentangled, the style of a sentence can be transformed by tuning the style representation without affecting other features of the sentence.
Extracting Outcomes from Appellate Decisions in US State Courts
Predicting the outcome of a legal process has recently gained considerable research attention.
Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks
However, there are several gaps between BP and learning in biologically plausible neuronal networks of the brain (learning in the brain, or simply BL, for short), in particular, (1) it has been unclear to date, if BP can be implemented exactly via BL, (2) there is a lack of local plasticity in BP, i. e., weight updates require information that is not locally available, while BL utilizes only locally available information, and (3)~there is a lack of autonomy in BP, i. e., some external control over the neural network is required (e. g., switching between prediction and learning stages requires changes to dynamics and synaptic plasticity rules), while BL works fully autonomously.
Reinforced Medical Report Generation with X-Linear Attention and Repetition Penalty
To reduce doctors' workload, deep-learning-based automatic medical report generation has recently attracted more and more research efforts, where attention mechanisms and reinforcement learning are integrated with the classic encoder-decoder architecture to enhance the performance of deep models.
SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images
We first generate MRI images on limited datasets, then we trained three popular classification models to get the best model for tumor classification.
w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution
Non-local attention and feature learning by multi-scale methods are widely used to model network, which drives progress in medical image segmentation.
Efficient Medical Image Segmentation with Intermediate Supervision Mechanism
However, U-Net is mainly engaged in segmentation, and the extracted features are also targeted at segmentation location information, and the input and output are different.
The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets
For example, if the feminine subset of a gender-bias-measuring coreference resolution dataset contains sentences with a longer average distance between the pronoun and the correct candidate, an RNN-based model may perform worse on this subset due to long-term dependencies.
Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
Computer-Aided Diagnosis and Treatment of Tumors is a hot topic of deep learning in recent years, which constitutes a series of medical tasks, such as detection of tumor markers, the outline of tumor leisures, subtypes and stages of tumors, prediction of therapeutic effect, and drug development.
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained training feedback at word-level, to facilitate training a lightweight generator that has a small number of parameters, but can still correctly focus on specific visual attributes of an image, and then edit them without affecting other contents that are not described in the text.
Coherent Hierarchical Multi-Label Classification Networks
Hierarchical multi-label classification (HMC) is a challenging classification task extending standard multi-label classification problems by imposing a hierarchy constraint on the classes.
Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution
Overall, four categories of training and evaluation objectives have been introduced.
The Surprising Power of Graph Neural Networks with Random Node Initialization
In this work, we analyze the expressive power of GNNs with RNI, and prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.
The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets
For neural models to garner widespread public trust and ensure fairness, we must have human-intelligible explanations for their predictions.
Knowledge Graph Extraction from Videos
Nearly all existing techniques for automated video annotation (or captioning) describe videos using natural language sentences.
BoxE: A Box Embedding Model for Knowledge Base Completion
Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB).
Ranked #1 on
Link Prediction
on FB-AUTO
A Review of Winograd Schema Challenge Datasets and Approaches
The Winograd Schema Challenge is both a commonsense reasoning and natural language understanding challenge, introduced as an alternative to the Turing test.
e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning.
Deep Bayesian Gaussian Processes for Uncertainty Estimation in Electronic Health Records
In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for more comprehensive uncertainty estimation.
Image-to-Image Translation with Text Guidance
The goal of this paper is to embed controllable factors, i. e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of synthetic images.
ManiGAN: Text-Guided Image Manipulation
The goal of our paper is to semantically edit parts of an image matching a given text that describes desired attributes (e. g., texture, colour, and background), while preserving other contents that are irrelevant to the text.
Distributed Low Precision Training Without Mixed Precision
However, most low precision training solution is based on a mixed precision strategy.
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations
To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions.
Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods
We aim for this framework to provide a publicly available, off-the-shelf evaluation when the feature-selection perspective on explanations is needed.
Controllable Text-to-Image Generation
In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language descriptions.
Ranked #7 on
Text-to-Image Generation
on Multi-Modal-CelebA-HQ
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset.
A Surprisingly Robust Trick for the Winograd Schema Challenge
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
That is, there is not yet a general evaluation platform for research on multi-agent intelligence.
A Surprisingly Robust Trick for Winograd Schema Challenge
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.
Ranked #13 on
Natural Language Inference
on WNLI
Mega-Reward: Achieving Human-Level Play without Extrinsic Rewards
Intrinsic rewards were introduced to simulate how human intelligence works; they are usually evaluated by intrinsically-motivated play, i. e., playing games without extrinsic rewards but evaluated with extrinsic rewards.
Segmentation is All You Need
Region proposal mechanisms are essential for existing deep learning approaches to object detection in images.
Ranked #1 on
Head Detection
on Rebar Head
Learning to Reason: Leveraging Neural Networks for Approximate DNF Counting
Weighted model counting (WMC) has emerged as a prevalent approach for probabilistic inference.
e-SNLI: Natural Language Inference with Natural Language Explanations
In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time.
Ranked #1 on
Natural Language Inference
on e-SNLI
Diversity-Driven Extensible Hierarchical Reinforcement Learning
However, HRL with multiple levels is usually needed in many real-world scenarios, whose ultimate goals are highly abstract, while their actions are very primitive.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Ontology Reasoning with Deep Neural Networks
This is an important and at the same time very natural logical reasoning task, which is why the presented approach is applicable to a plethora of important real-world problems.
Complexity Results for Preference Aggregation over (m)CP-nets: Pareto and Majority Voting
On the other hand, global voting over non-$\mathcal{O}$-legal CP-nets has not carefully been analyzed, despite it was stated in the literature that a theoretical comparison between global and sequential voting was promising and a precise complexity analysis for global voting has been asked for multiple times.
Deep Learning for Ontology Reasoning
In this work, we present a novel approach to ontology reasoning that is based on deep learning rather than logic-based formal reasoning.
Top-k Query Answering in Datalog+/- Ontologies under Subjective Reports (Technical Report)
Theses pieces of information of every report are then combined, along with the querying user's preferences and his/her trust into each report, to rank the query results.
