Search Results for author: Boi Faltings

Found 49 papers, 13 papers with code

REFINER: Reasoning Feedback on Intermediate Representations

1 code implementation4 Apr 2023 Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, Boi Faltings

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e. g., chain-of-thought prompting.

Language Model Decoding as Likelihood-Utility Alignment

1 code implementation13 Oct 2022 Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Boi Faltings, Robert West

Specifically, by analyzing the correlation between the likelihood and the utility of predictions across a diverse set of tasks, we provide empirical evidence supporting the proposed taxonomy and a set of principles to structure reasoning when choosing a decoding algorithm.

Language Modelling Text Generation

A Practical Influence Approximation for Privacy-Preserving Data Filtering in Federated Learning

no code implementations23 May 2022 Ljubomir Rokvic, Panayiotis Danassis, Boi Faltings

Federated Learning by nature is susceptible to low-quality, corrupted, or even malicious data that can severely degrade the quality of the learned model.

Data Valuation Federated Learning +2

Assistive Recipe Editing through Critiquing

no code implementations5 May 2022 Diego Antognini, Shuyang Li, Boi Faltings, Julian McAuley

Prior studies have used pre-trained language models, or relied on small paired recipe data (e. g., a recipe paired with a similar one that satisfies a dietary constraint).

Denoising Language Modelling

Positive and Negative Critiquing for VAE-based Recommenders

no code implementations5 Apr 2022 Diego Antognini, Boi Faltings

As a result of revisiting critiquing from the perspective of multimodal generative models, recent work has proposed M&Ms-VAE, which achieves state-of-the-art performance in terms of recommendation, explanation, and critiquing.

Representation Memorization for Fast Learning New Knowledge without Forgetting

no code implementations28 Aug 2021 Fei Mi, Tao Lin, Boi Faltings

In this paper, we consider scenarios that require learning new classes or data distributions quickly and incrementally over time, as it often occurs in real-world dynamic environments.

Image Classification Language Modelling +1

Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems

1 code implementation EMNLP 2021 Fei Mi, Wanhao Zhou, Fengyu Cai, Lingjing Kong, Minlie Huang, Boi Faltings

In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems.

dialog state tracking Few-Shot Learning +4

SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling

1 code implementation26 Aug 2021 Fengyu Cai, Wanhao Zhou, Fei Mi, Boi Faltings

Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems.

Intent Detection Natural Language Understanding +2

Multi-Step Critiquing User Interface for Recommender Systems

no code implementations13 Jul 2021 Diana Petrescu, Diego Antognini, Boi Faltings

Recommendations with personalized explanations have been shown to increase user trust and perceived quality and help users make better decisions.

Recommendation Systems

AI-driven Prices for Externalities and Sustainability in Production Markets

1 code implementation10 Jun 2021 Panayiotis Danassis, Aris Filos-Ratsikas, Haipeng Chen, Milind Tambe, Boi Faltings

Traditional competitive markets do not account for negative externalities; indirect costs that some participants impose on others, such as the cost of over-appropriating a common-pool resource (which diminishes future stock, and thus harvest, for everyone).


Rationalization through Concepts

no code implementations Findings (ACL) 2021 Diego Antognini, Boi Faltings

One type of explanation is a rationale, i. e., a selection of input features such as relevant text snippets from which the model computes the outcome.

Sentiment Analysis Sentiment Classification

Improving Multi-agent Coordination by Learning to Estimate Contention

no code implementations9 May 2021 Panayiotis Danassis, Florian Wiedemair, Boi Faltings

We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems.


Fast Multi-Step Critiquing for VAE-based Recommender Systems

no code implementations3 May 2021 Diego Antognini, Boi Faltings

Experiments on four real-world datasets demonstrate that among state-of-the-art models, our system is the first to dominate or match the performance in terms of recommendation, explanation, and multi-step critiquing.

Recommendation Systems

Improved Cooperation by Exploiting a Common Signal

1 code implementation3 Feb 2021 Panayiotis Danassis, Zeki Doruk Erden, Boi Faltings

Inspired by human behavior, we investigate the learning dynamics and emergence of temporal conventions, focusing on common-pool resources.

A Distributed Differentially Private Algorithm for Resource Allocation in Unboundedly Large Settings

no code implementations16 Nov 2020 Panayiotis Danassis, Aleksei Triastcyn, Boi Faltings

We introduce a practical and scalable algorithm (PALMA) for solving one of the fundamental problems of multi-agent systems -- finding matches and allocations -- in unboundedly large settings (e. g., resource allocation in urban environments, mobility-on-demand systems, etc.

Privacy Preserving

Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context

no code implementations19 Sep 2020 Milena Filipovic, Blagoj Mitrevski, Diego Antognini, Emma Lejal Glaude, Boi Faltings, Claudiu Musat

Finally, we validate that the Pareto Fronts obtained with the added objective dominate those produced by state-of-the-art models that are only optimized for accuracy on three real-world publicly available datasets.

Recommendation Systems

Momentum-based Gradient Methods in Multi-Objective Recommendation

no code implementations10 Sep 2020 Blagoj Mitrevski, Milena Filipovic, Diego Antognini, Emma Lejal Glaude, Boi Faltings, Claudiu Musat

We evaluate the benefits of Multi-objective Adamize on two multi-objective recommender systems and for three different objective combinations, both correlated or conflicting.

Recommendation Systems

Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm

no code implementations9 Sep 2020 Kirtan Padh, Diego Antognini, Emma Lejal Glaude, Boi Faltings, Claudiu Musat

The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender.

Fairness General Classification

ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation

1 code implementation23 Jul 2020 Fei Mi, Xiaoyu Lin, Boi Faltings

In this case, the recommender is updated continually and periodically with new data that arrives in each update cycle, and the updated model needs to provide recommendations for user activities before the next model update.

Continual Learning Session-Based Recommendations

Interacting with Explanations through Critiquing

no code implementations22 May 2020 Diego Antognini, Claudiu Musat, Boi Faltings

Using personalized explanations to support recommendations has been shown to increase trust and perceived quality.

Multi-Task Learning

Memory Augmented Neural Model for Incremental Session-based Recommendation

no code implementations28 Apr 2020 Fei Mi, Boi Faltings

We empirically show that MAN is well-suited for the incremental SR task, and it consistently outperforms state-of-the-art neural and nonparametric methods.

Session-Based Recommendations

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

no code implementations2 Mar 2020 Aleksei Triastcyn, Boi Faltings

This paper considers the problem of enhancing user privacy in common machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples form a generative adversarial network.

BIG-bench Machine Learning

GameWikiSum: a Novel Large Multi-Document Summarization Dataset

1 code implementation LREC 2020 Diego Antognini, Boi Faltings

In this paper, we propose GameWikiSum, a new domain-specific dataset for multi-document summarization, which is one hundred times larger than commonly used datasets, and in another domain than news.

Document Summarization Multi-Document Summarization

HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset

1 code implementation LREC 2020 Diego Antognini, Boi Faltings

In this paper, we propose HotelRec, a very large-scale hotel recommendation dataset, based on TripAdvisor, containing 50 million reviews.

Collaborative Filtering Recommendation Systems

Putting Ridesharing to the Test: Efficient and Scalable Solutions and the Power of Dynamic Vehicle Relocation

no code implementations17 Dec 2019 Panayiotis Danassis, Marija Sakota, Aris Filos-Ratsikas, Boi Faltings

We study the optimization of large-scale, real-time ridesharing systems and propose a modular design methodology, Component Algorithms for Ridesharing (CAR).

Federated Learning with Bayesian Differential Privacy

no code implementations22 Nov 2019 Aleksei Triastcyn, Boi Faltings

We consider the problem of reinforcing federated learning with formal privacy guarantees.

Federated Learning Image Classification

Federated Generative Privacy

no code implementations18 Oct 2019 Aleksei Triastcyn, Boi Faltings

In this paper, we propose FedGP, a framework for privacy-preserving data release in the federated learning setting.

Federated Learning Privacy Preserving

Multi-Dimensional Explanation of Target Variables from Documents

no code implementations25 Sep 2019 Diego Antognini, Claudiu Musat, Boi Faltings

Past work used attention and rationale mechanisms to find words that predict the target variable of a document.

Multi-Task Learning Sentiment Analysis

Multi-Dimensional Explanation of Reviews

no code implementations25 Sep 2019 Diego Antognini, Claudiu Musat, Boi Faltings

Neural models achieved considerable improvement for many natural language processing tasks, but they offer little transparency, and interpretability comes at a cost.

Multi-Task Learning Sentiment Analysis

Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization

no code implementations WS 2019 Diego Antognini, Boi Faltings

To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings: universal embeddings, which are trained on a large unrelated corpus, and domain-specific embeddings, which are learned during training.

Document Summarization Multi-Document Summarization +1

An Effective Upperbound on Treewidth Using Partial Fill-in of Separators

no code implementations6 Sep 2019 Boi Faltings, Martin Charles Golumbic

Partitioning a graph using graph separators, and particularly clique separators, are well-known techniques to decompose a graph into smaller units which can be treated independently.

Rewarding High-Quality Data via Influence Functions

no code implementations30 Aug 2019 Adam Richardson, Aris Filos-Ratsikas, Boi Faltings

We consider a crowdsourcing data acquisition scenario, such as federated learning, where a Center collects data points from a set of rational Agents, with the aim of training a model.

Federated Learning Vocal Bursts Intensity Prediction

Infochain: A Decentralized, Trustless and Transparent Oracle on Blockchain

no code implementations27 Aug 2019 Naman Goel, Cyril van Schreven, Aris Filos-Ratsikas, Boi Faltings

For the first time, we show how to implement a trustless and transparent oracle in Ethereum.

Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior

no code implementations25 Feb 2019 Panayiotis Danassis, Aris Filos-Ratsikas, Boi Faltings

We present a novel anytime heuristic (ALMA), inspired by the human principle of altruism, for solving the assignment problem.

Crowdsourcing with Fairness, Diversity and Budget Constraints

no code implementations31 Oct 2018 Naman Goel, Boi Faltings

Recent studies have shown that the labels collected from crowdworkers can be discriminatory with respect to sensitive attributes such as gender and race.

BIG-bench Machine Learning Fairness

Context Tree for Adaptive Session-based Recommendation

1 code implementation10 Jun 2018 Fei Mi, Boi Faltings

Therefore, recommendations need to be adaptive to such frequent changes.

Information Retrieval

CompNet: Neural networks growing via the compact network morphism

no code implementations27 Apr 2018 Jun Lu, Wei Ma, Boi Faltings

We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact.


Deep Bayesian Trust : A Dominant and Fair Incentive Mechanism for Crowd

no code implementations16 Apr 2018 Naman Goel, Boi Faltings

We propose a novel mechanism that assigns gold tasks to only a few workers and exploits transitivity to derive accuracy of the rest of the workers from their peers' accuracy.


Generating Artificial Data for Private Deep Learning

no code implementations8 Mar 2018 Aleksei Triastcyn, Boi Faltings

In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset.

BIG-bench Machine Learning Privacy Preserving

Generating Differentially Private Datasets Using GANs

no code implementations ICLR 2018 Aleksei Triastcyn, Boi Faltings

In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data.

BIG-bench Machine Learning Privacy Preserving

Personalization in Goal-Oriented Dialog

1 code implementation22 Jun 2017 Chaitanya K. Joshi, Fei Mi, Boi Faltings

The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios.

Goal-Oriented Dialog Multi-Task Learning

Protecting Privacy through Distributed Computation in Multi-agent Decision Making

no code implementations4 Feb 2014 Thomas Leaute, Boi Faltings

As large-scale theft of data from corporate servers is becoming increasingly common, it becomes interesting to examine alternatives to the paradigm of centralizing sensitive data into large databases.

Decision Making Scheduling

Personalized News Recommendation with Context Trees

no code implementations4 Mar 2013 Florent Garcin, Christos Dimitrakakis, Boi Faltings

The profusion of online news articles makes it difficult to find interesting articles, a problem that can be assuaged by using a recommender system to bring the most relevant news stories to readers.

News Recommendation Recommendation Systems

Cannot find the paper you are looking for? You can Submit a new open access paper.