1 code implementation • 31 Mar 2024 • Yashar Deldjoo, Zhankui He, Julian McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, René Vidal, Maheswaran Sathiamoorthy, Atoosa Kasirzadeh, Silvia Milano
Traditional recommender systems (RS) have used user-item rating histories as their primary data source, with collaborative filtering being one of the principal methods.
1 code implementation • 3 Mar 2024 • Willis Guo, Armin Toroghi, Scott Sanner
In this work, we seek a novel KGQA dataset that supports commonsense reasoning and focuses on long-tail entities (e. g., non-mainstream and recent entities) where LLMs frequently hallucinate, and thus create the need for novel methodologies that leverage the KG for factual and attributable commonsense inference.
no code implementations • 3 Mar 2024 • Armin Toroghi, Willis Guo, Mohammad Mahdi Abdollah Pour, Scott Sanner
Knowledge Graph Question Answering (KGQA) methods seek to answer Natural Language questions using the relational information stored in Knowledge Graphs (KGs).
no code implementations • 20 Jan 2024 • Michael Gimelfarb, Ayal Taitler, Scott Sanner
To achieve such results, CGPO proposes a bi-level mixed-integer nonlinear optimization framework for optimizing policies within defined expressivity classes (i. e. piecewise (non)-linear) and reduces it to an optimal constraint generation methodology that adversarially generates worst-case state trajectories.
no code implementations • 5 Sep 2023 • Griffin Floto, Thorsteinn Jonsson, Mihai Nica, Scott Sanner, Eric Zhengyu Zhu
However, the desired continuous nature of the noising process can be at odds with discrete data.
2 code implementations • 1 Aug 2023 • Mohammad Mahdi Abdollah Pour, Parsa Farinneya, Armin Toroghi, Anton Korikov, Ali Pesaranghader, Touqir Sajed, Manasa Bharadwaj, Borislav Mavrin, Scott Sanner
Experimental results show that Late Fusion contrastive learning for Neural RIR outperforms all other contrastive IR configurations, Neural IR, and sparse retrieval baselines, thus demonstrating the power of exploiting the two-level structure in Neural RIR approaches as well as the importance of preserving the nuance of individual review content via Late Fusion methods.
no code implementations • 26 Jul 2023 • Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, Lucas Dixon
Inspired by recent successes of prompting paradigms for large language models (LLMs), we study their use for making recommendations from both item-based and language-based preferences in comparison to state-of-the-art item-based collaborative filtering (CF) methods.
no code implementations • 14 Jun 2023 • Griffin Floto, Mohammad Mahdi Abdollah Pour, Parsa Farinneya, Zhenwei Tang, Ali Pesaranghader, Manasa Bharadwaj, Scott Sanner
Text detoxification is a conditional text generation task aiming to remove offensive content from toxic text.
no code implementations • 9 Jun 2023 • Armin Toroghi, Griffin Floto, Zhenwei Tang, Scott Sanner
This work enables a new paradigm for using rich knowledge content and reasoning over indirect evidence as a mechanism for critiquing interactions with CRS.
no code implementations • 30 May 2023 • Ta Jiun Ting, Xiaocan Li, Scott Sanner, Baher Abdulhai
This suggests that the current graph convolutional methods may not be the best approach to traffic prediction and there is still room for improvement.
no code implementations • 29 May 2023 • Xiaocan Li, Ray Coden Mercurius, Ayal Taitler, Xiaoyu Wang, Mohammad Noaeen, Scott Sanner, Baher Abdulhai
Moreover, no existing studies have employed reinforcement learning for homogeneous flow rate optimization in microscopic simulation, where spatial characteristics, vehicle-level information, and metering realizations -- often overlooked in macroscopic simulations -- are taken into account.
1 code implementation • 26 May 2023 • Yudong Xu, Wenhao Li, Pashootan Vaezipoor, Scott Sanner, Elias B. Khalil
Although the state-of-the-art GPT-4 is unable to "reason" perfectly within non-language domains such as the 1D-ARC or a simple ARC subset, our study reveals that the use of object-based representations can significantly improve its reasoning ability.
no code implementations • 7 May 2023 • Aravinth Chembu, Scott Sanner
In this article, we define a generalized optimization framework for predictive clustering that admits different cluster definitions (arbitrary point assignment, closest center, and bounding box) and both regression and classification objectives.
1 code implementation • 23 Apr 2023 • Zhenwei Tang, Griffin Floto, Armin Toroghi, Shichao Pei, Xiangliang Zhang, Scott Sanner
In this work, we formulate the problem of recommendation with users' logical requirements (LogicRec) and construct benchmark datasets for LogicRec.
1 code implementation • 6 Apr 2023 • Siow Meng Low, Akshat Kumar, Scott Sanner
In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects.
no code implementations • 26 Nov 2022 • Xiaoyu Wang, Scott Sanner, Baher Abdulhai
Recent years have witnessed substantial growth in adaptive traffic signal control (ATSC) methodologies that improve transportation network efficiency, especially in branches leveraging artificial intelligence based optimization and control algorithms such as reinforcement learning as well as conventional model predictive control.
2 code implementations • 11 Nov 2022 • Ayal Taitler, Michael Gimelfarb, Jihwan Jeong, Sriram Gopalakrishnan, Martin Mladenov, Xiaotian Liu, Scott Sanner
We present pyRDDLGym, a Python framework for auto-generation of OpenAI Gym environments from RDDL declerative description.
1 code implementation • 8 Nov 2022 • Mathieu Tuli, Andrew C. Li, Pashootan Vaezipoor, Toryn Q. Klassen, Scott Sanner, Sheila A. McIlraith
Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language.
1 code implementation • 18 Oct 2022 • Yudong Xu, Elias B. Khalil, Scott Sanner
The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms.
1 code implementation • 7 Oct 2022 • Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner
Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy.
no code implementations • 23 Mar 2022 • Siow Meng Low, Akshat Kumar, Scott Sanner
This novel formulation of DRP learning as iterative lower bound optimization (ILBO) is particularly appealing because (i) each step is structurally easier to optimize than the overall objective, (ii) it guarantees a monotonically improving objective under certain theoretical conditions, and (iii) it reuses samples between iterations thus lowering sample complexity.
1 code implementation • 14 Mar 2022 • Ruiwen Li, Zheda Mai, Chiheb Trabelsi, Zhibo Zhang, Jongseong Jang, Scott Sanner
In this paper, we propose TransCAM, a Conformer-based solution to WSSS that explicitly leverages the attention weights from the transformer branch of the Conformer to refine the CAM generated from the CNN branch.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 17 Jan 2022 • Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek, Zheda Mai, Scott Sanner
Conversational Recommendation Systems (CRSs) have recently started to leverage pretrained language models (LM) such as BERT for their ability to semantically interpret a wide range of preference statement variations.
1 code implementation • NeurIPS 2021 • Yi Sui, Ga Wu, Scott Sanner
Explaining the influence of training data on deep neural network predictions is a critical tool for debugging models through data curation.
1 code implementation • 28 Nov 2021 • Zhibo Zhang, Jongseong Jang, Chiheb Trabelsi, Ruiwen Li, Scott Sanner, Yeonjeong Jeong, Dongsub Shim
Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification.
1 code implementation • 5 Oct 2021 • Yi Sui, Ga Wu, Scott Sanner
We additionally introduce a novel Frobenius norm-based contrastive learning objective to improve latent representational generalization. Empirically, we validate MAPSED on two publicly accessible urban crime datasets for spatiotemporal sparse event prediction, where MAPSED outperforms both classical and state-of-the-art deep learning models.
no code implementations • 2 Aug 2021 • Buser Say, Scott Sanner, Jo Devriendt, Jakob Nordström, Peter J. Stuckey
This document provides a brief introduction to learned automated planning problem where the state transition function is in the form of a binarized neural network (BNN), presents a general MaxSAT encoding for this problem, and describes the four domains, namely: Navigation, Inventory Control, System Administrator and Cellda, that are submitted as benchmarks for MaxSAT Evaluation 2021.
no code implementations • 14 Jun 2021 • Noah Patton, Jihwan Jeong, Michael Gimelfarb, Scott Sanner
The direct optimization of this empirical objective in an end-to-end manner is called the risk-averse straight-line plan, which commits to a sequence of actions in advance and can be sub-optimal in highly stochastic domains.
no code implementations • 29 May 2021 • Ruiwen Li, Zhibo Zhang, Jiani Li, Chiheb Trabelsi, Scott Sanner, Jongseong Jang, Yeonjeong Jeong, Dongsub Shim
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions.
no code implementations • NeurIPS 2021 • Michael Gimelfarb, André Barreto, Scott Sanner, Chi-Guhn Lee
Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making.
3 code implementations • 22 Mar 2021 • Zheda Mai, Ruiwen Li, Hyunwoo Kim, Scott Sanner
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting.
1 code implementation • 25 Jan 2021 • Zheda Mai, Ruiwen Li, Jihwan Jeong, David Quispe, Hyunwoo Kim, Scott Sanner
To better understand the relative advantages of various approaches and the settings where they work best, this survey aims to (1) compare state-of-the-art methods such as MIR, iCARL, and GDumb and determine which works best at different experimental settings; (2) determine if the best class incremental methods are also competitive in domain incremental setting; (3) evaluate the performance of 7 simple but effective trick such as "review" trick and nearest class mean (NCM) classifier to assess their relative impact.
no code implementations • 24 Oct 2020 • Zheda Mai, Ga Wu, Kai Luo, Scott Sanner
In order to capture multifaceted user preferences, existing recommender systems either increase the encoding complexity or extend the latent representation dimension.
3 code implementations • 31 Aug 2020 • Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, Jongseong Jang
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption.
no code implementations • 3 Aug 2020 • Jin Peng Zhou, Ga Wu, Zheda Mai, Scott Sanner
One-class collaborative filtering (OC-CF) is a common class of recommendation problem where only the positive class is explicitly observed (e. g., purchases, clicks).
1 code implementation • 11 Jul 2020 • Zheda Mai, Hyunwoo Kim, Jihwan Jeong, Scott Sanner
Continual learning is a branch of deep learning that seeks to strike a balance between learning stability and plasticity.
1 code implementation • 2 Jul 2020 • Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Resolving the exploration-exploitation trade-off remains a fundamental problem in the design and implementation of reinforcement learning (RL) algorithms.
no code implementations • 10 Jun 2020 • Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
We demonstrate the effectiveness of this approach for static optimization of smooth functions, and transfer learning in a high-dimensional supply chain problem with cost uncertainty.
no code implementations • 29 Feb 2020 • Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
In this paper, we assume knowledge of estimated source task dynamics and policies, and common sub-goals but different dynamics.
no code implementations • 23 Apr 2019 • Kasra Safari, Scott Sanner
Thus, it is critically important to query the Twitter API relative to the intended topical classifier in a way that minimizes the amount of negatively classified data retrieved.
no code implementations • 19 Apr 2019 • Buser Say, Scott Sanner, Sylvie Thiébaux
We then strengthen the linear relaxation of the underlying MILP model by introducing constraints to bound the reward function based on the precomputed reward potentials.
no code implementations • 5 Apr 2019 • Ga Wu, Buser Say, Scott Sanner
But there remains one major problem for the task of control -- how can we plan with deep network learned transition models without resorting to Monte Carlo Tree Search and other black-box transition model techniques that ignore model structure and do not easily extend to mixed discrete and continuous domains?
no code implementations • NeurIPS 2018 • Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee
Potential based reward shaping is a powerful technique for accelerating convergence of reinforcement learning algorithms.
no code implementations • 26 Nov 2018 • Buser Say, Scott Sanner
In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces.
no code implementations • 31 Aug 2018 • Yu Qing Zhou, Ga Wu, Scott Sanner, Putra Manggala
Many photography websites such as Flickr, 500px, Unsplash, and Adobe Behance are used by amateur and professional photography enthusiasts.
1 code implementation • ICLR 2019 • Ga Wu, Justin Domke, Scott Sanner
Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging.
no code implementations • NeurIPS 2017 • Ga Wu, Buser Say, Scott Sanner
Given recent deep learning results that demonstrate the ability to effectively optimize high-dimensional non-convex functions with gradient descent optimization on GPUs, we ask in this paper whether symbolic gradient optimization tools such as Tensorflow can be effective for planning in hybrid (mixed discrete and continuous) nonlinear domains with high dimensional state and action spaces?
no code implementations • 4 Jan 2017 • Roni Khardon, Scott Sanner
Lifted probabilistic inference (Poole, 2003) and symbolic dynamic programming for lifted stochastic planning (Boutilier et al, 2001) were introduced around the same time as algorithmic efforts to use abstraction in stochastic systems.
1 code implementation • 19 Feb 2016 • Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrian, Honglin Yu, Pascal Van Hentenryck
Modeling and predicting the popularity of online content is a significant problem for the practice of information dissemination, advertising, and consumption.
Social and Information Networks
2 code implementations • Proceedings of the 24th International Conference on World Wide Web 2015 • Suvash Sedhain, Aditya Krishna Menon, Scott Sanner, Lexing Xie
This paper proposes AutoRec, a novel autoencoder framework for collaborative filtering (CF).
Ranked #5 on Recommendation Systems on MovieLens 1M
no code implementations • 26 Sep 2013 • Luis Gustavo Vianna, Scott Sanner, Leliane Nunes de Barros
Recent advances in symbolic dynamic programming (SDP) combined with the extended algebraic decision diagram (XADD) data structure have provided exact solutions for mixed discrete and continuous (hybrid) MDPs with piecewise linear dynamics and continuous actions.
no code implementations • NeurIPS 2012 • Zahra Zamani, Scott Sanner, Pascal Poupart, Kristian Kersting
In recent years, point- based value iteration methods have proven to be extremely effective techniques for finding (approximately) optimal dynamic programming solutions to POMDPs when an initial set of belief states is known.
no code implementations • NeurIPS 2010 • Shengbo Guo, Scott Sanner, Edwin V. Bonilla
Bayesian approaches to preference elicitation (PE) are particularly attractive due to their ability to explicitly model uncertainty in users' latent utility functions.