论文检索

William St-Arnaud, Margarida Carvalho, Golnoosh Farnadi

Generative Flow Networks, known as GFlowNets, have been introduced in recent times, presenting an exciting possibility for neural networks to model distributions across various data structures. In this paper, we broaden their applicability to encompass scenarios where the data structures are optimal solutions of a combinatorial problem. Concretely, we propose the use of GFlowNets to learn the distribution of optimal solutions for kidney exchange problems (KEPs), a generalized form of matching problems involving cycles.

Jan Sobotka, Petr Šimánek

Modern machine learning heavily relies on optimization, and as deep learning models grow more complex and data-hungry, the search for efficient learning becomes crucial. Learned optimizers disrupt traditional handcrafted methods such as SGD and Adam by learning the optimization strategy itself, potentially speeding up training. However, the learned optimizers' dynamics are still not well understood. To remedy this, our work explores their optimization trajectories from the perspective of network architecture symmetries and proposed parameter update distributions.

Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg

In this evolving era of machine learning security, membership inference attacks have emerged as a potent threat to the confidentiality of sensitive data. In this attack, adversaries aim to determine whether a particular point was used during the training of a target model. This paper proposes a new method to gauge a data point’s membership in a model’s training set. Instead of correlating loss with membership, as is traditionally done, we have leveraged the fact that training examples generally exhibit higher confidence values when classified into their actual class. During training, the model is essentially being ’fit’ to the training data and might face particular difficulties in generalization to unseen data. This asymmetry leads to the model achieving higher confidence on the training data as it exploits the specific patterns and noise present in the training data. Our proposed approach leverages the confidence values generated by the machine-learning model. These confidence values provide a probabilistic measure of the model’s certainty in its predictions and can further be used to infer the membership of a given data point. Additionally, we also introduce another variant of our method that allows us to carry out this attack without knowing the ground truth(true class) of a given data point, thus offering an edge over existing label-dependent attack methods.

Akshit Singh

Generative Artificial Intelligence (AI) has garnered significant attention for its remarkable ability to generate text, images, and other forms of content. However, an inherent and increasingly concerning issue within generative AI systems is bias. These AI models often exhibit an Anglo-centric bias and tend to overlook the importance of diversity. This can be attributed to their training on extensive datasets sourced from the internet, which inevitably inherit the biases present in those data sources. Employing these datasets leads to AI-generated content that mirrors and perpetuates existing biases, encompassing various aspects such as gender, ethnic and cultural stereotypes. Addressing bias in generative AI is a complex challenge that necessitates substantial efforts. In order to tackle this issue, we propose a methodology for constructing moderately sized datasets with a social inclination. These datasets can be employed to rectify existing imbalances in datasets or to train models to generate socially inclusive material. Additionally, we present preliminary findings derived from training our model on these socially inclined datasets.

Wenzheng Shu, Yanlong Huang, Wenxin Tai, Zhangtao Cheng, Bei Hui, Goce Trajcevski

Trip recommendation aims to plan user’s travel based on their specified preferences. Traditional heuristic and statistical approaches often fail to capture the intricate nuances of user intentions, leading to subpar performance. Recent deep-learning methods show attractive accuracy but struggle to generate faithful trajectories that match user intentions. In this work, we propose a DDPM-based incremental knowledge injection module to ensure the faithfulness of the generated trajectories. Experiments on two datasets verify the effectiveness of our approach.

Takumu Shimizu, Ryota Higa, Katsuhide Fujita, Shinji Nakadai

We propose an automated negotiation for a reinforcement learning agent to adapt the agent to unexpected situations such as demand changes in supply chain management (SCM). Existing studies that consider reinforcement learning and SCM assume a centralized environment where the coordination of chain components is hierarchical rather than through negotiations between agents. This study focused on a negotiation agent that considered the value function of reinforcement learning for SCM as its utility function in automated negotiation. We demonstrated that the proposed approach could avoid inventory shortages under increased demand requests from the terminal customer.

Devan Shah, Ruoqi Huang, Tingting Chen, Murtuza Jadliwala

Current practice of mobility scooter user authentication using physical keys and traditional password-based one-time security mechanisms cannot meet the needs of many mobility scooter riders, especially senior citizens having issues in recalling memory. Now seamless authentication approaches are needed to provide ongoing protection for mobility scooters against takeovers and unauthorized access. Existing continuous authentication techniques do not work well in a mobility scooter setting due to issues such as user comfort, deployment cost and enrollment time, among others. In that direction, our contributions in this research effort are two-fold: (i) we propose a novel system that incorporates advances in few-shot learning, hierarchical processing, and contextual embedding to establish continuous authentication for mobility scooter riders using only posture data. This security system, trained on data collected from real mobility scooter riders, demonstrates quick enrollment and easy deployability, while successfully serving as an unobtrusive first layer of security. (ii) we provide to the research community the largest publicly available repository of mobility scooter riders' body key-points data to enable further research in this direction.

Ryan Schuerkamp, Xinyu Li, Brian Kunzer, Leonard S. Weiss, Hernando Gómez, Francis X. Guyette, Michael R. Pinsky, Artur Dubrawski

Fluid resuscitation is an initial treatment frequently employed to treat shock, restore lost blood, protect tissues from injury, and prevent organ dysfunction in critically ill patients. However, it is not without risk (e.g., overly aggressive resuscitation may cause organ damage and even death). We leverage machine learning models trained to assess sufficiency of resuscitation in laboratory animals subjected to induced hemorrhage and transfer them to use with human trauma patients. Our key takeaway is that animal experiments and models can inform human healthcare, especially when human data is limited or when collecting relevant human data via potentially harmful protocols is unfeasible.

Richard Sances, Olivera Kotevska, Paul Laiu

As data privacy issues grow, finding the best privacy preservation algorithm for each situation is increasingly essential. This research has focused on understanding the frequency oracles (FO) privacy preservation algorithms. FO conduct the frequency estimation of any value in the domain. The aim is to explore how each can be best used and recommend which one to use with which data type. We experimented with different data scenarios and federated learning settings. Results showed clear guidance on when to use a specific algorithm.

Sehyun Ryu, Hosung Joo, Jonggyu Jang, Hyun Jong Yang

Recent research has shown a growing interest in per-instance differential privacy (pDP), highlighting the fact that each data instance within a dataset may incur distinct levels of privacy loss. However, conventional additive noise mechanisms apply identical noise to all query outputs, thereby deteriorating data statistics. In this study, we propose an instance-wise Laplace mechanism, which adds non-identical Laplace noises to the query output for each data instance. A challenge arises from the complex interaction of additive noise, where the noise introduced to individual instances impacts the pDP of other instances, adding complexity and resilience to straightforward solutions. To tackle this problem, we introduce an instance-wise Laplace mechanism algorithm via deep reinforcement learning and validate its ability to better preserve data statistics on a real dataset, compared to the original Laplace mechanism.

Jeremy Rutter, Maneesh Reddy Chamakura, Justin Delgado, Gene Louis Kim

Our work explores bridging the gap between large language models and text-to-image models to create a tool for quickly and easily generating high quality images from a given concept. In our experiments we successfully improved image quality with only a preliminary utilization of the available resources for finetuning.

Brandon Rozek, Junkyu Lee, Harsha Kokel, Michael Katz, Shirin Sohrabi

Partially observable Markov decision processes (POMDPs) challenge reinforcement learning agents due to incomplete knowledge of the environment. Even assuming monotonicity in uncertainty, it is difficult for an agent to know how and when to stop exploring for a given task. In this abstract, we discuss how to use hierarchical reinforcement learning (HRL) and AI Planning (AIP) to improve exploration when the agent knows possible valuations of unknown predicates and how to discover them. By encoding the uncertainty in an abstract planning model, the agent can derive a high-level plan which is then used to decompose the overall POMDP into a tree of semi-POMDPs for training. We evaluate our agent's performance on the MiniGrid domain and show how guided exploration may improve agent performance.

Syed Sameen Ahmad Rizvi, Aryan Seth, Pratik Narang

Facial Expression Recognition (FER) is an extensively explored research problem in the domain of computer vision and artificial intelligence. FER, a supervised learning problem, requires significant training data representative of multiple socio-cultural demographic attributes. However, most of the FER dataset consists of images annotated by humans, which propagates individual and demographic biases. This work attempts to mitigate this bias using representation learning based on latent spaces, thereby increasing a deep learning model's fairness and overall accuracy.

Célian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl

Seq-to-seq generative models recently gained attention for solving the relation extraction task. By approaching this problem as an end-to-end task, they surpassed encoder-based-only models. Little research investigated the effects of the output syntaxes on the training process of these models. Moreover, a limited number of approaches were proposed for extracting ready-to-load knowledge graphs following the RDF standard. In this paper, we consider that a set of triples can be linearized in many different ways, and we evaluate the combined effect of the size of the language models and different RDF syntaxes on the task of relation extraction from Wikipedia abstracts.

Aryaman Rao, Parth Singh, Dinesh Kumar Vishwakarma, Mukesh Prasad

Influence Maximization is the task of selecting optimal nodes maximising the influence spread in social networks. This study proposes a Discretized Quantum-based Salp Swarm Algorithm (DQSSA) for optimizing influence diffusion in social networks. By discretizing meta-heuristic algorithms and infusing them with quantum-inspired enhancements, we address issues like premature convergence and low efficacy. The proposed method, guided by quantum principles, offers a promising solution for Influence Maximisation. Experiments on four real-world datasets reveal DQSSA's superior performance as compared to established cutting-edge algorithms.

Md Maklachur Rahman, Tracy Hammond

Despite Siamese trackers’ substantial potential, they offer sub-optimal tracking performance in low-resolution (LR) contexts. We introduce a Random Noise Salient Feature Fusion Learning Network to address this issue. This method integrates random noise-infused feature maps into a similaritylearning matching model. This integration acts as an effective regularization technique, enhancing the network’s generalization capabilities in LR environments. Additionally, by integrating attention mechanisms, we enhance the discriminative ability of the network, assigning more weights to important features. This directs the network’s focus toward the most salient regions of the feature map, ensuring improved accuracy without a significant increase in parameter overhead, and maintaining a high operating speed. To validate the effectiveness of our method, we performed qualitative and quantitative comparisons with state-of-the-art (SOTA) trackers.

Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński, Przemysław Spurek

Implicit field representations offer an effective way of generating 3D object shapes. They leverage an implicit decoder (IM-NET) trained to take a 3D point coordinate concatenated with a shape encoding and to output a value indicating whether the point is outside the shape. This approach enables the efficient rendering of visually plausible objects but also has some significant limitations, resulting in a cumbersome training procedure and empty spaces within the rendered mesh. In this paper, we introduce a new HyperCube architecture based on interval arithmetic that enables direct processing of 3D voxels, trained using a hypernetwork paradigm to enforce model convergence. The code is available at https://github.com/mproszewska/hypercube.

Jiaming Pei, Wei Li, Lukun Wang

Communication overhead remains a significant challenge in federated learning due to frequent global model updates. Essentially, the update of the global model can be viewed as knowledge transfer. We aim to transfer more knowledge through a compact model while reducing communication overhead. In our study, we introduce a federated learning framework where clients pre-train large models locally and the server initializes a compact model to communicate. This compact model should be light in size but still have enough knowledge to refine the global model effectively. We facilitate the knowledge transfer from local to global models based on pre-training outcomes. Our experiments show that our approach significantly reduce communication overhead without sacrificing accuracy.

Morgan Payette, Charlotte Curtis

Rendering of complex scenes from software such as Blender is time consuming, but corresponding auxiliary data such as depth or object segmentation maps are relatively fast to generate. The auxiliary data also provides a wealth of information for tasks such as optical flow prediction. In this paper we present the QuickRender dataset, a collection of procedurally generated scenes rendered into over 5,000 sequential image triplets along with accompanying auxiliary data. The goal of this dataset is to provide a diversity of scenes and motion while maintaining realistic behaviours. A sample application using this dataset to perform single image super resolution is also presented. The dataset and related source code can be found at https://github.com/MP-mtroyal/MetaSRGAN.

June-Young Park, Jae-Ryung Hong, Min-Hye Kim, Tae-Joon Kim

Anomaly detection is a critical task across various domains. Fundamentally, anomaly detection models offer methods to identify unusual patterns that do not align with expected behaviors. Notably, in the medical field, detecting anomalies in medical imagery or biometrics can facilitate early diagnosis of diseases. Consequently, we propose the Skip-GANomaly++ model, an enhanced and more efficient version of the conventional anomaly detection models. The proposed model's performance was evaluated through comparative experiments. Experimental results demonstrated superior performance across most classes compared to the previous models.