Mathieu Seurin

@inproceedings{dornaika_2957,

title = {Semi-supervised Classification through Data and Label Graph Fusion},

author = {Fadi Dornaika and Jinan Charafeddine},

url = {https://ieeexplore.ieee.org/abstract/document/10401729},

issn = {ISBN 979-8-3503-0325-4},

year  = {2023},

date = {2023-12-01},

booktitle = {"2023 International Conference on Computer and Applications (ICCA)"},

pages = {pp. 1-6},

publisher = {IEEE},

address = {Cairo , Egypt},

abstract = {This study introduces a groundbreaking structure for semi-supervised learning based on graphs. Our technique provides an all-encompassing strategy that simultaneously tackles the challenges of label prediction and linear transformation. Specifically, the linear transformation we advocate is designed to forge a distinguishing subspace, thereby significantly compressing the data's dimensionality.In advancing semi-supervised learning techniques, our framework particularly focuses on effectively utilizing the intrinsic data configuration and the provisional labels related to the unlabeled examples in our possession. This distinctive methodology leads to a more sophisticated and discriminative form of linear transformation. Tests carried out on authentic image datasets clearly validate the efficiency of the method we advocate. These tests repeatedly show enhanced performance in contrast to semi-supervised strategies that address the fusion of data and label deduction in isolation.

keywords: {Estimation;Semisupervised learning;Iterative methods;Labeling;Graph-based semi-supervised learning;data graph;label graph;graph fusion;pattern recognition},

URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10401729&isnumber=10401330},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{seurin_2689,

title = {Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness},

author = {Mathieu Seurin and Florian Strub and Philippe Preux and Olivier Pietquin},

url = {https://www.ijcai.org/proceedings/2021/0406.pdf},

issn = {9781713836322},

year  = {2021},

date = {2021-08-01},

booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21)},

address = {Montreal, Canada},

abstract = {Sparse rewards are double-edged training signals in

reinforcement learning: easy to design but hard to

optimize. Intrinsic motivation guidances have thus

been developed toward alleviating the resulting ex-

ploration problem. They usually incentivize agents

to look for new states through novelty signals. Yet,

such methods encourage exhaustive exploration of

the state space rather than focusing on the environ-

ment's salient interaction opportunities. We pro-

pose a new exploration method, called Don't Do

What Doesn't Matter (DoWhaM), shifting the em-

phasis from state novelty to state with relevant ac-

tions. While most actions consistently change the

state when used, e.g. moving the agent, some ac-

tions are only effective in specific states, e.g., open-

ing a door, grabbing an object. DoWhaM detects

and rewards actions that seldom affect the environ-

ment. We evaluate DoWhaM on the procedurally-

generated environment MiniGrid, against state-of-

the-art methods. Experiments consistently show

that DoWhaM greatly reduces sample complexity,

installing the new state-of-the-art in MiniGrid.},

note = {Montreal-themed Virtual Reality, 19th -26th August, 2021.  30th International Joint Conference on Artificial Intelligence (IJCAI-21)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cideron_2687,

title = {HIGhER: Improving instruction following with Hindsight Generation for Experience Replay},

author = {Geoffrey Cideron and Mathieu Seurin and Florian Strub and Olivier Pietquin},

url = {https://ieeexplore.ieee.org/abstract/document/9308603},

issn = {978-1-7281-2547-3},

year  = {2020},

date = {2020-01-01},

booktitle = {2020 IEEE Symposium Series on Computational Intelligence (SSCI)},

address = {Canberra, Australia},

abstract = {Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language understanding and reinforcement learning in even simple instruction following scenarios. This joint learning problem is alleviated through expert demonstrations, auxiliary losses, or neural inductive biases. In this paper, we propose an orthogonal approach called Hindsight Generation for Experience Replay (HIGhER) that extends the Hindsight Experience Replay approach to the language-conditioned policy setting. Whenever the agent does not fulfill its instruction, HIGhER learns to output a new directive that matches the agent trajectory, and it relabels the episode with a positive reward. To do so, HIGhER learns to map a state into an instruction by using past successful trajectories, which removes the need to have external expert interventions to relabel episodes as in vanilla HER. We show the efficiency of our approach in the BabyAI environment, and demonstrate how it complements other instruction following methods.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{seurin_2688,

title = {A Machine of Few Words Interactive Speaker Recognition with Reinforcement Learning},

author = {Mathieu Seurin and Florian Strub and Philippe Preux and Olivier Pietquin},

url = {http://www.interspeech2020.org/uploadfile/pdf/Thu-2-7-7.pdf},

issn = {9781713820697},

year  = {2020},

date = {2020-01-01},

booktitle = {Interspeech 2020?Proceedings},

address = {Shanghai, China},

abstract = {Speaker recognition is a well known and studied task in the

speech processing domain. It has many applications, either for

security or speaker adaptation of personal devices. In this pa-

per, we present a new paradigm for automatic speaker recogni-

tion that we call Interactive Speaker Recognition (ISR). In this

paradigm, the recognition system aims to incrementally build a

representation of the speakers by requesting personalized utter-

ances to be spoken in contrast to the standard text-dependent or

text-independent schemes. To do so, we cast the speaker recog-

nition task into a sequential decision-making problem that we

solve with Reinforcement Learning. Using a standard dataset,

we show that our method achieves excellent performance while

using little speech signal amounts. This method could also be

applied as an utterance selection mechanism for building speech

synthesis systems.},

note = {October 25-29, 2020, Shanghai, China},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}