CoLLAs 2024

53 papers

A Contrastive Symmetric Forward-Forward Algorithm (SFFA) for Continual Learning Tasks Erik B Terres-Escudero, Javier Del Ser, Pablo Garcia-Bringas

Adaptive Action Advising with Different Rewards Yue Guo, Xijia Zhang, Simon Stepputtis, Joseph Campbell, Katia P. Sycara

An Empirical Analysis of Forgetting in Pre-Trained Models with Incremental Low-Rank Updates Albin Soutif, Simone Magistri, Joost van de Weijer, Andrew D. Bagdanov

ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning Hosung Lee, Sejin Kim, Seungpil Lee, Sanha Hwang, Jihwan Lee, Byung-Jun Lee, Sundong Kim

Automatic Pruning of Fine-Tuning Datasets for Transformer-Based Language Models Sayed Mohammadreza Tayaranian Hosseini, Seyyed Hasan Mozafari, Brett H. Meyer, James J. Clark, Warren J. Gross

Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning Fahad Sarfraz, Bahram Zonooz, Elahe Arani

Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation Pedro Vianna, Muawiz Sajjad Chaudhary, Paria Mehrbod, An Tang, Guy Cloutier, Guy Wolf, Michael Eickenberg, Eugene Belilovsky

Chunking: Continual Learning Is Not Just About Distribution Shift Thomas L Lee, Amos Storkey

Compositional Interfaces for Compositional Generalization Jelena Luketina, Jack Lanchantin, Sainbayar Sukhbaatar, Arthur Szlam

Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation Amir El-Ghoussani, Julia Hornauer, Gustavo Carneiro, Vasileios Belagiannis

Continual Learning for Unsupervised Concept Bottleneck Discovery Luca Salvatore Lorello, Marco Lippi, Stefano Melacci

Continual Learning of Diffusion Models with Generative Distillation Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M van de Ven

Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning Hayato Watahiki, Ryo Iwase, Ryosuke Unno, Yoshimasa Tsuruoka

Decoupled Prompt-Adapter Tuning for Continual Activity Recognition Di Fu, Thanh Vinh Vo, Haozhe Ma, Tze-Yun Leong

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning Norman Di Palo, Leonard Hasenclever, Jan Humplik, Arunkumar Byravan

Disentangling the Causes of Plasticity Loss in Neural Networks Clare Lyle, Zeyu Zheng, Khimya Khetarpal, Hado van Hasselt, Razvan Pascanu, James Martens, Will Dabney

Enhanced Label Propagation Through Affinity Matrix Fusion for Source-Free Domain Adaptation Li Guo, Yuxuan Xia, Shengjie Wang

From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim, Bernard Ghanem, Philip Torr, Adel Bibi

Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation Yao Ma, Samuel Louvan, Zhunxuan Wang

GRASP: A Rehearsal Policy for Efficient Online Continual Learning Md Yousuf Harun, Jhair Gallardo, Junyu Chen, Christopher Kanan

Hadamard Domain Training with Integers for Class Incremental Quantized Learning Martin Schiemer, Clemens JS Schaefer, Mark James Horeni, Yu Emma Wang, Juan Ye, Siddharth Joshi

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization Sebastian Dziadzio, Çagatay Yildiz, Gido M. Ven, Tomasz Trzcinski, Tinne Tuytelaars, Matthias Bethge

Integrating Present and past in Unsupervised Continual Learning Yipeng Zhang, Laurent Charlin, Richard Zemel, Mengye Ren

iWISDM: Assessing Instruction Following in Multimodal Models at Scale Xiaoxuan Lei, Lucas Gomez, Hao Yuan Bai, Pouya Bashivan

Keep Moving: Identifying Task-Relevant Subspaces to Maximise Plasticity for Newly Learned Tasks Daniel Anthes, Sushrut Thorat, Peter König, Tim C Kietzmann

Label Augmentation for Neural Networks Robustness Fatemeh Amerehi, Patrick Healy

Learning to Learn Without Forgetting Using Attention Anna Vettoruzzo, Joaquin Vanschoren, Mohamed-Rafik Bouguelia, Thorsteinn S. Rögnvaldsson

Less Is More: Summarizing Patch Tokens for Efficient Multi-Label Class-Incremental Learning Thomas De Min, Massimiliano Mancini, Stéphane Lathuilière, Subhankar Roy, Elisa Ricci

Local vs Global Continual Learning Giulia Lanzillotta, Sidak Pal Singh, Benjamin F Grewe, Thomas Hofmann

Maintaining Plasticity in Continual Learning via Regenerative Regularization Saurabh Kumar, Henrik Marklund, Benjamin Van Roy

Masked Autoencoders Are Efficient Continual Federated Learners Subarnaduti Paul, Lars-Joel Frey, Roshni Ramanna Kamath, Kristian Kersting, Martin Mundt

Memory Head for Pre-Trained Backbones in Continual Learning Matteo Tiezzi, Federico Becattini, Simone Marullo, Stefano Melacci

Mitigating Interference in the Knowledge Continuum Through Attention-Guided Incremental Learning Prashant Shivaram Bhat, Bharath Chennamkulam Renjith, Elahe Arani, Bahram Zonooz

On the Limitation and Experience Replay for GNNs in Continual Learning Junwei Su, Difan Zou, Chuan Wu

Optimizing the Learning Rate for the Online Training of Neural Networks Lucas Cazzonelli, Cedric Kulbach, Steffen Thoma

PANDAS: Prototype-Based Novel Class Discovery and Detection Tyler L. Hayes, César Roberto de Souza, Namil Kim, Jiwon Kim, Riccardo Volpi, Diane Larlus

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents Safa Alver, Ali Rahimi-Kalahroudi, Doina Precup

Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning Cameron Ethan Taylor, Vassilis Vassiliades, Constantine Dovrolis

POWN: Prototypical Open-World Node Classification Marcel Hoffmann, Lukas Galke, Ansgar Scherp

Probabilistic Test-Time Generalization by Variational Neighbor-Labeling Sameer Ambekar, Zehao Xiao, Jiayi Shen, Xiantong Zhen, Cees G. M. Snoek

Reflecting on the State of Rehearsal-Free Continual Learning with Pretrained Models Lukas Thede, Karsten Roth, Olivier J Henaff, Matthias Bethge, Zeynep Akata

Replaying with Realistic Latent Vectors in Generative Continual Learning Hyemin Jeong, Seong-Woong Kim, Dong-Wan Choi

Simplified Priors for Object-Centric Learning Vihang Prakash Patil, Andreas Radler, Daniel Klotz, Sepp Hochreiter

Stable Update of Regression Trees Morten Blørstad, Berent Ånund Strømnes Lunde, Nello Blaser

Statistical Context Detection for Deep Lifelong Reinforcement Learning Jeffery Dick, Saptarshi Nath, Christos Peridis, Eseoghene Ben-Iwhiwhu, Soheil Kolouri, Andrea Soltoggio

Sub-Goal Distillation: A Method to Improve Small Language Agents Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar, Marc-Alexandre Côté

Subspace-Configurable Networks Dong Wang, Olga Saukh, Xiaoxi He, Lothar Thiele

SymbolicAI: A Framework for Logic-Based Approaches Combining Generative Models and Solvers Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner, Werner Zellinger, Sepp Hochreiter

T-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making William Yue, Bo Liu, Peter Stone

The Empirical Impact of Forgetting and Transfer in Continual Visual Odometry Paolo Cudrano, Xiaoyu Luo, Matteo Matteucci

Tomorrow Brings Greater Knowledge: Large Language Models Join Dynamic Temporal Knowledge Graphs Christian Di Maio, Andrea Zugarini, Francesco Giannini, Marco Maggini, Stefano Melacci

Towards More Diverse Evaluation of Class Incremental Learning: Representation Learning Perspective Sungmin Cha, Jihwan Kwak, Dongsub Shim, Hyunwoo Kim, Moontae Lee, Honglak Lee, Taesup Moon

Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation Jihwan Kwak, Sungmin Cha, Taesup Moon