REVIEW 7 cited by
Understanding Black-box Predictions via Influence Functions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. To scale up influence functions to modern machine learning settings, we develop a simple, efficient implementation that requires only oracle access to gradients and Hessian-vector products. We show that even on non-convex and non-differentiable models where the theory breaks down, approximations to influence functions can still provide valuable information. On linear models and convolutional neural networks, we demonstrate that influence functions are useful for multiple purposes: understanding model behavior, debugging models, detecting dataset errors, and even creating visually-indistinguishable training-set attacks.
Forward citations
Cited by 7 Pith papers
-
Influence Dynamics and Stagewise Data Attribution
Using Bayesian influence functions and singular learning theory, the authors show that a sample's influence on a model varies non-monotonically over training, peaking and flipping sign at phase transitions.
-
Implicit Reasoning Steering via Concept Chaining
Reinforcement-learning-optimized concept-chain paragraphs covertly steer language-model multiple-choice preferences after continued pretraining, with far lower detectability than direct paraphrases.
-
Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence ana...
-
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
GUDA approximates leave-one-group-out counterfactual models with unlearning and ranks group influence by ELBO differences.
-
Evaluating the Dynamics of Membership Privacy in Deep Learning
Per-sample membership vulnerability is established early in training, especially for hard-to-learn examples, and can be tracked on an FPR-TPR plane.
-
How to Protect Models against Adversarial Unlearning?
A 'healing' procedure that uses similar real examples as surrogates for unlearned data during fine-tuning mitigates accuracy loss from machine unlearning in several classification benchmarks.
-
When unlearning is free: leveraging low influence points to reduce computational costs
Low-influence training points can be dropped from forget/retain sets before unlearning, cutting runtime up to ~50% with little measured loss in accuracy or MIA-based privacy.
Discussion (0). Sign in to comment.